uu.seUppsala University Publications
Change search
Link to record
Permanent link

Direct link
BETA
Wählby, Carolina, professorORCID iD iconorcid.org/0000-0002-4139-7003
Alternative names
Publications (10 of 101) Show all publications
Strom, P., Kartasalo, K., Olsson, H., Solorzano, L., Delahunt, B., Berney, D. M., . . . Eklund, M. (2020). Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study. The Lancet Oncology, 21(2), 222-232
Open this publication in new window or tab >>Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study
Show others...
2020 (English)In: The Lancet Oncology, ISSN 1470-2045, E-ISSN 1474-5488, Vol. 21, no 2, p. 222-232Article in journal (Refereed) Published
Abstract [en]

Background

An increasing volume of prostate biopsies and a worldwide shortage of urological pathologists puts a strain on pathology departments. Additionally, the high intra-observer and inter-observer variability in grading can result in overtreatment and undertreatment of prostate cancer. To alleviate these problems, we aimed to develop an artificial intelligence (AI) system with clinically acceptable accuracy for prostate cancer detection, localisation, and Gleason grading.

Methods

We digitised 6682 slides from needle core biopsies from 976 randomly selected participants aged 50–69 in the Swedish prospective and population-based STHLM3 diagnostic study done between May 28, 2012, and Dec 30, 2014 (ISRCTN84445406), and another 271 from 93 men from outside the study. The resulting images were used to train deep neural networks for assessment of prostate biopsies. The networks were evaluated by predicting the presence, extent, and Gleason grade of malignant tissue for an independent test dataset comprising 1631 biopsies from 246 men from STHLM3 and an external validation dataset of 330 biopsies from 73 men. We also evaluated grading performance on 87 biopsies individually graded by 23 experienced urological pathologists from the International Society of Urological Pathology. We assessed discriminatory performance by receiver operating characteristics and tumour extent predictions by correlating predicted cancer length against measurements by the reporting pathologist. We quantified the concordance between grades assigned by the AI system and the expert urological pathologists using Cohen's kappa.

Findings

The AI achieved an area under the receiver operating characteristics curve of 0·997 (95% CI 0·994–0·999) for distinguishing between benign (n=910) and malignant (n=721) biopsy cores on the independent test dataset and 0·986 (0·972–0·996) on the external validation dataset (benign n=108, malignant n=222). The correlation between cancer length predicted by the AI and assigned by the reporting pathologist was 0·96 (95% CI 0·95–0·97) for the independent test dataset and 0·87 (0·84–0·90) for the external validation dataset. For assigning Gleason grades, the AI achieved a mean pairwise kappa of 0·62, which was within the range of the corresponding values for the expert pathologists (0·60–0·73).

Interpretation

An AI system can be trained to detect and grade cancer in prostate needle biopsy samples at a ranking comparable to that of international experts in prostate pathology. Clinical application could reduce pathology workload by reducing the assessment of benign biopsies and by automating the task of measuring cancer length in positive biopsy cores. An AI system with expert-level grading performance might contribute a second opinion, aid in standardising grading, and provide pathology expertise in parts of the world where it does not exist.

National Category
Cancer and Oncology Urology and Nephrology
Identifiers
urn:nbn:se:uu:diva-407437 (URN)10.1016/S1470-2045(19)30738-7 (DOI)000510481800031 ()31926806 (PubMedID)
Funder
Swedish Research CouncilSwedish Cancer SocietyForte, Swedish Research Council for Health, Working Life and WelfareEU, European Research Council, ERC-2015-CoG 682810Swedish e‐Science Research CenterAcademy of Finland, 313921
Available from: 2020-03-26 Created: 2020-03-26 Last updated: 2020-03-26Bibliographically approved
Gupta, A., Harrison, P. J., Wieslander, H., Pielawski, N., Kartasalo, K., Partel, G., . . . Wählby, C. (2019). Deep Learning in Image Cytometry: A Review. Cytometry Part A, 95(6), 366-380
Open this publication in new window or tab >>Deep Learning in Image Cytometry: A Review
Show others...
2019 (English)In: Cytometry Part A, ISSN 1552-4922, E-ISSN 1552-4930, Vol. 95, no 6, p. 366-380Article, review/survey (Refereed) Published
National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-371631 (URN)10.1002/cyto.a.23701 (DOI)000466792700002 ()30565841 (PubMedID)
Funder
Swedish Foundation for Strategic Research , BD15-0008SB16-0046Swedish Research Council, 2014-6075EU, European Research Council, ERC-2015-CoG 683810
Available from: 2018-12-19 Created: 2018-12-21 Last updated: 2019-06-14Bibliographically approved
Günaydin, G., Edfeldt, G., Garber, D. A., Asghar, M., Noel-Romas, L., Burgener, A., . . . Broliden, K. (2019). Impact of Q-Griffithsin anti-HIV microbicide gel in non-human primates: In situ analyses of epithelial and immune cell markers in rectal mucosa. Scientific Reports, 9, Article ID 18120.
Open this publication in new window or tab >>Impact of Q-Griffithsin anti-HIV microbicide gel in non-human primates: In situ analyses of epithelial and immune cell markers in rectal mucosa
Show others...
2019 (English)In: Scientific Reports, ISSN 2045-2322, E-ISSN 2045-2322, Vol. 9, article id 18120Article in journal (Refereed) Published
Abstract [en]

Natural-product derived lectins can function as potent viral inhibitors with minimal toxicity as shown in vitro and in small animal models. We here assessed the effect of rectal application of an anti-HIV lectin-based microbicide Q-Griffithsin (Q-GRFT) in rectal tissue samples from rhesus macaques. E-cadherin(+) cells, CD4(+) cells and total mucosal cells were assessed using in situ staining combined with a novel customized digital image analysis platform. Variations in cell numbers between baseline, placebo and Q-GRFT treated samples were analyzed using random intercept linear mixed effect models. The frequencies of rectal E-cadherin(+) cells remained stable despite multiple tissue samplings and Q-GRFT gel (0.1%, 0.3% and 1%, respectively) treatment. Whereas single dose application of Q-GRFT did not affect the frequencies of rectal CD4(+) cells, multi-dose Q-GRFT caused a small, but significant increase of the frequencies of intra-epithelial CD4(+) cells (placebo: median 4%; 1% Q-GRFT: median 7%) and of the CD4(+) lamina propria cells (placebo: median 30%; 0.1-1% Q-GRFT: median 36-39%). The resting time between sampling points were further associated with minor changes in the total and CD4(+) rectal mucosal cell levels. The results add to general knowledge of in vivo evaluation of anti-HIV microbicide application concerning cellular effects in rectal mucosa.

Place, publisher, year, edition, pages
NATURE PUBLISHING GROUP, 2019
National Category
Cell and Molecular Biology
Identifiers
urn:nbn:se:uu:diva-400679 (URN)10.1038/s41598-019-54493-4 (DOI)000500566600001 ()31792342 (PubMedID)
Funder
Swedish Research Council
Available from: 2020-01-02 Created: 2020-01-02 Last updated: 2020-01-02Bibliographically approved
Runow Stark, C., Gustavsson, I., Gyllensten, U., Darai Ramqvist, E., Lindblad, J., Wählby, C., . . . Hirsch, J.-M. (2018). Brush Biopsy For HR-HPV Detection With FTA Card And AI For Cytology Analysis - A Viable Non-invasive Alternative. In: Bengt Hasséus (Ed.), EAOM2018: . Paper presented at 14th Biennial Congress of the European Association of Oral Medicine, Göteborg, Sweden, September 2018.
Open this publication in new window or tab >>Brush Biopsy For HR-HPV Detection With FTA Card And AI For Cytology Analysis - A Viable Non-invasive Alternative
Show others...
2018 (English)In: EAOM2018 / [ed] Bengt Hasséus, 2018Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

Introduction: Oral cancer accounts for about 800-1,000 new cases each year in Sweden and the ratio of cancer related to high-risk human papillomavirus (HR-HPV) is increasing in the younger population due to changes in sexual habits. The most two frequent HR-HPV types 16 and 18 have both significant oncogenic potential.

Objectives: In this pilot study we evaluate two non-invasive automated methods; 1) detection of HR-HPV using FTA cards, and 2) image scanning of cytology for detection of premalignant lesions as well as eradicate the early stage of neoplasia.

Material and Methods: 160 patients with verified HR-HPV oropharyngeal cancer, previous ano-genital HR-HPV-infection or potentially malignant oral disorder were recruited for non-invasive brush sampling and analyzed with two validated automated methods both used in cervix cancer screening. For analysis of HR-HPV DNA the indicating FTA elute micro cardTM were used for dry collection, transportation and storage of the brush samples. For analysis of cell morphology changes an automated liquid base Cytology method (Preserve Cyt) combined with deep learning computer aided technique was used.

Results: Preliminary results show that the FTA-method is reliable and indicates that healthy and malignant brush samples can be separated by image analysis. 

Conclusions: With further development of these fully automated methods, it is possible to implement a National Screening Program of the oral mucosa, and thereby select patients for further investigation in order to find lesions with potential malignancy in an early stage. 

Keywords
cytometry, deep learning, oral cancer, image analysis, HPV
National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-367985 (URN)
Conference
14th Biennial Congress of the European Association of Oral Medicine, Göteborg, Sweden, September 2018
Funder
VINNOVA, 2017-02447
Available from: 2018-12-02 Created: 2018-12-02 Last updated: 2018-12-02
Bengtsson, E., Wieslander, H., Forslid, G., Wählby, C., Hirsch, J.-M., Runow Stark, C., . . . Lindblad, J. (2018). Detection of Malignancy-Associated Changes Due to Precancerous and Oral Cancer Lesions: A Pilot Study Using Deep Learning. In: Andrea Cossarizza (Ed.), CYTO2018: . Paper presented at 33rd Congress of the International Society for Advancement of Cytometry.
Open this publication in new window or tab >>Detection of Malignancy-Associated Changes Due to Precancerous and Oral Cancer Lesions: A Pilot Study Using Deep Learning
Show others...
2018 (English)In: CYTO2018 / [ed] Andrea Cossarizza, 2018Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

Background: The incidence of oral cancer is increasing and it is effecting younger individuals. PAP smear-based screening, visual, and automated, have been used for decades, to successfully decrease the incidence of cervical cancer. Can similar methods be used for oral cancer screening? We have carried out a pilot study using neural networks for classifying cells, both from cervical cancer and oral cancer patients. The results which were reported from a technical point of view at the 2017 IEEE International Conference on Computer Vision Workshop (ICCVW), were particularly interesting for the oral cancer cases, and we are currently collecting and analyzing samples from more patients. Methods: Samples were collected with a brush in the oral cavity and smeared on glass slides, stained, and prepared, according to standard PAP procedures. Images from the slides were digitized with a 0.35 micron pixel size, using focus stacks with 15 levels 0.4 micron apart. Between 245 and 2,123 cell nuclei were manually selected for analysis for each of 14 datasets, usually 2 datasets for each of the 6 cases, in total around 15,000 cells. A small region was cropped around each nucleus, and the best 2 adjacent focus layers in each direction were automatically found, thus creating images of 100x100x5 pixels. Nuclei were chosen with an aim to select well preserved free-lying cells, with no effort to specifically select diagnostic cells. We therefore had no ground truth on the cellular level, only on the patient level. Subsets of these images were used for training 2 sets of neural networks, created according to the ResNet and VGG architectures described in literature, to distinguish between cells from healthy persons, and those with precancerous lesions. The datasets were augmented through mirroring and 90 degrees rotations. The resulting networks were used to classify subsets of cells from different persons, than those in the training sets. This was repeated for a total of 5 folds. Results: The results were expressed as the percentage of cell nuclei that the neural networks indicated as positive. The percentage of positive cells from healthy persons was in the range 8% to 38%. The percentage of positive cells collected near the lesions was in the range 31% to 96%. The percentages from the healthy side of the oral cavity of patients with lesions ranged 37% to 89%. For each fold, it was possible to find a threshold for the number of positive cells that would correctly classify all patients as normal or positive, even for the samples taken from the healthy side of the oral cavity. The network based on the ResNet architecture showed slightly better performance than the VGG-based one. Conclusion: Our small pilot study indicates that malignancyassociated changes that can be detected by neural networks may exist among cells in the oral cavity of patients with precancerous lesions. We are currently collecting samples from more patients, and will present those results as well, with our poster at CYTO 2018.

Keywords
cytometry, deep learning, oral cancer, image analysis
National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-366820 (URN)
Conference
33rd Congress of the International Society for Advancement of Cytometry
Funder
VINNOVA
Available from: 2018-11-26 Created: 2018-11-26 Last updated: 2018-11-26
Gibbs, A., Buggert, M., Edfeldt, G., Ranefall, P., Introini, A., Cheuk, S., . . . Tjernlund, A. (2018). Human Immunodeficiency Virus-Infected Women Have High Numbers of CD103-CD8+ T Cells Residing Close to the Basal Membrane of the Ectocervical Epithelium. Journal of Infectious Diseases, 218(3), 453-465
Open this publication in new window or tab >>Human Immunodeficiency Virus-Infected Women Have High Numbers of CD103-CD8+ T Cells Residing Close to the Basal Membrane of the Ectocervical Epithelium
Show others...
2018 (English)In: Journal of Infectious Diseases, ISSN 0022-1899, E-ISSN 1537-6613, Vol. 218, no 3, p. 453-465Article in journal (Refereed) Published
National Category
Infectious Medicine
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-361497 (URN)10.1093/infdis/jix661 (DOI)000439174200014 ()29272532 (PubMedID)
Available from: 2017-12-20 Created: 2018-09-26 Last updated: 2018-09-27Bibliographically approved
Matuszewski, D. J., Wählby, C., Krona, C., Nelander, S. & Sintorn, I.-M. (2018). Image-Based Detection of Patient-Specific Drug-Induced Cell-Cycle Effects in Glioblastoma. SLAS Discovery: Advancing Life Sciences R&D, 23(10), 1030-1039
Open this publication in new window or tab >>Image-Based Detection of Patient-Specific Drug-Induced Cell-Cycle Effects in Glioblastoma
Show others...
2018 (English)In: SLAS Discovery: Advancing Life Sciences R&D, ISSN 2472-5552, Vol. 23, no 10, p. 1030-1039Article in journal (Refereed) Published
Abstract [en]

Image-based analysis is an increasingly important tool to characterize the effect of drugs in large-scale chemical screens. Herein, we present image and data analysis methods to investigate population cell-cycle dynamics in patient-derived brain tumor cells. Images of glioblastoma cells grown in multiwell plates were used to extract per-cell descriptors, including nuclear DNA content. We reduced the DNA content data from per-cell descriptors to per-well frequency distributions, which were used to identify compounds affecting cell-cycle phase distribution. We analyzed cells from 15 patient cases representing multiple subtypes of glioblastoma and searched for clusters of cell-cycle phase distributions characterizing similarities in response to 249 compounds at 11 doses. We show that this approach applied in a blind analysis with unlabeled substances identified drugs that are commonly used for treating solid tumors as well as other compounds that are well known for inducing cell-cycle arrest. Redistribution of nuclear DNA content signals is thus a robust metric of cell-cycle arrest in patient-derived glioblastoma cells.

National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-368698 (URN)10.1177/2472555218791414 (DOI)000452283500003 ()30074852 (PubMedID)
Funder
AstraZenecaSwedish Research Council, 2012-4968; 2014-6075eSSENCE - An eScience Collaboration
Available from: 2018-12-06 Created: 2018-12-06 Last updated: 2019-10-09Bibliographically approved
Holzwarth, K., Köhler, R., Philipsen, L., Tokoyoda, K., Ladyhina, V., Wählby, C., . . . Hauser, A. E. (2018). Multiplexed fluorescence microscopy reveals heterogeneity among stromal cells in mouse bone marrow sections. Cytometry Part A, 93(9), 876-888
Open this publication in new window or tab >>Multiplexed fluorescence microscopy reveals heterogeneity among stromal cells in mouse bone marrow sections
Show others...
2018 (English)In: Cytometry Part A, ISSN 1552-4922, E-ISSN 1552-4930, Vol. 93, no 9, p. 876-888Article in journal (Refereed) Published
National Category
Cell and Molecular Biology Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-363627 (URN)10.1002/cyto.a.23526 (DOI)000445603300002 ()30107096 (PubMedID)
Available from: 2018-08-14 Created: 2018-10-25 Last updated: 2018-10-31Bibliographically approved
Zhang, H., Ericsson, M., Virtanen, M., Weström, S., Wählby, C., Vahlquist, A. & Törmä, H. (2018). Quantitative image analysis of protein expression and colocalisation in skin sections [Letter to the editor]. Experimental dermatology, 27(2), 196-199
Open this publication in new window or tab >>Quantitative image analysis of protein expression and colocalisation in skin sections
Show others...
2018 (English)In: Experimental dermatology, ISSN 0906-6705, E-ISSN 1600-0625, Vol. 27, no 2, p. 196-199Article in journal, Letter (Refereed) Published
Abstract [en]

Immunofluorescence (IF) and in situ proximity ligation assay (isPLA) are techniques that are used for in situ protein expression and colocalisation analysis, respectively. However, an efficient quantitative method to analyse both IF and isPLA staining on skin sections is lacking. Therefore, we developed a new method for semi-automatic quantitative layer-by-layer measurement of protein expression and colocalisation in skin sections using the free open-source software CellProfiler. As a proof of principle, IF and isPLA of ichthyosis-related proteins TGm-1 and SDR9C7 were examined. The results indicate that this new method can be used for protein expression and colocalisation analysis in skin sections.

National Category
Biomedical Laboratory Science/Technology Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-338544 (URN)10.1111/exd.13457 (DOI)000423679700014 ()
Projects
Inherited skin disorders
Funder
Swedish Research Council, K2013-57x-22309-3
Available from: 2018-01-09 Created: 2018-01-10 Last updated: 2019-02-21Bibliographically approved
Edfeldt, G., Lajoie, J., Röhl, M., Omollo, K., Wählby, C., Boily-Larouche, G., . . . Tjernlund, A. (2018). The Effect of DMPA Use on the Human Cervical Epithelium: Mechanisms Revealed by Image Analysis. Paper presented at HIV Research for Prevention Meeting (HIVR4P 2018), October 21–25, Madrid, Spain. AIDS Research and Human Retroviruses, 34(S1), 310-310
Open this publication in new window or tab >>The Effect of DMPA Use on the Human Cervical Epithelium: Mechanisms Revealed by Image Analysis
Show others...
2018 (English)In: AIDS Research and Human Retroviruses, ISSN 0889-2229, E-ISSN 1931-8405, Vol. 34, no S1, p. 310-310Article in journal, Meeting abstract (Other academic) Published
National Category
Microbiology in the medical area
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-370042 (URN)000448371600570 ()
Conference
HIV Research for Prevention Meeting (HIVR4P 2018), October 21–25, Madrid, Spain
Available from: 2018-10-22 Created: 2019-01-08 Last updated: 2019-01-10Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-4139-7003

Search in DiVA

Show all publications