Logo: to the web site of Uppsala University

uu.sePublications from Uppsala University
Change search
Refine search result
123456 1 - 50 of 254
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Ahmad, Awais
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Cajander, Åsa
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Johansson, Birgitta
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Immunology, Genetics and Pathology, Experimental and Clinical Oncology.
    Ehrsson, Ylva Tiblom
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Otolaryngology and Head and Neck Surgery.
    Langegård, Ulrica
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Immunology, Genetics and Pathology, Experimental and Clinical Oncology.
    Designing for Human Well-Being: A Case Study with Informal Caregivers of Individuals with Cancer2022In: Studies in Health Technology and Informatics, ISSN 0926-9630, E-ISSN 1879-8365, Vol. 294, p. 214-218Article in journal (Refereed)
    Abstract [en]

    Informal Caregivers such as a spouse, other close relatives or friends of cancer patients can play an essential role in home-based treatment and care. However, the informal caregivers might not be prepared for this responsibility, and they might have several unmet requirements for taking care of patients in the home environment. The informal caregivers’ physical, social and psychological health is also profoundly affected due to the health conditions of their relatives. We propose a User-centred Positive Design as a hybrid framework by merging the traditional User-cantered design and positive design frameworks to enhance the informal caregivers’ subjective well-being. Our ongoing project (Carer-eSupport) will be used as a case study, and its main objective is to co-create and evaluate a web-based support system for informal caregivers of people with cancer. The proposed framework can be used for the design and development of health information systems with a special focus on users’ wellbeing and positive emotions.

    Download full text (pdf)
    fulltext
  • 2.
    Ahmad, Awais
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Premanandan, Shweta
    Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Social Sciences, Department of Informatics and Media. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Cajander, Åsa
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computing Education Research. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Social Sciences, Department of Informatics and Media.
    Improving Remote Examination Formats: Addressing Challenges and Providing Recommendations for University Educators in the Age of ChatGPT2024Conference paper (Refereed)
    Abstract [en]

    The availability of Large Language Models (LLM), such as the widely accessible ChatGPT, has raised concerns regarding the reliability of assessment formats in university education. This presentation sheds light on the potential impact of ChatGPT on existing remote examination formats and offers recommendations to overcome associated challenges. Through interviews with three computer science educators and an analysis of insights from blog posts, social media platforms, and academic forums, we gathered diverse opinions and experiences related to ChatGPT's impact on university assessment formats. Our findings reveal challenges, particularly in cheating prevention, prompting the need for educators to adapt their teaching methods to this evolving landscape. While GPT performs well in answering open-ended questions, it struggles with calculations and problem-solving, with multiple-choice questions posing additional challenges. Incorporating interactive activities and oral examinations should be prioritized in this context. As ChatGPT gains traction, institutions must address concerns to maintain academic integrity.

  • 3.
    Ahmad, Awais
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Premanandan, Shweta
    Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Social Sciences, Department of Informatics and Media.
    Langegård, Ulrica
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Immunology, Genetics and Pathology, Cancer precision medicine.
    Cajander, Åsa
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Johansson, Birgitta
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Immunology, Genetics and Pathology, Cancer precision medicine. Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Healthcare Sciences and e-Health.
    Carlsson, Maria E.
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Public Health and Caring Sciences, Lifestyle and rehabilitation in long term illness.
    Ehrsson, Ylva Tiblom
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Otolaryngology and Head and Neck Surgery.
    Positive Design Framework for Carer-eSupport: A Qualitative Study to Support Informal Caregivers of Patients with Head and Neck Cancer in Sweden2023In: JMIR Cancer, E-ISSN 2369-1999, Vol. 9, article id e45748Article in journal (Refereed)
    Abstract [en]

    Background: Informal caregivers of patients with head and neck cancer (HNC), such as the patient’s spouse, other close relatives, or friends, can play an important role in home-based treatment and health care. Research shows that informal caregivers are usually unprepared for this responsibility and need support with taking care of patients and other daily life activities. These circumstances place them in a vulnerable position, and their well-being may be compromised. This study is part of our ongoing project Carer eSupport, which aims to develop a web-based intervention to facilitate informal caregivers in the home environment.

    Objective: This study aimed to explore the situation and context of informal caregivers of patients with HNC and their needs for designing and developing a web-based intervention (Carer eSupport). In addition, we proposed a novel framework for the development of a web-based intervention aimed at promoting the well-being of informal caregivers. Methods: Focus groups were conducted with 15 informal caregivers and 13 healthcare professionals. Both informal caregivers and healthcare professionals were recruited from 3 university hospitals in Sweden. We adopted a thematic data analysis process to analyze the data.

    Results: We investigated informal caregivers’ needs, critical factors for adoption, and desired functionalities of Carer eSupport.A total of 4 major themes, including information, web-based forum, virtual meeting place, and chatbot, emerged and were discussed by informal caregivers and health care professionals for Carer eSupport. However, most study participants did not like the idea of a chatbot for asking questions and retrieving information and expressed their concerns such as a lack of trust in robotic technologies and missing human contact while communicating with chatbots. The results from the focus groups were discussed through the lens of positive design research approaches.

    Conclusions: This study provided an in-depth understanding of informal caregivers’ contexts and their preferred functions for a web-based intervention (Carer eSupport). Using the theoretical foundation of designing for well-being and positive design in the informal caregiving context, we proposed a positive design framework to support informal caregivers’ well-being. Our proposed framework might be helpful for human-computer interaction and user experience researchers to design meaningful health interventions with a clear focus on users’ well-being and positive emotions, especially for informal caregivers of patients with HNC.

    Download full text (pdf)
    fulltext
  • 4.
    Ahmad, Nouman
    et al.
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology.
    Dahlberg, Hugo
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology.
    Jönsson, Hanna
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology.
    Tarai, Sambit
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology.
    Guggilla, Rama Krishna
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology.
    Strand, Robin
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Lundström, Elin
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology.
    Bergstrom, Goran
    Univ Gothenburg, Inst Med, Sahlgrenska Acad, Dept Mol & Clin Med, Gothenburg, Sweden.;Sahlgrens Univ Hosp, Dept Clin Physiol, Reg Vastra Gotaland, Gothenburg, Sweden..
    Ahlström, Håkan
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology. Antaros Med, Mölndal, Sweden..
    Kullberg, Joel
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology. Antaros Med, Mölndal, Sweden..
    Voxel-wise body composition analysis using image registration of a three-slice CT imaging protocol: methodology and proof-of-concept studies2024In: Biomedical engineering online, E-ISSN 1475-925X, Vol. 23, no 1, article id 42Article in journal (Refereed)
    Abstract [en]

    Background Computed tomography (CT) is an imaging modality commonly used for studies of internal body structures and very useful for detailed studies of body composition. The aim of this study was to develop and evaluate a fully automatic image registration framework for inter-subject CT slice registration. The aim was also to use the results, in a set of proof-of-concept studies, for voxel-wise statistical body composition analysis (Imiomics) of correlations between imaging and non-imaging data.Methods The current study utilized three single-slice CT images of the liver, abdomen, and thigh from two large cohort studies, SCAPIS and IGT. The image registration method developed and evaluated used both CT images together with image-derived tissue and organ segmentation masks. To evaluate the performance of the registration method, a set of baseline 3-single-slice CT images (from 2780 subjects including 8285 slices) from the SCAPIS and IGT cohorts were registered. Vector magnitude and intensity magnitude error indicating inverse consistency were used for evaluation. Image registration results were further used for voxel-wise analysis of associations between the CT images (as represented by tissue volume from Hounsfield unit and Jacobian determinant) and various explicit measurements of various tissues, fat depots, and organs collected in both cohort studies.Results Our findings demonstrated that the key organs and anatomical structures were registered appropriately. The evaluation parameters of inverse consistency, such as vector magnitude and intensity magnitude error, were on average less than 3 mm and 50 Hounsfield units. The registration followed by Imiomics analysis enabled the examination of associations between various explicit measurements (liver, spleen, abdominal muscle, visceral adipose tissue (VAT), subcutaneous adipose tissue (SAT), thigh SAT, intermuscular adipose tissue (IMAT), and thigh muscle) and the voxel-wise image information.Conclusion The developed and evaluated framework allows accurate image registrations of the collected three single-slice CT images and enables detailed voxel-wise studies of associations between body composition and associated diseases and risk factors.

    Download full text (pdf)
    FULLTEXT01
  • 5.
    Akkuzu, Anastasia
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Castellano, Ginevra
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Calvo-Barajas, Natalia
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Behavioural Observations as Objective Measures of Trust in Child-Robot Interaction: Mutual Gaze2023In: HAI '23: Proceedings of the 11th International Conference on Human-Agent Interaction, Association for Computing Machinery (ACM), 2023, p. 452-454Conference paper (Refereed)
    Abstract [en]

    In developing a computational model of trust, this paper summarises the findings in a previous study exploring mutual gaze as a behavioural parameter of social trust and liking [1]. Drawing on the data collected in a related paper [6], which provides us with video clips of children interacting with a robot during a collaborative storytelling game, we look at the interactions between metrics assessing social trust and liking, and the development of mutual gaze as an objective measure of social trust and liking. We achieve this through several statistical analyses between the percent of mutual gaze in each interaction, scores from social trust and liking metrics, age of the participant, and duration. The findings of our study support the use of mutual gaze as an objective measure for liking, but there is still not sufficient evidence to support the use of mutual gaze as an objective measure to identify and capture social trust as a whole. Furthermore, interaction context impacts the amount of mutual gaze in an interaction, and the age of the participant has an impact on the amount of mutual gaze that occurs.

  • 6.
    Alenljung, Beatrice
    et al.
    Univ Skovde, Hogskolevagen, S-54128 Skovde, Sweden..
    Lindblom, Jessica
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Zaragoza-Sundqvist, Maximiliano
    AstraZeneca R&D, S-43183 Molndal, Sweden..
    Hanna, Atieh
    Volvo AB, S-40508 Gothenburg, Sweden..
    Towards a Framework of Human-Robot Interaction Strategies from an Operator 5.0 Perspective2023In: Advances in Manufacturing Technology XXXVI / [ed] Andrew Thomas;Lyndon Murphy;Wyn Morris;Vincenzo Dispenza;David Jones, IOS Press, 2023, Vol. 44, p. 81-86Conference paper (Refereed)
    Abstract [en]

    The industrial transition to Industrie 4.0 and subsequently Industrie 5.0 requires robots to be able to share physical and social space with humans in such a way that interaction and coexistence are positively experienced by the humans and where it is possible for the human and the robot to mutually perceive, interpret and act on each other's actions and intentions. To achieve this, strategies for humanrobot interaction are needed that are adapted to operators' needs and characteristics in an industrial context, i.e., Operator 5.0. This paper presents a research design for the development of a framework for human-robot interaction strategies based on ANEMONE, which is an evaluation framework based on activity theory, the seven stages of action model, and user experience (UX) evaluation methodology. At two companies, ANEMONE is applied in two concrete use cases, collaborative kitting and mobile robot platforms for chemical laboratory assignments. The proposed research approach consists of 1) evaluations of existing demonstrators, 2) development of preliminary strategies that are implemented, 3) re-evaluations and 4) cross-analysis of results to produce an interaction strategy framework. The theoretically and empirically underpinned framework-to-be is expected to, in the long run, contribute to a sustainable work environment for Operator 5.0.

    Download full text (pdf)
    FULLTEXT01
  • 7.
    Anderhagen Holmes, Oskar
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Automatisering av biträkning: med bildanalys och maskininlärning2024Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    This project examines the possibility to automate the process of counting tool parts. The project is done in cooperation with Sandvik Coromant, and a successful solution may be implemented in their production units in Gimo.

    The different solutions that were examined were two-fold. Firstly, “ordinary” image analysis algorithms, which are hard coded and with parameters that are manually adjusted to find the most accurate solution. Secondly, several machine-learning algorithms were tested, both “homemade” and out-of-the-box solutions.

    The results show that there is still a lot of work that needs to be done to reach the required accuracy for use on the production line. Of the methods studied, the so-called Segment anything model(SAM) showed the most potential. It outperformed all other methods. The only issue was that the method was discovered quite late into the study and was therefore not thoroughly studied compared to the other solutions.

    The author recommends that future research is conducted with SAM as the starting point. Combining a SAM implementation with some of the other points discussed, standardization of input and use of machine learning is expected to yield much more valuable results than what was achieved in this project.

     

    Download full text (pdf)
    fulltext
  • 8.
    Andersson, Axel
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    An Analytical Neighborhood Enrichment Score for Spatial OmicsManuscript (preprint) (Other academic)
    Abstract [en]

    The neighborhood enrichment test is commonly used to quantify spatial enrichment or depletion between spatial points with categorical labels — a data type frequently occurring in spatial omics. Traditionally, it is performed via permutation-based Monte Carlo methods, which can be computationally expensive. This study presents an analytical solution to the neighborhood enrichment problem. This direct calculation strongly correlated with traditional tests, offering substantially faster processing times across eight spatial omics datasets. Further validation on an extensive Xenium dataset highlighted the method’s ability to rapidly analyze large-scale data, making it a valuable tool for advancing spatial omics research. The implementation is publicly available.

  • 9.
    Andersson, Axel
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Computational Methods for Image-Based Spatial Transcriptomics2024Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    Why does cancer develop, spread, grow, and lead to mortality? To answer these questions, one must study the fundamental building blocks of all living organisms — cells. Like a well-calibrated manufacturing unit, cells follow precise instructions by gene expression to initiate the synthesis of proteins, the workforces that drive all living biochemical processes.

    Recently, researchers have developed techniques for imaging the expression of hundreds of unique genes within tissue samples. This information is extremely valuable for understanding the cellular activities behind cancer-related diseases.  These methods, collectively known as image-based spatial transcriptomics (IST) techniques,  use fluorescence microscopy to combinatorically label mRNA species (corresponding to expressed genes) in tissue samples. 

    Here, automatic image analysis is required to locate fluorescence signals and decode the combinatorial code. This process results in large quantities of points, marking the location of expressed genes. These new data formats pose several challenges regarding visualization and automated analysis.

    This thesis presents several computational methods and applications related to data generated from IST methods. 

    Key contributions include: (i) A decoding method that jointly optimizes the detection and decoding of signals, particularly beneficial in scenarios with low signal-to-noise ratios or densely packed signals;  (ii) a computational method for automatically delineating regions with similar gene compositions — efficient, interactive, and scalable for exploring patterns across different scales;  (iii) a software enabling interactive visualization of millions of gene markers atop Terapixel-sized images (TissUUmaps);  (iv) a tool utilizing signed-graph partitioning for the automatic identification of cells, independent of the complementary nuclear stain;  (v) A fast and analytical expression for a score that quantifies co-localization between spatial points (such as located genes);  (vi) a demonstration that gene expression markers can train deep-learning models to classify tissue morphology.

    In the final contribution (vii), an IST technique features in a clinical study to spatially map the molecular diversity within tumors from patients with colorectal liver metastases, specifically those exhibiting a desmoplastic growth pattern. The study unveils novel molecular patterns characterizing cellular diversity in the transitional region between healthy liver tissue and the tumor. While a direct answer to the initial questions remains elusive, this study sheds illuminating insights into the growth dynamics of colorectal cancer liver metastases, bringing us closer to understanding the journey from development to mortality in cancer.

    List of papers
    1. ISTDECO: In Situ Transcriptomics Decoding by Deconvolution
    Open this publication in new window or tab >>ISTDECO: In Situ Transcriptomics Decoding by Deconvolution
    (English)Manuscript (preprint) (Other academic)
    Abstract [en]

    In Situ Transcriptomics (IST) is a set of image-based transcriptomics approaches that enables localisation of gene expression directly in tissue samples. IST techniques produce multiplexed image series in which fluorescent spots are either present or absent across imaging rounds and colour channels. A spot’spresence and absence form a type of barcoded pattern that labels a particular type of mRNA. Therefore, the expression of agene can be determined by localising the fluorescent spots and decode the barcode that they form. Existing IST algorithms usually do this in two separate steps: spot localisation and barcode decoding. Although these algorithms are efficient, they are limited by strictly separating the localisation and decoding steps. This limitation becomes apparent in regions with low signal-to-noise ratio or high spot densities. We argue that an improved gene expression decoding can be obtained by combining these two steps into a single algorithm. This allows for an efficient decoding that is less sensitive to noise and optical crowding. We present IST Decoding by Deconvolution (ISTDECO), a principled decoding approach combining spectral and spatial deconvolution into a single algorithm. We evaluate ISTDECOon simulated data, as well as on two real IST datasets, and compare with state-of-the-art. ISTDECO achieves state-of-the-art performance despite high spot densities and low signal-to-noise ratios. It is easily implemented and runs efficiently using a GPU.ISTDECO implementation, datasets and demos are available online at: github.com/axanderssonuu/istdeco

    Keywords
    Deconvolution, In situ sequencing, Decoding, Image-based spatial transcriptomics
    National Category
    Medical Image Processing Bioinformatics (Computational Biology)
    Research subject
    Computerized Image Processing; Computerized Image Processing
    Identifiers
    urn:nbn:se:uu:diva-524008 (URN)
    Funder
    EU, European Research Council, 682810
    Note

    De två sista författarna delar sistaförfattarskapet

    Available from: 2024-02-27 Created: 2024-02-27 Last updated: 2024-02-28Bibliographically approved
    2. Points2Regions: Fast, interactive clustering of imaging-based spatial transcriptomics data
    Open this publication in new window or tab >>Points2Regions: Fast, interactive clustering of imaging-based spatial transcriptomics data
    Show others...
    (English)Manuscript (preprint) (Other academic)
    Abstract [en]

    Imaging-based spatial transcriptomics techniques generate image data that, once processed, results in a set of spatial points with categorical labels for different mRNA species. A crucial part of analyzing downstream data involves the analysis of these point patterns. Here, biologically interesting patterns can be explored at different spatial scales. Molecular patterns on a cellular level would correspond to cell types, whereas patterns on a millimeter scale would correspond to tissue-level structures. Often, clustering methods are employed to identify and segment regions with distinct point-patterns. Traditional clustering techniques for such data are constrained by reliance on complementary data or extensive machine learning, limiting their applicability to tasks on a particular scale. This paper introduces 'Points2Regions', a practical tool for clustering spatial points with categorical labels. Its flexible and computationally efficient clustering approach enables pattern discovery across multiple scales, making it a powerful tool for exploratory analysis. Points2Regions has demonstrated efficient performance in various datasets, adeptly defining biologically relevant regions similar to those found by scale-specific methods. As a Python package integrated into TissUUmaps and a Napari plugin, it offers interactive clustering and visualization, significantly enhancing user experience in data exploration. In essence, Points2Regions presents a user-friendly and simple tool for exploratory analysis of spatial points with categorical labels. 

    National Category
    Bioinformatics (Computational Biology)
    Research subject
    Bioinformatics; Immunology; Computerized Image Processing
    Identifiers
    urn:nbn:se:uu:diva-523994 (URN)
    Funder
    EU, European Research Council, 682810Science for Life Laboratory, SciLifeLab
    Available from: 2024-02-27 Created: 2024-02-27 Last updated: 2024-02-28
    3. TissUUmaps 3: Improvements in interactive visualization, exploration, and quality assessment of large-scale spatial omics data
    Open this publication in new window or tab >>TissUUmaps 3: Improvements in interactive visualization, exploration, and quality assessment of large-scale spatial omics data
    Show others...
    2023 (English)In: Heliyon, E-ISSN 2405-8440, Vol. 9, no 5, article id e15306Article in journal (Refereed) Published
    Abstract [en]

    Background and objectives: Spatially resolved techniques for exploring the molecular landscape of tissue samples, such as spatial transcriptomics, often result in millions of data points and images too large to view on a regular desktop computer, limiting the possibilities in visual interactive data exploration. TissUUmaps is a free, open-source browser-based tool for GPU-accelerated visualization and interactive exploration of 107+ data points overlaying tissue samples.

    Methods: Herein we describe how TissUUmaps 3 provides instant multiresolution image viewing and can be customized, shared, and also integrated into Jupyter Notebooks. We introduce new modules where users can visualize markers and regions, explore spatial statistics, perform quantitative analyses of tissue morphology, and assess the quality of decoding in situ transcriptomics data.

    Results: We show that thanks to targeted optimizations the time and cost associated with interactive data exploration were reduced, enabling TissUUmaps 3 to handle the scale of today's spatial transcriptomics methods.

    Conclusion: TissUUmaps 3 provides significantly improved performance for large multiplex datasets as compared to previous versions. We envision TissUUmaps to contribute to broader dissemination and flexible sharing of largescale spatial omics data.

    Place, publisher, year, edition, pages
    Elsevier BV, 2023
    Keywords
    Interactive visualization, Spatial omics, Spatial transcriptomics
    National Category
    Bioinformatics and Systems Biology
    Identifiers
    urn:nbn:se:uu:diva-508867 (URN)10.1016/j.heliyon.2023.e15306 (DOI)001029211200001 ()37131430 (PubMedID)
    Funder
    Swedish Foundation for Strategic Research, BD150008Swedish Foundation for Strategic Research, SB160046EU, European Research Council, CoG682810
    Available from: 2023-08-11 Created: 2023-08-11 Last updated: 2024-02-28Bibliographically approved
    4. Cell Segmentation of in situ Transcriptomics Data using Signed Graph Partitioning
    Open this publication in new window or tab >>Cell Segmentation of in situ Transcriptomics Data using Signed Graph Partitioning
    2023 (English)In: Graph-Based Representations in Pattern Recognition / [ed] Mario Vento; Pasquale Foggia; Donatello Conte; Vincenzo Carletti, Cham: Springer, 2023, p. 139-148Conference paper, Published paper (Refereed)
    Abstract [en]

    The locations of different mRNA molecules can be revealed by multiplexed in situ RNA detection. By assigning detected mRNA molecules to individual cells, it is possible to identify many different cell types in parallel. This in turn enables investigation of the spatial cellular architecture in tissue, which is crucial for furthering our understanding of biological processes and diseases. However, cell typing typically depends on the segmentation of cell nuclei, which is often done based on images of a DNA stain, such as DAPI. Limiting cell definition to a nuclear stain makes it fundamentally difficult to determine accurate cell borders, and thereby also difficult to assign mRNA molecules to the correct cell. As such, we have developed a computational tool that segments cells solely based on the local composition of mRNA molecules. First, a small neural network is trained to compute attractive and repulsive edges between pairs of mRNA molecules. The signed graph is then partitioned by a mutex watershed into components corresponding to different cells. We evaluated our method on two publicly available datasets and compared it against the current state-of-the-art and older baselines. We conclude that combining neural networks with combinatorial optimization is a promising approach for cell segmentation of in situ transcriptomics data. The tool is open-source and publicly available for use at https://github.com/wahlby-lab/IS3G.

    Place, publisher, year, edition, pages
    Cham: Springer, 2023
    Series
    Lecture Notes in Computer Science (LNCS), ISSN 0302-9743, E-ISSN 1611-3349 ; 14121
    Keywords
    Cell segmentation, in situ transcriptomics, tissue analysis, mutex watershed
    National Category
    Bioinformatics (Computational Biology)
    Research subject
    Computerized Image Processing; Machine learning
    Identifiers
    urn:nbn:se:uu:diva-523993 (URN)10.1007/978-3-031-42795-4_13 (DOI)978-3-031-42794-7 (ISBN)978-3-031-42795-4 (ISBN)
    Conference
    13th IAPR-TC-15 International Workshop, GbRPR 2023, Vietri sul Mare, Italy, September 6–8, 2023
    Available from: 2024-02-27 Created: 2024-02-27 Last updated: 2024-02-28Bibliographically approved
    5. An Analytical Neighborhood Enrichment Score for Spatial Omics
    Open this publication in new window or tab >>An Analytical Neighborhood Enrichment Score for Spatial Omics
    (English)Manuscript (preprint) (Other academic)
    Abstract [en]

    The neighborhood enrichment test is commonly used to quantify spatial enrichment or depletion between spatial points with categorical labels — a data type frequently occurring in spatial omics. Traditionally, it is performed via permutation-based Monte Carlo methods, which can be computationally expensive. This study presents an analytical solution to the neighborhood enrichment problem. This direct calculation strongly correlated with traditional tests, offering substantially faster processing times across eight spatial omics datasets. Further validation on an extensive Xenium dataset highlighted the method’s ability to rapidly analyze large-scale data, making it a valuable tool for advancing spatial omics research. The implementation is publicly available.

    Keywords
    Spatial statistics, Neighborhood enrichment, Spatial omics, Co-localization
    National Category
    Bioinformatics (Computational Biology) Probability Theory and Statistics
    Research subject
    Bioinformatics; Mathematical Statistics; Computerized Image Processing
    Identifiers
    urn:nbn:se:uu:diva-524007 (URN)
    Available from: 2024-02-27 Created: 2024-02-27 Last updated: 2024-02-28Bibliographically approved
    6. Transcriptome-Supervised Classification of Tissue Morphology Using Deep Learning
    Open this publication in new window or tab >>Transcriptome-Supervised Classification of Tissue Morphology Using Deep Learning
    2020 (English)In: IEEE 17th International Symposium on Biomedical Imaging (ISBI), 2020, p. 1630-1633Conference paper, Published paper (Refereed)
    Abstract [en]

    Deep learning has proven to successfully learn variations in tissue and cell morphology. Training of such models typically relies on expensive manual annotations. Here we conjecture that spatially resolved gene expression, e.i., the transcriptome, can be used as an alternative to manual annotations. In particular, we trained five convolutional neural networks with patches of different size extracted from locations defined by spatially resolved gene expression. The network is trained to classify tissue morphology related to two different genes, general tissue, as well as background, on an image of fluorescence stained nuclei in a mouse brain coronal section. Performance is evaluated on an independent tissue section from a different mouse brain, reaching an average Dice score of 0.51. Results may indicate that novel techniques for spatially resolved transcriptomics together with deep learning may provide a unique and unbiased way to find genotype phenotype relationships

    Series
    IEEE International Symposium on Biomedical Imaging (ISBI), ISSN 1945-7928, E-ISSN 1945-8452
    Keywords
    In situ sequencing, Gene expression, Tissue classification, Deep learning
    National Category
    Bioinformatics and Systems Biology
    Research subject
    Bioinformatics
    Identifiers
    urn:nbn:se:uu:diva-420376 (URN)10.1109/ISBI45749.2020.9098361 (DOI)000578080300341 ()978-1-5386-9330-8 (ISBN)978-1-5386-9331-5 (ISBN)
    Conference
    2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Iowa City, 3-7 april
    Projects
    TissUUmaps
    Funder
    EU, European Research Council, 682810
    Available from: 2020-09-24 Created: 2020-09-24 Last updated: 2024-02-28Bibliographically approved
    7. Spatial transcriptome mapping of the desmoplastic growth pattern of colorectal liver metastases by in situ sequencing reveals a biologically relevant zonation of the desmoplastic rim
    Open this publication in new window or tab >>Spatial transcriptome mapping of the desmoplastic growth pattern of colorectal liver metastases by in situ sequencing reveals a biologically relevant zonation of the desmoplastic rim
    Show others...
    (English)Manuscript (preprint) (Other academic)
    Keywords
    Colorectal cancer liver metastasis, growth pattern, in situ sequencing, desmoplastic
    National Category
    Cell and Molecular Biology Bioinformatics (Computational Biology) Cancer and Oncology
    Research subject
    Microbiology; Computerized Image Processing; Molecular Cellbiology
    Identifiers
    urn:nbn:se:uu:diva-523995 (URN)
    Funder
    Swedish Cancer SocietyKnut and Alice Wallenberg Foundation, 2021/1726Region VästerbottenCancerforskningsfonden i NorrlandUmeå UniversitySwedish Research Council, 2019-01238EU, European Research Council, 682810Science for Life Laboratory, SciLifeLab
    Available from: 2024-02-27 Created: 2024-02-27 Last updated: 2024-02-28Bibliographically approved
    Download full text (pdf)
    UUThesis_A-Andersson-2024
    Download (jpg)
    preview image
  • 10.
    Andersson, Axel
    et al.
    Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Behanova, Andrea
    Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Avenel, Christophe
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Science for Life Laboratory, SciLifeLab.
    Windhager, Jonas
    Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Malmberg, Filip
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Science for Life Laboratory, SciLifeLab.
    Wählby, Carolina
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Points2Regions: Fast, interactive clustering of imaging-based spatial transcriptomics dataManuscript (preprint) (Other academic)
    Abstract [en]

    Imaging-based spatial transcriptomics techniques generate image data that, once processed, results in a set of spatial points with categorical labels for different mRNA species. A crucial part of analyzing downstream data involves the analysis of these point patterns. Here, biologically interesting patterns can be explored at different spatial scales. Molecular patterns on a cellular level would correspond to cell types, whereas patterns on a millimeter scale would correspond to tissue-level structures. Often, clustering methods are employed to identify and segment regions with distinct point-patterns. Traditional clustering techniques for such data are constrained by reliance on complementary data or extensive machine learning, limiting their applicability to tasks on a particular scale. This paper introduces 'Points2Regions', a practical tool for clustering spatial points with categorical labels. Its flexible and computationally efficient clustering approach enables pattern discovery across multiple scales, making it a powerful tool for exploratory analysis. Points2Regions has demonstrated efficient performance in various datasets, adeptly defining biologically relevant regions similar to those found by scale-specific methods. As a Python package integrated into TissUUmaps and a Napari plugin, it offers interactive clustering and visualization, significantly enhancing user experience in data exploration. In essence, Points2Regions presents a user-friendly and simple tool for exploratory analysis of spatial points with categorical labels. 

  • 11.
    Andersson, Axel
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Science for Life Laboratory, SciLifeLab.
    Behanova, Andrea
    Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Wählby, Carolina
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Malmberg, Filip
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Science for Life Laboratory, SciLifeLab.
    Cell Segmentation of in situ Transcriptomics Data using Signed Graph Partitioning2023In: Graph-Based Representations in Pattern Recognition / [ed] Mario Vento; Pasquale Foggia; Donatello Conte; Vincenzo Carletti, Cham: Springer, 2023, p. 139-148Conference paper (Refereed)
    Abstract [en]

    The locations of different mRNA molecules can be revealed by multiplexed in situ RNA detection. By assigning detected mRNA molecules to individual cells, it is possible to identify many different cell types in parallel. This in turn enables investigation of the spatial cellular architecture in tissue, which is crucial for furthering our understanding of biological processes and diseases. However, cell typing typically depends on the segmentation of cell nuclei, which is often done based on images of a DNA stain, such as DAPI. Limiting cell definition to a nuclear stain makes it fundamentally difficult to determine accurate cell borders, and thereby also difficult to assign mRNA molecules to the correct cell. As such, we have developed a computational tool that segments cells solely based on the local composition of mRNA molecules. First, a small neural network is trained to compute attractive and repulsive edges between pairs of mRNA molecules. The signed graph is then partitioned by a mutex watershed into components corresponding to different cells. We evaluated our method on two publicly available datasets and compared it against the current state-of-the-art and older baselines. We conclude that combining neural networks with combinatorial optimization is a promising approach for cell segmentation of in situ transcriptomics data. The tool is open-source and publicly available for use at https://github.com/wahlby-lab/IS3G.

  • 12.
    Andersson, Axel
    et al.
    Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Diego, Ferran
    HCI/IWR and Department of Physics and Astronomy, Heidelberg University, Heidelberg.
    Hamprecht, Fred A.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Science for Life Laboratory, SciLifeLab. HCI/IWR and Department of Physics and Astronomy, Heidelberg University, Heidelberg.
    Wählby, Carolina
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    ISTDECO: In Situ Transcriptomics Decoding by DeconvolutionManuscript (preprint) (Other academic)
    Abstract [en]

    In Situ Transcriptomics (IST) is a set of image-based transcriptomics approaches that enables localisation of gene expression directly in tissue samples. IST techniques produce multiplexed image series in which fluorescent spots are either present or absent across imaging rounds and colour channels. A spot’spresence and absence form a type of barcoded pattern that labels a particular type of mRNA. Therefore, the expression of agene can be determined by localising the fluorescent spots and decode the barcode that they form. Existing IST algorithms usually do this in two separate steps: spot localisation and barcode decoding. Although these algorithms are efficient, they are limited by strictly separating the localisation and decoding steps. This limitation becomes apparent in regions with low signal-to-noise ratio or high spot densities. We argue that an improved gene expression decoding can be obtained by combining these two steps into a single algorithm. This allows for an efficient decoding that is less sensitive to noise and optical crowding. We present IST Decoding by Deconvolution (ISTDECO), a principled decoding approach combining spectral and spatial deconvolution into a single algorithm. We evaluate ISTDECOon simulated data, as well as on two real IST datasets, and compare with state-of-the-art. ISTDECO achieves state-of-the-art performance despite high spot densities and low signal-to-noise ratios. It is easily implemented and runs efficiently using a GPU.ISTDECO implementation, datasets and demos are available online at: github.com/axanderssonuu/istdeco

  • 13.
    Andersson, Axel
    et al.
    Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Escriva Conde, Maria
    Stockholm University.
    Surova, Olga
    Stockholm University.
    Vermeulen, Peter
    GZA Hospital Sint-Augustinus.
    Wählby, Carolina
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Nilsson, Mats
    Stockholm University.
    Nyström, Hanna
    Umeå University.
    Spatial transcriptome mapping of the desmoplastic growth pattern of colorectal liver metastases by in situ sequencing reveals a biologically relevant zonation of the desmoplastic rimManuscript (preprint) (Other academic)
  • 14.
    Andersson, Axel
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Koriakina, Nadezhda
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Sladoje, Nataša
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Lindblad, Joakim
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    End-to-end Multiple Instance Learning with Gradient Accumulation2022In: 2022 IEEE International Conference on Big Data (Big Data), Institute of Electrical and Electronics Engineers (IEEE), 2022, p. 2742-2746Conference paper (Refereed)
    Abstract [en]

    Being able to learn on weakly labeled data and provide interpretability are two of the main reasons why attention-based deep multiple instance learning (ABMIL) methods have become particularly popular for classification of histopathological images. Such image data usually come in the form of gigapixel-sized whole-slide-images (WSI) that are cropped into smaller patches (instances). However, the sheer volume of the data poses a practical big data challenge: All the instances from one WSI cannot fit the GPU memory of conventional deep-learning models. Existing solutions compromise training by relying on pre-trained models, strategic selection of instances, sub-sampling, or self-supervised pre-training. We propose a training strategy based on gradient accumulation that enables direct end-to-end training of ABMIL models without being limited by GPU memory. We conduct experiments on both QMNIST and Imagenette to investigate the performance and training time and compare with the conventional memory-expensive baseline as well as a recent sampled-based approach. This memory-efficient approach, although slower, reaches performance indistinguishable from the memory-expensive baseline.

  • 15.
    Asai, Ryoko
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Ruhr Universität Bohum, Germany.
    Nakada, Makoto
    University of Tsukuba, Japan.
    Kavathatzopoulos, Iordanis
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Care Robots and Humanity: How Can We Cope with The Indeterminacy and Ambiguity of Robot-Human Relationships?2023In: Tethics 2023: Proceedings of the Conference on Technology Ethics 2023 / [ed] Minna M. Rantanen, Salla Westerstrand, Otto Sahlgren and Jani Koskinen, CEUR-WS.org , 2023, p. 1-10Conference paper (Refereed)
    Abstract [en]

    Ageing society, labour shortages in the care sector and increasing social security costs havebecome serious social problems in many countries. Sweden and Japan are, of course, noexception in this respect. In order to alleviate this situation, both countries have implementedvarious policies in different social areas, as well as promoting digitalisation and introducingcare robots in the healthcare sector. While older people are generally considered to be reluctantto adapt to new technologies, in both Japan and Sweden, the digital integration of older peopleis higher than in other countries. In the near future, care robots or robotic care would becomemore common in the care sector in both countries. This study examines how people in bothcountries perceive robots and autonomous artefacts and how they construct relationships withthese artefacts, based on the results of two surveys, one conducted in Japan 2020, and anotherin Sweden 2019, and elucidates the relationship between humans and robots from an ethicalperspective. The research findings show that people’s orientation toward the search for theexistential meaning and their complex emotions related to ephemerality and transience canaffect the relationship between humans and robots. Furthermore, this study is a new attempt toincorporate a 'care' perspective into technology ethics.

  • 16.
    Aslani, Mohammad
    et al.
    Univ Gävle, Dept Comp & Geospatial Sci, Gävle, Sweden..
    Seipel, Stefan
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Univ Gävle, Dept Comp & Geospatial Sci, Gävle, Sweden..
    Rooftop segmentation and optimization of photovoltaic panel layouts in digital surface models2023In: Computers, Environment and Urban Systems, ISSN 0198-9715, E-ISSN 1873-7587, Vol. 105, article id 102026Article in journal (Refereed)
    Abstract [en]

    Rooftop photovoltaic panels (RPVs) are being increasingly used in urban areas as a promising means of achieving energy sustainability. Determining proper layouts of RPVs that make the best use of rooftop areas is of importance as they have a considerable impact on the RPVs performance in efficiently producing energy. In this study, a new spatial methodology for automatically determining the proper layouts of RPVs is proposed. It aims to both extract planar rooftop segments and identify feasible layouts with the highest number of RPVs in highly irradiated areas. It leverages digital surface models (DSMs) to consider roof shapes and occlusions in placing RPVs. The innovations of the work are twofold: (a) a new method for plane segmentation, and (b) a new method for optimally placing RPVs based on metaheuristic optimization, which best utilizes the limited rooftop areas. The proposed methodology is evaluated on two test sites that differ in urban morphology, building size, and spatial resolution. The results show that the plane segmentation method can accurately extract planar segments, achieving 88.7% and 99.5% precision in the test sites. In addition, the results indicate that complex rooftops are adequately handled for placing RPVs, and overestimation of solar energy potential is avoided if detailed analysis based on panel placement is employed.

    Download full text (pdf)
    fulltext
  • 17.
    Azar, Jimmy C
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Simonsson, Martin
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Bengtsson, Ewert
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala university.
    Hast, Anders
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Automated classification of glandular tissue by statistical proximity sampling.2015In: International Journal of Biomedical Imaging, ISSN 1687-4188, E-ISSN 1687-4196, ISSN 1687-4188, Vol. 2015Article in journal (Refereed)
    Abstract [en]

    Due to the complexity of biological tissue and variations in staining procedures, features that are based on the explicit extraction of properties from subglandular structures in tissue images may have difficulty generalizing well over an unrestricted set of images and staining variations. We circumvent this problem by an implicit representation that is both robust and highly descriptive, especially when combined with a multiple instance learning approach to image classification. The new feature method is able to describe tissue architecture based on glandular structure. It is based on statistically representing the relative distribution of tissue components around lumen regions, while preserving spatial and quantitative information, as a basis for diagnosing and analyzing different areas within an image. We demonstrate the efficacy of the method in extracting discriminative features for obtaining high classification rates for tubular formation in both healthy and cancerous tissue, which is an important component in Gleason and tubule-based Elston grading. The proposed method may be used for glandular classification, also in other tissue types, in addition to general applicability as a region-based feature descriptor in image analysis where the image represents a bag with a certain label (or grade) and the region-based feature vectors represent instances.

  • 18.
    Bajic, Buda
    et al.
    Univ. of Novi Sad, Fac Tech Sci, Novi Sad, Serbia.
    Lindblad, Joakim
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Sladoje, Nataša
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Blind deconvolution of images degraded with mixed Poisson-Gaussian noise with application in Transmission Electron Microscopy2016In: Proceedings of the Swedish Society for Automated Image Analysis, Uppsala, 2016, p. 137-141Conference paper (Other academic)
  • 19.
    Banerjee, Subhashis
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Nysjö, Fredrik
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology.
    Toumpanakis, Dimitrios
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology.
    Dhara, Ashis Kumar
    Natl Inst Technol Durgapur, Dept Elect Engn, Durgapur, India..
    Wikström, Johan
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology. Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Neuroradiologi.
    Strand, Robin
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Streamlining neuroradiology workflow with AI for improved cerebrovascular structure monitoring2024In: Scientific Reports, E-ISSN 2045-2322, Vol. 14, no 1, article id 9245Article in journal (Refereed)
    Abstract [en]

    Radiological imaging to examine intracranial blood vessels is critical for preoperative planning and postoperative follow-up. Automated segmentation of cerebrovascular anatomy from Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) can provide radiologists with a more detailed and precise view of these vessels. This paper introduces a domain generalized artificial intelligence (AI) solution for volumetric monitoring of cerebrovascular structures from multi-center MRAs. Our approach utilizes a multi-task deep convolutional neural network (CNN) with a topology-aware loss function to learn voxel-wise segmentation of the cerebrovascular tree. We use Decorrelation Loss to achieve domain regularization for the encoder network and auxiliary tasks to provide additional regularization and enable the encoder to learn higher-level intermediate representations for improved performance. We compare our method to six state-of-the-art 3D vessel segmentation methods using retrospective TOF-MRA datasets from multiple private and public data sources scanned at six hospitals, with and without vascular pathologies. The proposed model achieved the best scores in all the qualitative performance measures. Furthermore, we have developed an AI-assisted Graphical User Interface (GUI) based on our research to assist radiologists in their daily work and establish a more efficient work process that saves time.

    Download full text (pdf)
    FULLTEXT01
  • 20.
    Banerjee, Subhashis
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Strand, Robin
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Lifelong Learning with Dynamic Convolutions for Glioma: Segmentation from Multi-Modal MRI2023In: Medical Imaging 2023: Image Processing / [ed] Olivier Colliot;Ivana Išgum, SPIE - International Society for Optical Engineering, 2023, Vol. 12464, article id 124643JConference paper (Refereed)
    Abstract [en]

    This paper presents a novel solution for catastrophic forgetting in life long learning (LL) using Dynamic ConvolutionNeural Network (Dy-CNN). The proposed dynamic convolution layer, can adapt convolution filters bylearning kernel coefficients or weights based on the input image. Suitability of the proposed Dy-CNN in a lifelongsequential learning-based scenario with multi-modal MR images is experimentally demonstrated for segmentation of Glioma tumor from multi-modal MR images. Experimental results demonstrated the superiority of the Dy-CNN-based segmenting network in terms of learning through multi-modal MRI images and better convergence of lifelong learning-based training.

  • 21.
    Banerjee, Subhashis
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Strand, Robin
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Lifelong Learning with Dynamic Convolutions for Glioma Segmentation from Multi-Modal MRI2023In: Medical imaging 2023 / [ed] Colliot, O Isgum, I, SPIE - International Society for Optical Engineering, 2023, Vol. 12464, article id 124643JConference paper (Refereed)
    Abstract [en]

    This paper presents a novel solution for catastrophic forgetting in lifelong learning (LL) using Dynamic Convolution Neural Network (Dy-CNN). The proposed dynamic convolution layer can adapt convolution filters by learning kernel coefficients or weights based on the input image. The suitability of the proposed Dy-CNN in a lifelong sequential learning-based scenario with multi-modal MR images is experimentally demonstrated for the segmentation of Glioma tumors from multi-modal MR images. Experimental results demonstrated the superiority of the Dy-CNN-based segmenting network in terms of learning through multi-modal MRI images and better convergence of lifelong learning-based training.

    Download full text (pdf)
    fulltext
  • 22.
    Banerjee, Subhashis
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Toumpanakis, Dimitrios
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology.
    Dhara, Ashis
    Department of Electrical Engineering, National Institute of Technology Durgapur, India.
    Wikström, Johan
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology.
    Strand, Robin
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Deep Curriculum Learning for Follow-up MRI Registration in Glioblastoma2023In: Medical Imaging 2023: Image Processing, SPIE -Society of Photo-Optical Instrumentation Engineers , 2023, Vol. 12464, article id 124643IConference paper (Refereed)
    Abstract [en]

    This paper presents a weakly supervised deep convolutional neural network-based approach to perform voxel-level3D registration between subsequent follow-up MRI scans of the same patient. To handle the large deformation inthe surrounding brain tissues due to the tumor’s mass effect we proposed curriculum learning-based training forthe network. Weak supervision helps the network to concentrate more focus on the tumor region and resectioncavity through a saliency detection network. Qualitative and quantitative experimental results show the proposedregistration network outperformed two popular state-of-the-art methods.

  • 23.
    Beháňová, Andrea
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Avenel, Christophe
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Science for Life Laboratory, SciLifeLab.
    Andersson, Axel
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Chelebian, Eduard
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Science for Life Laboratory, SciLifeLab.
    Klemm, Anna
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Wik, Lina
    Östman, Arne
    Wählby, Carolina
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Visualization and quality control tools for large-scale multiplex tissue analysis in TissUUmaps32023In: Biological Imaging, E-ISSN 2633-903X, Vol. 3, article id e6Article in journal (Refereed)
  • 24.
    Bengtsson Bernander, Karl
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Sintorn, Ida-Maria
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Science for Life Laboratory, SciLifeLab. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Strand, Robin
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Radiology. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Nyström, Ingela
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Classification of Viruses in Transmission Electron Microscopy Images using Equivariant Neural NetworksManuscript (preprint) (Other academic)
  • 25.
    Berglund, Anders
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computing Education Research. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Daniels, Mats
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computing Education Research. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Reardon, Jake
    External Relations Team Faculty of Science, University of Southern Denmark, Odense, Denmark.
    Encouraging Asian academic STEM teachers to research their own teaching practice2021In: 2021 IEEE Frontiers in Education Conference (FIE), Institute of Electrical and Electronics Engineers (IEEE), 2021Conference paper (Refereed)
    Abstract [en]

    It might be a challenge for a STEM researcher to engage in research that is not directly relevant to his or her own field of specialization. The CUP EASTEM course, described in this paper, aims to support academic Asian STEM teachers in overcoming the challenge of researching their own teaching practices. In this paper we discuss, with CUP EASTEM, as a case study, how we have supported academic STEM teachers to take the steps needed to conduct research on their own teaching practices. The key is to broaden the perspective to also include theoretically sound, qualitative interpretative research. Furthermore, this is a journey that must be made without losing sight of the object of the students' learning, that is, the fundamental concepts within the STEM disciplines.

  • 26.
    Bezek, Can Deniz
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Bilgin, Mert
    Department of Information Technology and Electrical Engineering, ETH Zurich, Zurich, Switzerland.
    Zhang, Lin
    Department of Information Technology and Electrical Engineering, ETH Zurich, Zurich, Switzerland.
    Göksel, Orcun
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Department of Information Technology and Electrical Engineering, ETH Zurich, Zurich, Switzerland.
    Global Speed-of-Sound Prediction Using Transmission Geometry2022In: Proceedings of the 2022 IEEE International Ultrasonics Symposium (IUS), IEEE, 2022, p. 1-4Conference paper (Refereed)
    Abstract [en]

    Most ultrasound (US) imaging techniques usespatially-constant speed-of-sound (SoS) values for beamforming.Having a discrepancy between the actual and used SoS valueleads to aberration artifacts, e.g., reducing the image resolution,which may affect diagnostic usability. Accuracy and quality ofdifferent US imaging modalities, such as tomographic reconstruc-tion of local SoS maps, also depend on a good initial beamformingSoS. In this work, we develop an analytical method for estimatingmean SoS in an imaged medium. We show that the relative shiftsbetween beamformed frames depend on the SoS offset and thegeometric disparities in transmission paths. Using this relation,we estimate a correction factor and hence a corrected mean SoSin the medium. We evaluated our proposed method on a set ofnumerical simulations, demonstrating its utility both for globalSoS prediction and for local SoS tomographic reconstruction.For our evaluation dataset, for an initial SoS under- and over-assumption of 5% the medium SoS, our method is able to predictthe actual mean SoS within 0.3% accuracy. For the tomographicreconstruction of local SoS maps, the reconstruction accuracy isimproved on average by 78.5% and 87%, respectively, comparedto an initial SoS under- and over-assumption of 5%.Index Terms—Beamforming, aberration correction.

  • 27.
    Bezek, Can Deniz
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Göksel, Orcun
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Analytical Estimation of Beamforming Speed-of-Sound Using Transmission Geometry2023In: Ultrasonics, ISSN 0041-624X, E-ISSN 1874-9968, Vol. 134, article id 107069Article in journal (Refereed)
    Abstract [en]

    Most ultrasound imaging techniques necessitate the fundamental step of converting temporal signals received from transducer elements into a spatial echogenecity map. This beamforming (BF) step requires the knowledge of speed-of-sound (SoS) value in the imaged medium. An incorrect assumption of BF SoS leads to aberration artifacts, not only deteriorating the quality and resolution of conventional brightness mode (B-mode) images, hence limiting their clinical usability, but also impairing other ultrasound modalities such as elastography and spatial SoS reconstructions, which rely on faithfully beamformed images as their input. In this work, we propose an analytical method for estimating BF SoS. We show that pixel-wise relative shifts between frames beamformed with an assumed SoS is a function of geometric disparities of the transmission paths and the error in such SoS assumption. Using this relation, we devise an analytical model, the closed form solution of which yields the difference between the assumed and the true SoS in the medium. Based on this, we correct the BF SoS, which can also be applied iteratively. Both in simulations and experiments, lateral B-mode resolution is shown to be improved by ≈ 25% compared to that with an initial SoS assumption error of 3.3% (50 m/s), while localization artifacts from beamforming are also corrected. After 5 iterations, our method achieves BF SoS errors of under 0.6 m/s in simulations. Residual time-delay errors in beamforming 32 numerical phantoms are shown to reduce down to 0.07 µs, with average improvements of up to 21 folds compared to initial inaccurate assumptions. We additionally show the utility of the proposed method in imaging local SoS maps, where using our correction method reduces reconstruction root-mean-square errors substantially, down to their lower-bound with actual BF SoS.

    Download full text (pdf)
    fulltext
  • 28.
    Bleichner, Andreas
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Hermansson, Nils
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Investigating the usefulness of a generative AI when designing user interfaces2023Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Generative AI is a hot topic as of 2023, with huge financial investments in the industry. The areas of use for it are rapidly expanding. One potential benefit of generative AI could be in the field of UX design.For this master's thesis, a Stable Diffusion model has been fine-tuned to create pictures of login screens based on text prompts written by a user. A set of these pictures have been used in a prototype and the concept has been evaluated through user tests. The prototype and the concept of using generative AI in UX design received a positive reception from testers. It was established that further work on the fine-tuned model and how to use it as a tool is required for it to be effectively integrated into the design process of user interfaces.

    Download full text (pdf)
    fulltext
  • 29.
    Boström, Gustav
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Parker, Thomas
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Effectivization of white-collarwork through AI applications: A roadmap for future development in production2024Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    The demand for products continues to increase in today’s society, and to meet this demandcompanies are searching for new ways to improve the performance of their workers.Therefore, there is a constant push to develop and implement new technological solutionswithin the Industry 4.0 approach. The aim of this study is to research the different pathwaysone could take when implementing these technological solutions and what challenges itwould entail, with a focus on Artificial Intelligence (AI). This is done in collaboration withSaab Surveillance within their production division, who wishes to increase theirperformance within their white-collar environment. In this study, performance is defined andmeasured through productivity. The main indicators of productivity will, therefore, be timededicated to a task as well as the potential to improve the quality of a task. The result of thisstudy is presented with a roadmap framework where seven key areas, i.e., work processes,were discovered that could benefit from AI applications. These areas were uncovered byconducting a contextual inquiry and semi-structured interviews, and were then matched withrelevant AI applications. The discovered key areas are categorized based on a cost-benefitanalysis, with the scale of; low, medium, and high. The roadmap illustrates in which areas itcould be most beneficial to implement the suggested AI applications. Using this study, Saaband other companies can make more informed decisions on the pathways for adopting newtechnological solutions that will improve the performance of their white-collar workers.

    Download full text (pdf)
    fulltext
  • 30. Bradley, Steven
    et al.
    Parker, Miranda C.
    Altin, Rukiye
    Barker, Lecia
    Hooshangi, Sara
    Kamal, Samia
    Kunkeler, Thom
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computing Education Research. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Lennon, Ruth G.
    McNeill, Fiona
    Minguillón, Julià
    Parkinson, Jack
    Peltsverger, Svetlana
    Sibia, Naaz
    A Methodology for Investigating Women's Module Choices in Computer Science2023In: ITiCSE 2023: Proceedings of the 2023 Conference on Innovation and Technology in Computer Science Education / [ed] Mikko-Jussi Laakso; Mattia Monga; Simon; Judithe Sheard, Association for Computing Machinery (ACM), 2023, Vol. 2, p. 569-570Conference paper (Refereed)
    Abstract [en]

    At ITiCSE 2021, Working Group 3 examined the evidence for teaching practices that broaden participation for women in computing, based on the National Center for Women & Information Technology (NCWIT) Engagement Practices framework. One of the report's recommendations was "Make connections from computing to your students' lives and interests (Make it Matter) but don't assume you know what those interests are; find out!" The goal of this 2023 working group is to find out what interests women students by bringing together data from our institutions on undergraduate module enrollment, seeing how they differ for women and men, and what drives those choices. We will code published module content based on ACM curriculum guidelines and combine these data to build a hierarchical statistical model of factors affecting student choice. This model should be able to tell us how interesting or valuable different topics are to women, and to what extent topic affects choice of module - as opposed to other factors such as the instructor, the timetable, or the mode of assessment. Equipped with this knowledge we can advise departments how to focus curriculum development on areas that are of value to women, and hence work towards making the discipline more inclusive.

  • 31.
    Bradley, Steven
    et al.
    Durham Univ, Dept Comp Sci, Durham, NC 27708 USA. San Diego State Univ, Dept Comp Sci, San Diego, CA USA..
    Parker, Miranda C.
    Altin, Rukiye
    Univ Kiel, Dept Comp Sci, Kiel, Germany..
    Barker, Lecia
    Univ Colorado, Natl Ctr Women & IT, Dept Informat Sci, Boulder, CO USA..
    Hooshangi, Sara
    Virginia Tech, Dept Comp Sci, Blacksburg, VA USA..
    Kunkeler, Thom
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computing Education Research. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Computer Systems. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Lennon, Ruth G.
    Atlantic Technol Univ, Dept Comp, Donegal, Ireland..
    McNeill, Fiona
    Univ Edinburgh, Sch Informat, Edinburgh, Midlothian, Scotland..
    Minguillón, Julià
    Univ Oberta Catalunya, Dept Comp Sci Multimedia & Telecommun, Barcelona, Spain..
    Parkinson, Jack
    Univ Glasgow, Ctr Comp Sci Educ, Glasgow, Lanark, Scotland..
    Peltsverger, Svetlana
    Kennesaw State Univ, Coll Comp & Software Engn, Marietta, GA USA..
    Sibia, Naaz
    Univ Toronto, Dept Comp Sci, Toronto, ON, Canada..
    Modeling Women's Elective Choices in Computing2023In: ITiCSE-WGR '23: Proceedings of the 2023 Working Group Reports on Innovation and Technology in Computer Science Education / [ed] Mikko-Jussi Laakso; Mattia Monga; Simon; Judithe Sheard, Association for Computing Machinery (ACM), 2023, p. 196-226Conference paper (Refereed)
    Abstract [en]

    Evidence-based strategies suggest ways to reduce the gender gap in computing. For example, elective classes are valuable in enabling students to choose in which directions to expand their computing knowledge in areas aligned with their interests. The availability of electives of interest may also make computing programs of study more meaningful to women. However, research on which elective computing topics are more appealing to women is often class or institution specific. In this study, we investigate differences in enrollment within undergraduate-level elective classes in computing to study differences between women and men. The study combined data from nine institutions from both Western Europe and North America and included 272 different classes with 49,710 student enrollments. These classes were encoded using ACM curriculum guidelines and combined with the enrollment data to build a hierarchical statistical model of factors affecting student choice. Our model shows which elective topics are less popular with all students (including fundamentals of programming languages and parallel and distributed computing), and which elective topics are more popular with women students (including mathematical and statistical foundations, human computer interaction and society, ethics, and professionalism). Understanding which classes appeal to different students can help departments gain insight of student choices and develop programs accordingly. Additionally, these choices can also help departments explore whether some students are less likely to choose certain classes than others, indicating potential barriers to participation in computing.

    Download full text (pdf)
    FULLTEXT01
  • 32.
    Breznik, Eva
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Strand, Robin
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Effects of distance transform choice in training with boundary loss2021Conference paper (Other academic)
    Abstract [en]

    Convolutional neural networks are the method of choice for many medical imaging tasks, in particular segmentation. Recently, efforts have been made to include distance measures in the network training, as for example the introduction of boundary loss, calculated via a signed distance transform. Using boundary loss for segmentation can alleviate issues with imbalance and irregular shapes, leading to a better segmentation boundary. It is originally based on the Euclidean distance transform. In this paper we investigate the effects of employing various definitions of distance when using the boundary loss for medical image segmentation. Our results show a promising behaviour in training with non-Euclidean distances, and suggest a possible new use of the boundary loss in segmentation problems.

  • 33.
    Bylander, Karl
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    More efficient training using equivariant neural networks2023Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Convolutional neural networks are equivariant to translations; equivariance to other symmetries, however, is not defined and the class output may vary depending on the input's orientation. To mitigate this, the training data can be augmented at the cost of increased redundancy in the model. Another solution is to build an equivariant neural network and thereby increasing the equivariance to a larger symmetry group.

    In this study, two convolutional neural networks and their respective equivariant counterparts are constructed and applied to the symmetry groups D4 and C8 to explore the impact on performance when removing and adding batch normalisation and data augmentation. The results suggest that data augmentation is irrelevant to an equivariant model and equivariance to more symmetries can slightly improve accuracy. The convolutional neural networks rely heavily on batch normalisation, whereas the equivariant models achieve high accuracy, although lower than with batch normalisation present.

    Download full text (pdf)
    fulltext
  • 34.
    Bärkås, Annika
    et al.
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Healthcare Sciences and e-Health.
    Hägglund, Maria
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Healthcare Sciences and e-Health.
    Moll, Jonas
    Cajander, Åsa
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Rexhepi, Hanife
    Hörhammer, Iiris
    Blease, Charlotte
    Scandurra, Isabella
    Patients' Access to Their Psychiatric Records: A Comparison of Four Countries2022In: Challenges of Trustable AI and Added-Value on Health: Proceedings of MIE 2022 / [ed] Brigitte Séroussi, Patrick Weber, Ferdinand Dhombres, Cyril Grouin, Jan-David Liebe, Sylvia Pelayo, Andrea Pinna, Bastien Rance, Lucia Sacchi, Adrien Ugon, Arriel Benis & Parisis Gallos, IOS Press, 2022, p. 510-514Conference paper (Refereed)
    Abstract [en]

    Several Nordic and Baltic countries are forerunners in the digitalization of patient ehealth services and have since long implemented psychiatric records as parts of the ehealth services. There are country-specific differences in what clinical information is offered to patients concerning their online patient accessible psychiatric records. This study explores national differences in Sweden, Norway, Finland, and Estonia in patient access to their psychiatric records. Data was collected through a socio-technical data collection template developed during a workshop series and then analyzed in a cross-country comparison focusing on items related to psychiatry records online. The results show that psychiatric records online are offered to patients in all four countries, and provide the same functionality and similar psychiatry information. Overall, the conclusion is that experiences of various functionalities should be scrutinized to promote transparency of psychiatric records as part of the national eHealth services to increase equality of care and patient empowerment.

    Download full text (pdf)
    fulltext
  • 35.
    Bärkås, Annika
    et al.
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Participatory eHealth and Health Data Research Group. Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Healthcare Sciences and e-Health.
    Kharko, Anna
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Participatory eHealth and Health Data Research Group. Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Healthcare Sciences and e-Health.
    Blease, Charlotte
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Participatory eHealth and Health Data Research Group. Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Healthcare Sciences and e-Health.
    Cajander, Åsa
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Johansen Fagerlund, Asbjørn
    Huvila, Isto
    Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Arts, Department of ALM.
    Johansen, Monika Alise
    Kane, Bridget
    Kujala, Sari
    Moll, Jonas
    Rexhepi, Hanife
    Scandurra, Isabella
    Wang, Bo
    Hägglund, Maria
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Healthcare Sciences and e-Health.
    Errors, Omissions, and Offenses in the Health Record of Mental Health Care Patients: Results from a Nationwide Survey in Sweden2023In: Journal of Medical Internet Research, E-ISSN 1438-8871, Vol. 25, article id e47841Article in journal (Refereed)
    Abstract [en]

    Background: Previous research reports that patients with mental health conditions experience benefits, for example, increased empowerment and validation, from reading their patient-accessible electronic health records (PAEHRs). In mental health care (MHC), PAEHRs remain controversial, as health care professionals are concerned that patients may feel worried or offended by the content of the notes. Moreover, existing research has focused on specific mental health diagnoses, excluding the larger PAEHR userbase with experience in MHC. Objective: The objective of this study is to establish if and how the experiences of patients with and those without MHC differ in using their PAEHRs by (1) comparing patient characteristics and differences in using the national patient portal between the 2 groups and (2) establishing group differences in the prevalence of negative experiences, for example, rates of errors, omissions, and offenses between the 2 groups. Methods: Our analysis was performed on data from an online patient survey distributed through the Swedish national patient portal as part of our international research project, NORDeHEALTH. The respondents were patient users of the national patient portal 1177, aged 15 years or older, and categorized either as those with MHC experience or with any other health care experience (nonmental health care [non-MHC]). Patient characteristics such as gender, age, education, employment, and health status were gathered. Portal use characteristics included frequency of access, encouragement to read the record, and instances of positive and negative experiences. Negative experiences were further explored through rates of error, omission, and offense. The data were summarized through descriptive statistics. Group differences were analyzed through Pearson chi-square. Results: Of the total sample (N=12,334), MHC respondents (n=3131) experienced errors (1586/3131, 50.65%, and non-MHC 3311/9203, 35.98%), omissions (1089/3131, 34.78%, and non-MHC 2427/9203, 26.37%) and offenses (1183/3131, 37.78%, and non-MHC 1616/9203, 17.56%) in the electronic health record at a higher rate than non-MHC respondents (n=9203). Respondents reported that the identified error (MHC 795/3131, 50.13%, and non-MHC 1366/9203, 41.26%) and omission (MHC 622/3131, 57.12%, and non-MHC 1329/9203, 54.76%) were “very important,” but most did nothing to correct them (MHC 792/3131, 41.29%, and non-MHC 1838/9203, 42.17%). Most of the respondents identified as women in both groups. Conclusions: About 1 in 2 MHC patients identified an error in the record, and about 1 in 3 identified an omission, both at a much higher rate than in the non-MHC group. Patients with MHC also felt offended by the content of the notes more commonly (1 in 3 vs 1 in 6). These findings validate some of the worries expressed by health care professionals about providing patients with MHC with PAEHRs and highlight challenges with the documentation quality in the records.

  • 36.
    Cajander, Åsa
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Corneliussen, Hilde
    Western Norway Research Institute.
    Myreteg, Gunilla
    Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Social Sciences, Department of Business Studies. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction.
    Dyb, Kari
    Norwegian Centre for E-health Research.
    What brings women into ehealth?: Women's career trajectories in digital transformations in health care2020In: Proceedings of the 12th International Conference on e-Health, 2020Conference paper (Refereed)
    Abstract [en]

    Digital transformation of health care services is addressed world-wide in order to more efficiently meet the patients’ information and health care needs. However, little is known about the people working with this transformation, where two traditionally gendered fields meet; health care and IT. While work with digitalization generally is dominated by men, digitalization of health care services involves a large number of women. This case study explores the career trajectories of women working with the digital transformation of eHealth services. Who are the women in this eHealth project, and how did they come to working with this digital transformation? The analysis shows different types of trajectories that brought the women into eHealth transformations: The first illustrating women who were pushed into working with eHealth by their job descriptions, the second showing women using eHealth as an escape route from something else, and the last trajectory showing how women stumbled across eHealth and decided to stay on. This has implications for the educational system, and points to the need for being able to study computer science later in life. It also calls for a better understanding of what drives women in transformation processes.

  • 37.
    Cajander, Åsa
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Huvila, Isto
    Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Arts, Department of ALM.
    Salminen-Karlsson, Minna
    Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Arts, Centre for Gender Research.
    Lind, Thomas
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Scandurra, Isabella
    Örebro University School of Business, Örebro, Sweden.
    Effects of patient accessible electronic health records on nurses’ work environment: a survey study on expectations in Sweden2022In: BMJ Open, E-ISSN 2044-6055, Vol. 12, no 11, article id e059188Article in journal (Refereed)
    Abstract [en]

    ObjectivesThe introduction of information and communication technology influences the work environment of large groups of employees in healthcare. In Sweden, a national healthcare service providing patient accessible electronic health records (PAEHR) has been deployed, and this paper investigates nurses' expected effects of this implementation.SettingNurses associated with the Swedish Association of Health Professionals working in healthcare such as primary care, hospitals and midwives in Sweden. Before a full-scale national implementation of PAEHR, a web survey study was distributed nationally. The respondents represented all 21 Swedish regions. Questions included five-point Likert scale questions and open questions.ParticipantsA survey link was distributed via email to 8460 registered nurses, midwives and union representatives in Sweden. The response rate was 35.4% (2867 respondents: registered nurses 84%; midwives 6%; chief position 5%; in projects 2% and other 3%). Three reminders were sent out, all of them increasing the response rate. A majority of the respondents were female (89.9%), 8.4% male, whereas 1.7% did not indicate their gender. 31.4% were under 40 years old, 53.8% 40-59 and 13.7% over 60.ResultsData were analysed using exploratory factor analysis with principal component analysis as the extraction method. The analysis revealed three distinct factors related to nurses' expectations of PAEHR: (1) PAEHR improves the quality of care, (2) PAEHR improves the quality of the work environment and (3) risk and fears concerning patients' well-being. Some interesting results include that more experienced nurses are more favourable to PAEHR. Our analysis also shows that the view of the nurse-patient relationship is an essential underlying factor related to positive or negative expectations.ConclusionsResults show that the expectations and perceptions of PAEHR vary depending on the nurse's view of who the electronic record belongs to. Younger nurses are somewhat more negative towards PAEHR than older nurses.

    Download full text (pdf)
    fulltext
  • 38.
    Cajander, Åsa
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computing Education Research. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Larusdottir, Marta
    Reykjavik University Department of Computer Science, , Menntavegur 1, 102 Reykjavik, Iceland.
    Lind, Thomas
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Stadin, Magdalena
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Experiences of Extensive User Involvement through Vision Seminars in a Large IT Project2023In: Interacting with computers, ISSN 0953-5438, E-ISSN 1873-7951, Vol. 35, no 4, p. 543-552Article in journal (Refereed)
    Abstract [en]

    As the complexity of IT systems increases, the demand for methods taking the whole work situation into account grows. The Vision Seminar (VS) process addresses the future usage of technologies in complex digital work environments. This paper describes the experiences of conducting the VS process in the context of a large IT project to improve study-administrative work. The participants and stakeholders' experiences of participating in VS workshops were studied as the effect the participants and stakeholders believed the vision might have. Data were gathered through interviews and a survey. The participants were confident that the time spent on workshops was worthwhile and that achieving the future described in the resulting vision was feasible. The stakeholders perceived the VS process as rigorous. They were happily surprised by the positive spirit and engagement displayed by the participants. The utility of the resulting vision not being obvious was the most notable weakness mentioned.

  • 39.
    Cajander, Åsa
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computing Education Research. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Lárusdóttir, Marta
    Geiser, Johannes L.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology.
    UX professionals’ learning and usage of UX methods in agile2022In: Information and Software Technology, ISSN 0950-5849, E-ISSN 1873-6025, Vol. 151, p. 107005-107005, article id 107005Article in journal (Refereed)
    Abstract [en]

    Context: The usage of User Experience (UX) methods has been studied through the years. However, little is known about UX professionals’ lifelong learning processes related to UX methods in Agile, choosing what UX methods to use, and the enablers and hindrances for using the UX methods.

    Objective: The study aims to broaden current knowledge about UX professionals’ lifelong learning practices to understand their work situations better. The paper describes how UX professionals learn about and choose UX methods, their frequency of use, and the enablers and barriers when using the UX methods in Agile.

    Method: An interview study was conducted with 13 UX professionals from various industries and two countries working with Agile and UX. We used a qualitative approach, and a thematic analysis was carried out to answer the research questions.

    Results: The results show that support from colleagues is an essential component for learning about the methods and how to use UX methods. Time pressure makes UX professionals choose methods they know will deliver their desired results. Prototyping, user testing, user journeys, and workshops are the most frequently used UX methods. Additionally, the results show that UX professionals think that the UX methods are often too complicated and take too long to learn. Additionally, they find it challenging to integrate UX methods into Agile.

    Conclusion: These findings indicate that UX methods might work better if designed to be less complicated and deliver results more efficiently. Moreover, collegial and peer learning is central to UX professionals. The HCI community could be more active in supporting this culture by sharing information and learning. Finally, the usability and UX of the tools affect which UX methods are used.

    Download full text (pdf)
    fulltext
  • 40.
    Cajander, Åsa
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Lárusdóttir, Marta K.
    Reykjavik University .
    Lind, Thomas
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Nauwerck, Gerolf
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Walking in the Jungle with a Machete: ICT Leaders' Perspectives on User-Centred Systems Design2022In: Behavior and Information Technology, ISSN 0144-929X, E-ISSN 1362-3001, Vol. 41, no 6, p. 1230-1244Article in journal (Refereed)
    Abstract [en]

    Previous research has established that leaders in information and communication technology (ICT) are crucial for establishing a user-centred systems design perspective in ICT for work-related tasks. This paper therefore describes the perspectives of 18 ICT leaders in three kinds of leadership roles (managers, project leaders and specialists) in order to understand their views of user-centred systems design concerning ICT. It uses the concept of technological frames of reference to analyse three domains: technology-in-use, technology strategy and nature of technology. The results show that many specialists see user involvement as a critical factor in successfully establishing new information and communication technologies, but that these systems are currently built around the needs of management rather than end users. Looking forward, all three relevant social groups are optimistic about how ICT will become more user-centred and more strategically aligned in the future. However, changes in ICT are described as extremely energy-consuming and difficult – akin to ‘walking in the jungle with a machete’. Finally, we discuss the relevance of technological frames and present some implications for the successful establishment of user-centred system design as a perspective in organisations.

    Download full text (pdf)
    fulltext
  • 41.
    Cajander, Åsa
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Sandblad, Bengt
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Stadin, Magdalena
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Artificial intelligence, robotisation and the work environment: Literature review2022Report (Other academic)
  • 42.
    Cajander, Åsa
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Sandblad, Bengt
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Stadin, Magdalena
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Raviola, Elena
    Göteborgs universitet .
    Artificiell intelligens, robotisering och arbetsmiljön2022Report (Other (popular science, discussion, etc.))
  • 43.
    Calvo Barajas, Natalia
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Exploring Multidimensional Trust: Shaping Child-Robot Creative Collaborations in Education2023Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    As trust plays a pivotal role in maintaining long-term interactions between children and robots, it is vital to comprehend how children conceptualise trust and the factors influencing their trust in robots. This thesis examines the impact of social robots' behaviours and attributes on children's trust, relationship formation, and task performance in collaborative educational scenarios. A systematic review of child-robot interaction (cHRI) literature identified two primary dimensions of trust: social trust and competency trust. The literature suggests a lack of consensus about how different robot behaviours and attributes affect these two dimensions of trust, as evidence points to different directions. To address these gaps, a collaborative storytelling game was developed to facilitate interactions between children and social robots, aiming to study trust dynamics and enhance learning by fostering children's creativity. The research also examined the impact of robot-related factors, such as behaviour and appearance, on children's interactions with robots. Empirical evidence suggests that while making robots look and behave more like humans is critical for competency trust and task performance, lower human-like attributes are more crucial for developing social trust and relationship formation with robots. Other factors, like time, provide insights into children's trust dynamics. Thus, this thesis explores the role of repeated interactions with artificial agents, indicating that children's competency trust in robots changes over time. This thesis offers significant contributions to the cHRI community. Firstly, it demonstrates that trust is a multidimensional construct that is complex to capture, highlighting the need for reliable, objective measures tailored to the task and intended trust dimension. Secondly, it emphasises the importance of balancing human likeness with social robots when collaborating with children in educational scenarios. Lastly, it proposes that to sustain trustworthy long-term interactions in education; social robots should adapt their behaviour to provide scaffolding, as children will be more inclined to rely on them for learning support as time progresses.

    List of papers
    1. A Meta-analysis on Children’s Trust in Social Robots
    Open this publication in new window or tab >>A Meta-analysis on Children’s Trust in Social Robots
    2021 (English)In: International Journal of Social Robotics, ISSN 1875-4791, E-ISSN 1875-4805, Vol. 13, no 8, p. 1979-2001Article in journal (Refereed) Published
    Abstract [en]

    Although research on children’s trust in social robots is increasingly growing in popularity, a systematic understanding of the factors which influence children’s trust in robots is lacking. In addition, meta-analyses in child–robot-interaction (cHRI) have yet to be popularly adopted as a method for synthesising results. We therefore conducted a meta-analysis aimed at identifying factors influencing children’s trust in robots. We constructed four meta-analytic models based on 20 identified studies, drawn from an initial pool of 414 papers, as a means of investigating the effect of robot embodiment and behaviour on both social and competency trust. Children’s pro-social attitudes towards social robots were also explored. There was tentative evidence to suggest that more human-like attributes lead to less competency trust in robots. In addition, we found a trend towards the type of measure that was used (subjective or objective) influencing the direction of effects for social trust. The meta-analysis also revealed a tendency towards under-powered designs, as well as variation in the methods and measures used to define trust. Nonetheless, we demonstrate that it is still possible to perform rigorous analyses despite these challenges. We also provide concrete methodological recommendations for future research, such as simplifying experimental designs, conducting a priori power analyses and clearer statistical reporting.

    Place, publisher, year, edition, pages
    Springer, 2021
    Keywords
    Trust, Social robot, Child robot interaction, Human robot interaction, Meta-analysis, Review, Robot errorsPro-social attitudes, Developmental
    National Category
    Human Computer Interaction Robotics
    Research subject
    Human-Computer Interaction
    Identifiers
    urn:nbn:se:uu:diva-460444 (URN)10.1007/s12369-020-00736-8 (DOI)000616461300002 ()
    Funder
    EU, Horizon 2020, 765955
    Available from: 2021-12-06 Created: 2021-12-06 Last updated: 2023-04-03Bibliographically approved
    2. "And then what happens?" Promoting Children's Verbal Creativity Using a Robot
    Open this publication in new window or tab >>"And then what happens?" Promoting Children's Verbal Creativity Using a Robot
    Show others...
    2022 (English)In: Proceedings of the 2022 ACM/IEEE International Conference on Human-Robot Interaction (HRI '22), IEEE, 2022, p. 71-79Conference paper, Published paper (Refereed)
    Abstract [en]

    While creativity has been previously studied in Child-Robot interaction, the effect of regulatory focus on creativity skills has not been investigated. This paper presents an exploratory study that, for the first time, uses the Regulatory Focus Theory to assess children's creativity skills in an educational context with a social robot. We investigated whether two key emotional regulation techniques, promotion (approach) and prevention (avoidance), stimulate creativity during a storytelling activity between a child and a robot. We conducted a between-subjects field study with 69 children between the ages of 7 and 9 years old, divided between two study conditions: (1) promotion, where a social robot primes children for action by eliciting positive emotional states, and (2) prevention, where a social robot primes children for avoidance by evoking a states related to security and safety associated with blockage-oriented behaviors. To assess changes in creativity as a response to the priming interaction, children were asked to tell stories to the robot before (pre-test) and after (post-test) the priming interaction. We measured creativity levels by analyzing the verbal content of the stories. We coded verbal expressions related to creativity variables, including fluency, flexibility, elaboration, and originality. Our results show that children in the promotion condition generated significantly more ideas, and their ideas were on average more original in the stories they created in the post-test rather than in the pre-test. We also modeled the process of creativity that emerges during storytelling in response to the robot's verbal behavior. This paper enriches the scientific understanding of creativity emergence in child-robot collaborative interactions.

    Place, publisher, year, edition, pages
    IEEE, 2022
    Series
    ACM/IEEE International Conference on Human-Robot Interaction (HRI), ISSN 2167-2121, E-ISSN 2167-2148
    Keywords
    creativity, regulatory focus, social robots
    National Category
    Robotics
    Research subject
    Computer Science with specialization in Human-Computer Interaction
    Identifiers
    urn:nbn:se:uu:diva-481071 (URN)10.1109/HRI53351.2022.9889408 (DOI)000869793600011 ()978-1-6654-0731-1 (ISBN)978-1-6654-0732-8 (ISBN)
    Conference
    17th Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI), MAR 07-10, 2022, Online
    Funder
    EU, Horizon 2020, 765955
    Available from: 2022-08-02 Created: 2022-08-02 Last updated: 2023-11-22Bibliographically approved
    3. Hurry Up, We Need to Find the Key! How Regulatory Focus Design Affects Children's Trust in a Social Robot
    Open this publication in new window or tab >>Hurry Up, We Need to Find the Key! How Regulatory Focus Design Affects Children's Trust in a Social Robot
    Show others...
    2021 (English)In: Frontiers in Robotics and AI, E-ISSN 2296-9144, Vol. 8, article id 652035Article in journal (Refereed) Published
    Abstract [en]

    In educational scenarios involving social robots, understanding the way robot behaviors affect children's motivation to achieve their learning goals is of vital importance. It is crucial for the formation of a trust relationship between the child and the robot so that the robot can effectively fulfill its role as a learning companion. In this study, we investigate the effect of a regulatory focus design scenario on the way children interact with a social robot. Regulatory focus theory is a type of self-regulation that involves specific strategies in pursuit of goals. It provides insights into how a person achieves a particular goal, either through a strategy focused on "promotion" that aims to achieve positive outcomes or through one focused on "prevention" that aims to avoid negative outcomes. In a user study, 69 children (7-9 years old) played a regulatory focus design goal-oriented collaborative game with the EMYS robot. We assessed children's perception of likability and competence and their trust in the robot, as well as their willingness to follow the robot's suggestions when pursuing a goal. Results showed that children perceived the prevention-focused robot as being more likable than the promotion-focused robot. We observed that a regulatory focus design did not directly affect trust. However, the perception of likability and competence was positively correlated with children's trust but negatively correlated with children's acceptance of the robot's suggestions.

    Place, publisher, year, edition, pages
    Frontiers Media S.A.FRONTIERS MEDIA SA, 2021
    Keywords
    trust, child-robot interaction, regulatory focus, goal orientation, affective, emotional robot
    National Category
    Robotics
    Identifiers
    urn:nbn:se:uu:diva-451600 (URN)10.3389/frobt.2021.652035 (DOI)000675557600001 ()34307468 (PubMedID)
    Funder
    EU, Horizon 2020, 765955
    Available from: 2021-08-30 Created: 2021-08-30 Last updated: 2024-01-15Bibliographically approved
    4. The Effects of Robot’s Facial Expressions on Children’s First Impressions of Trustworthiness
    Open this publication in new window or tab >>The Effects of Robot’s Facial Expressions on Children’s First Impressions of Trustworthiness
    2020 (English)In: 2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), IEEE Press, 2020, p. 165-171Conference paper, Published paper (Refereed)
    Abstract [en]

    Facial expressions of emotions influence the perception of robots in first encounters. People can judge trustworthiness, likability, and aggressiveness in a few milliseconds by simply observing other individuals' faces. While first impressions have been extensively studied in adult-robot interaction, they have been addressed in child-robot interaction only rarely. This knowledge is crucial, as the first impression children build of robots might influence their willingness to interact with them over extended periods of time, for example in applications where robots play the role of companions or tutors. The present study focuses on investigating the effects of facial expressions of emotions on children's perceptions of trust towards robots during first encounters. We constructed a set of facial expressions of happiness and anger varying in terms of intensity. We implemented these facial expressions onto a Furhat robot that was either male-like or female-like. 129 children were exposed to the robot's expressions for a few seconds. We asked them to evaluate the robot in terms of trustworthiness, likability, and competence and investigated how emotion type, emotion intensity, and gender-likeness affected the perception of the robot. Results showed that a few seconds are enough for children to make a trait inference based on the robot's emotion. We observed that emotion type, emotion intensity, and gender-likeness did not directly affect trust, but the perception of likability and competence of the robot served as facilitator to judge trustworthiness.

    Place, publisher, year, edition, pages
    IEEE Press, 2020
    Series
    IEEE RO-MAN, E-ISSN 1944-9437
    Keywords
    Emotion Recognition, face recognition, human-computer interaction, humanoid robots, human-robot interaction
    National Category
    Computer Sciences
    Identifiers
    urn:nbn:se:uu:diva-429723 (URN)10.1109/RO-MAN47096.2020.9223456 (DOI)000598571700025 ()978-1-7281-6075-7 (ISBN)
    Conference
    29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Naples, Italy, 31 Aug.-4 Sept. 2020
    Funder
    EU, Horizon 2020, 765955
    Available from: 2021-01-02 Created: 2021-01-02 Last updated: 2023-04-03Bibliographically approved
    5. Balancing Human Likeness in Social Robots: Impact on Children's Trust and Interaction in a Storytelling Context
    Open this publication in new window or tab >>Balancing Human Likeness in Social Robots: Impact on Children's Trust and Interaction in a Storytelling Context
    (English)Manuscript (preprint) (Other academic)
    Abstract [en]

    While there is evidence that human-like characteristics in robots could benefit child-robot interaction in many ways, open questions remain about the appropriate degree of human likeness that should be implemented in robots to avoid adverse effects on acceptance and trust. This study investigates how human likeness, appearance and behavior, influence children's social and competency trust in a robot. We first designed two versions of the Furhat robot with visual and auditory human-like and machine-like cues validated in two online studies. Secondly, we created verbal behaviors where human likeness was manipulated as responsiveness regarding the robot's lexical alignment. Then, 52 children (7-10 years old) played a storytelling game in a between-subjects experimental design. Results show that the conditions did not affect subjective trust measures. However, objective measures showed that the level of human likeness affects trust differently. While low human-like appearance enhanced social trust, high human-like behavior improved competency trust. This work provides empirical evidence on manipulating facial features and behavior to control human likeness levels in a robot with a highly human-like morphology. We discuss the implications and importance of balancing human likeness in social robot design and its impacts on task performance, as it directly impacts trust-building with children.

    Keywords
    child-robot interaction, social robots, human likeness, trust
    National Category
    Robotics
    Research subject
    Human-Computer Interaction; Computer Science with specialization in Human-Computer Interaction
    Identifiers
    urn:nbn:se:uu:diva-499698 (URN)
    Funder
    EU, Horizon 2020, 765955
    Available from: 2023-04-03 Created: 2023-04-03 Last updated: 2023-04-03
    6. "I have an idea!": Enhancing Children's Verbal Creativity through Repeated Interactions with a Virtual Robot
    Open this publication in new window or tab >>"I have an idea!": Enhancing Children's Verbal Creativity through Repeated Interactions with a Virtual Robot
    2022 (English)In: IVA '22: Proceedings of the 22nd ACM International Conference on Intelligent Virtual Agents, ACM Digital Library, 2022, article id 10Conference paper, Published paper (Refereed)
    Abstract [en]

    In the context of child development, practice is recognised as one of the essential activities to stimulate creativity. Here we aimed to explore whether repeated interactions with a virtual social robot could help build up children's creative performance over time. To this end, we developed an interactive storytelling game with the virtual robot Furhat. Twenty-five children between 9- and 12- years old played the online game two times with seven days of zero exposure in between. Our results revealed that repeated encounters have mixed effects on verbal creativity: while children were more creative in terms of flexibility, fluency, and elaboration in the second interaction, the level of originality remained stagnant. Moreover, the second encounter positively affected children's collaboration with and social behaviour toward the virtual robot. These results provide valuable evidence supporting the potential of multiple interactions with artificial agents to foster children's creativity over time. This paper, thus, provides readers with (1) a novel approach to stimulating verbal creativity through practice with artificial agents, (2) an assessment of the creative process in repeated interactions, and (3) evidence of how the behaviour of the robot influences children's creativity and their behaviour over time. 

    Place, publisher, year, edition, pages
    ACM Digital Library, 2022
    Keywords
    creativity, virtual robots, long-term interaction, storytelling
    National Category
    Robotics
    Research subject
    Computer Science with specialization in Human-Computer Interaction
    Identifiers
    urn:nbn:se:uu:diva-481075 (URN)10.1145/3514197.3549690 (DOI)001118873500026 ()978-1-4503-9248-8 (ISBN)
    Conference
    22nd ACM International Conference on Intelligent Virtual Agents (IVA), SEP 06-09, 2022, Univ Algarve, Faro, PORTUGAL
    Funder
    EU, Horizon 2020, 765955
    Available from: 2022-08-02 Created: 2022-08-02 Last updated: 2024-06-27Bibliographically approved
    7. Understanding Children's Trust Development through Repeated Interactions with a Virtual Social Robot
    Open this publication in new window or tab >>Understanding Children's Trust Development through Repeated Interactions with a Virtual Social Robot
    2022 (English)In: 2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Institute of Electrical and Electronics Engineers (IEEE), 2022, p. 1451-1458Conference paper, Published paper (Refereed)
    Abstract [en]

    Studies in Child-Robot Interaction have shown that children form first impressions of a robot's trustworthiness that might influence how they interact with social robots in long-term interactions. However, how children's trust in robots evolves and how it relates to relationship formation is not well understood. This study investigates the effects of repeated encounters with a virtual social robot on children's social and competency trust in social robots and their relationship formation. We developed an online storytelling game with the Furhat robot, where 25 children (9-12 years old) played with the robot over two sessions with seven days of zero exposure in between. Results show that children's competency trust improved with time. We also found empirical evidence that children felt closer to the robot in the second encounter. This work enriches the scientific understanding of children's trust development in social robots over extended periods of time in child-robot collaborative interactions.

    Place, publisher, year, edition, pages
    Institute of Electrical and Electronics Engineers (IEEE), 2022
    National Category
    Robotics
    Research subject
    Computer Science with specialization in Human-Computer Interaction
    Identifiers
    urn:nbn:se:uu:diva-481074 (URN)10.1109/RO-MAN53752.2022.9900537 (DOI)000885903300206 ()
    Conference
    31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), 29 August-2 September 2022, Napoli, Italy
    Funder
    EU, Horizon 2020, 765955Wallenberg AI, Autonomous Systems and Software Program (WASP)Marianne and Marcus Wallenberg FoundationMarcus and Amalia Wallenberg Foundation
    Available from: 2022-08-02 Created: 2022-08-02 Last updated: 2023-04-03Bibliographically approved
    Download full text (pdf)
    UUThesis_N-Calvo-Barajas-2023
    Download (jpg)
    preview image
  • 44.
    Calvo Barajas, Natalia
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Akkuzu, Anastasia
    Castellano, Ginevra
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Balancing Human Likeness in Social Robots: Impact on Children's Trust and Interaction in a Storytelling ContextManuscript (preprint) (Other academic)
    Abstract [en]

    While there is evidence that human-like characteristics in robots could benefit child-robot interaction in many ways, open questions remain about the appropriate degree of human likeness that should be implemented in robots to avoid adverse effects on acceptance and trust. This study investigates how human likeness, appearance and behavior, influence children's social and competency trust in a robot. We first designed two versions of the Furhat robot with visual and auditory human-like and machine-like cues validated in two online studies. Secondly, we created verbal behaviors where human likeness was manipulated as responsiveness regarding the robot's lexical alignment. Then, 52 children (7-10 years old) played a storytelling game in a between-subjects experimental design. Results show that the conditions did not affect subjective trust measures. However, objective measures showed that the level of human likeness affects trust differently. While low human-like appearance enhanced social trust, high human-like behavior improved competency trust. This work provides empirical evidence on manipulating facial features and behavior to control human likeness levels in a robot with a highly human-like morphology. We discuss the implications and importance of balancing human likeness in social robot design and its impacts on task performance, as it directly impacts trust-building with children.

  • 45.
    Calvo-Barajas, Natalia
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Castellano, Ginevra
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Understanding Children's Trust Development through Repeated Interactions with a Virtual Social Robot2022In: 2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Institute of Electrical and Electronics Engineers (IEEE), 2022, p. 1451-1458Conference paper (Refereed)
    Abstract [en]

    Studies in Child-Robot Interaction have shown that children form first impressions of a robot's trustworthiness that might influence how they interact with social robots in long-term interactions. However, how children's trust in robots evolves and how it relates to relationship formation is not well understood. This study investigates the effects of repeated encounters with a virtual social robot on children's social and competency trust in social robots and their relationship formation. We developed an online storytelling game with the Furhat robot, where 25 children (9-12 years old) played with the robot over two sessions with seven days of zero exposure in between. Results show that children's competency trust improved with time. We also found empirical evidence that children felt closer to the robot in the second encounter. This work enriches the scientific understanding of children's trust development in social robots over extended periods of time in child-robot collaborative interactions.

    Download full text (pdf)
    fulltext
  • 46.
    Chatterjee, Swarnadip
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Sladoje, Nataša
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Lindblad, Joakim
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    DCNN based Oral Cancer Screening using Whole Slide Cytology Images: Effect of Increased Patch Size2022Conference paper (Other academic)
    Abstract [en]

    Cases of Oral Cancer are increasing around the world. Oral Squamous Cell Carcinomas constitute majority of all Oral Cancer cases and arise from the oral epithelium. Although this type of Oral Cancer is highly accessible to clinicians as they are superficial, they are often discovered late. To improve early detection in order to increase the chances of survival, we propose a Deep Convolutional Neural Network based framework on whole slide cytology images. In this ongoing work, we have shown that increasing the size of the patch centered at the detected nuclei, increases the accuracy of classification of the pathological condition of the nuclei using only slide-level labels.

  • 47.
    Chatterjee, Swarnadip
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Sladoje, Nataša
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Lindblad, Joakim
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Investigating the Relevance of Contextual Information Towards Improving Deep CNN Based Oral Cancer Screening on Whole Slide Cytology Samples2023Conference paper (Other academic)
    Abstract [en]

    Cases of Oral Cancer are increasing around the world. Oral Squamous Cell Carcinomas constitute the majority of all oral cancer cases and arise from the oral epithelium. Although this type of cancer is superficial and highly accessible to clinicians, it is often discovered late. To improve early detection in order to increase the chances of survival, we propose a Deep Convolutional Neural Network based framework on whole slide cytology images. In this ongoing work, we investigate the relevance of contextual information towards improving accuracy of classification of the pathological condition of cells from brush samples using only slide-level labels. For this, we consider nuclei centered patches of sizes 80 × 80, 160 × 160, 240 × 240, and 320 × 320 pixels and observe an increasing trend in the classification performances with respect to increasing patch sizes for three deep CNN architectures: ResNet50, DenseNet201 and SEResNet50.

  • 48. Chen, Boqi
    et al.
    Thandiackal, Kevin
    Pati, Pushpak
    Göksel, Orcun
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3.
    Generative appearance replay for continual unsupervised domain adaptation2023In: Medical Image Analysis, ISSN 1361-8415, E-ISSN 1361-8423, Vol. 89, p. 102924-102924, article id 102924Article in journal (Refereed)
    Abstract [en]

    Deep learning models can achieve high accuracy when trained on large amounts of labeled data. However, real-world scenarios often involve several challenges: Training data may become available in installments, may originate from multiple different domains, and may not contain labels for training. Certain settings, for instance medical applications, often involve further restrictions that prohibit retention of previously seen data due to privacy regulations. In this work, to address such challenges, we study unsupervised segmentation in continual learning scenarios that involve domain shift. To that end, we introduce GarDA (Generative Appearance Replay for continual Domain Adaptation), a generative-replay based approach that can adapt a segmentation model sequentially to new domains with unlabeled data. In contrast to single-step unsupervised domain adaptation (UDA), continual adaptation to a sequence of domains enables leveraging and consolidation of information from multiple domains. Unlike previous approaches in incremental UDA, our method does not require access to previously seen data, making it applicable in many practical scenarios. We evaluate GarDA on three datasets with different organs and modalities, where it substantially outperforms existing techniques. Our code is available at: https://github.com/histocartography/generative-appearance-replay.Previous article in issue

    Download full text (pdf)
    fulltext
  • 49.
    Chintada, Bhaskara Rao
    et al.
    Swiss Fed Inst Technol, Comp Assisted Applicat Med, Zurich, Switzerland..
    Rau, Richard
    Swiss Fed Inst Technol, Comp Assisted Applicat Med, Zurich, Switzerland..
    Göksel, Orcun
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Swiss Fed Inst Technol, Comp Assisted Applicat Med, Zurich, Switzerland..
    Spectral Ultrasound Imaging of Speed-of-Sound and Attenuation Using an Acoustic Mirror2022In: Frontiers in Physics, E-ISSN 2296-424X, Vol. 10, article id 860725Article in journal (Refereed)
    Abstract [en]

    Speed-of-sound and attenuation of ultrasound waves vary in the tissues. There exist methods in the literature that allow for spatially reconstructing the distribution of group speed-of-sound (SoS) and frequency-dependent ultrasound attenuation (UA) using reflections from an acoustic mirror positioned at a known distance from the transducer. These methods utilize a conventional ultrasound transducer operating in pulse-echo mode and a calibration protocol with measurements in water. In this study, we introduce a novel method for reconstructing local SoS and UA maps as a function of acoustic frequency through Fourier-domain analysis and by fitting linear and power-law dependency models in closed form. Frequency-dependent SoS and UA together characterize the tissue comprehensively in spectral domain within the utilized transducer bandwidth. In simulations, our proposed methods are shown to yield low reconstruction error: 0.01 dB/cm.MHz(y) for attenuation coefficient and 0.05 for the frequency exponent. For tissue-mimicking phantoms and ex-vivo bovine muscle samples, a high reconstruction contrast was achieved. Attenuation exponents in a gelatin-cellulose mixture and an ex-vivo bovine muscle sample were found to be, respectively, 1.3 and 0.6 on average. Linear dispersion of SoS in a gelatin-cellulose mixture and an ex-vivo bovine muscle sample were found to be, respectively, 1.3 and 4.0 m/s.MHz on average. These findings were reproducible when the inclusion and substrate materials were exchanged. Bulk loss modulus in the bovine muscle sample was computed to be approximately 4 times the bulk loss modulus in the gelatin-cellulose mixture. Such frequency-dependent characteristics of SoS and UA, and bulk loss modulus may therefore differentiate tissues as potential diagnostic biomarkers.

    Download full text (pdf)
    FULLTEXT01
  • 50.
    Daniels, Mats
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computing Education Research. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. University of Uppsala,Department of Information Technology,Uppsala,Sweden.
    Berglund, Anders
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computing Education Research. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division Vi3. University of Uppsala,Department of Information Technology,Uppsala,Sweden.
    McDermott, Roger
    Robert Gordon University,School of Computing,Aberdeen,United Kingdom.
    Influencing Student Academic Integrity Choices using Ethics Scenarios2022Conference paper (Refereed)
    Abstract [en]

    Academic misconduct seems to have increased substantially during the pandemic, with a worldwide upsurge in reported cases. The aim of this project is to construct a framework for helping students engage with issues concerning academic integrity and avoid academic misconduct. This Work-In-Progress paper reports on the construction of a scenario-based framework to investigate the beliefs and attitudes of university stakeholders when confronted with decisions about potential academic misconduct. The framework will be based on using scenarios to spur individual reflections and discussions among the students regarding values related to academic integrity focusing on Uppsala University context. A repository of "misconduct" scenarios related to different cultures, including different views and regulations, is intended to support teachers to develop modules tailored to their current need. The underlying idea is to provide students with an understanding of what constitutes academic misconduct in Uppsala University setting and to help them find honest alternatives when faced with temptations to "cheat". Our view is that students, in general, want to behave honestly, and that this framework will provide a means to help students follow their moral "compass" and avoid dishonest behaviour.

123456 1 - 50 of 254
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf