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

Direct 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
Image and Data Analysis for Biomedical Quantitative Microscopy
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.ORCID iD: 0000-0002-6148-5174
2019 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

This thesis presents automatic image and data analysis methods to facilitate and improve microscopy-based research and diagnosis. New technologies and computational tools are necessary for handling the ever-growing amounts of data produced in life science. The thesis presents methods developed in three projects with different biomedical applications.

In the first project, we analyzed a large high-content screen aimed at enabling personalized medicine for glioblastoma patients. We focused on capturing drug-induced cell-cycle disruption in fluorescence microscopy images of cancer cell cultures. Our main objectives were to identify drugs affecting the cell-cycle and to increase the understanding of different drugs’ mechanisms of action.  Here we present tools for automatic cell-cycle analysis and identification of drugs of interest and their effective doses.

In the second project, we developed a feature descriptor for image matching. Image matching is a central pre-processing step in many applications. For example, when two or more images must be matched and registered to create a larger field of view or to analyze differences and changes over time. Our descriptor is rotation-, scale-, and illumination-invariant and it has a short feature vector which makes it computationally attractive. The flexibility to combine it with any feature detector and the customization possibility make it a very versatile tool.

In the third project, we addressed two general problems for bridging the gap between deep learning method development and their use in practical scenarios. We developed a method for convolutional neural network training using minimally annotated images. In many biomedical applications, the objects of interest cannot be accurately delineated due to their fuzzy shape, ambiguous morphology, image quality, or the expert knowledge and time it requires. The minimal annotations, in this case, consist of center-points or centerlines of target objects of approximately known size. We demonstrated our training method in a challenging application of a multi-class semantic segmentation of viruses in transmission electron microscopy images. We also systematically explored the influence of network architecture hyper-parameters on its size and performance and show the possibility to substantially reduce the size of a network without compromising its performance.

All methods in this thesis were designed to work with little or no input from biomedical experts but of course, require fine-tuning for new applications. The usefulness of the tools has been demonstrated by collaborators and other researchers and has inspired further development of related algorithms.

Place, publisher, year, edition, pages
Uppsala: Acta Universitatis Upsaliensis, 2019. , p. 63
Series
Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology, ISSN 1651-6214 ; 1864
Keywords [en]
high-content screening, drug selection, DNA content histogram, manual image annotation, deep learning, convolutional neural networks, hardware integration
National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
URN: urn:nbn:se:uu:diva-394709ISBN: 978-91-513-0771-8 (print)OAI: oai:DiVA.org:uu-394709DiVA, id: diva2:1359483
Public defence
2019-12-12, 2446, ITC, Polacksbacken, Lägerhyddsvägen 2, Uppsala, 10:15 (English)
Opponent
Supervisors
Available from: 2019-11-20 Created: 2019-10-09 Last updated: 2019-11-27
List of papers
1. Comparison of Flow Cytometry and Image-Based Screening for Cell Cycle Analysis
Open this publication in new window or tab >>Comparison of Flow Cytometry and Image-Based Screening for Cell Cycle Analysis
2016 (English)In: Image Analysis And Recognition (ICIAR 2016) / [ed] Aurélio Campilho, Fakhri Karray, Springer, 2016, Vol. 9730, p. 623-630Conference paper, Published paper (Refereed)
Abstract [en]

Quantitative cell state measurements can provide a wealth of information about mechanism of action of chemical compounds and gene functionality. Here we present a comparison of cell cycle disruption measurements from commonly used flow cytometry (generating onedimensional signal data) and bioimaging (producing two-dimensional image data). Our results show high correlation between the two approaches indicating that image-based screening can be used as an alternative to flow cytometry. Furthermore, we discuss the benefits of image informatics over conventional single-signal flow cytometry.

Place, publisher, year, edition, pages
Springer, 2016
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 9730
Keywords
Quantitative microscopy, DNA content histogram
National Category
Bioinformatics (Computational Biology)
Identifiers
urn:nbn:se:uu:diva-307245 (URN)10.1007/978-3-319-41501-7_70 (DOI)000386604000070 ()
Conference
13th International Conference, ICIAR 2016, in Memory of Mohamed Kamel, Póvoa de Varzim, Portugal, July 13-15, 2016
Available from: 2016-11-11 Created: 2016-11-11 Last updated: 2019-10-09Bibliographically approved
2. PopulationProfiler: A Tool for Population Analysis and Visualization of Image-Based Cell Screening Data
Open this publication in new window or tab >>PopulationProfiler: A Tool for Population Analysis and Visualization of Image-Based Cell Screening Data
2016 (English)In: PLoS ONE, ISSN 1932-6203, E-ISSN 1932-6203, Vol. 11, no 3, article id e0151554Article in journal (Refereed) Published
Abstract [en]

Image-based screening typically produces quantitative measurements of cell appearance. Large-scale screens involving tens of thousands of images, each containing hundreds of cells described by hundreds of measurements, result in overwhelming amounts of data. Reducing per-cell measurements to the averages across the image(s) for each treatment leads to loss of potentially valuable information on population variability. We present PopulationProfiler-a new software tool that reduces per-cell measurements to population statistics. The software imports measurements from a simple text file, visualizes population distributions in a compact and comprehensive way, and can create gates for subpopulation classes based on control samples. We validate the tool by showing how PopulationProfiler can be used to analyze the effect of drugs that disturb the cell cycle, and compare the results to those obtained with flow cytometry.

National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-282026 (URN)10.1371/journal.pone.0151554 (DOI)000372580300085 ()26987120 (PubMedID)
Funder
Science for Life Laboratory - a national resource center for high-throughput molecular bioscienceSwedish Research Council, 2012-4968; 2014-6075
Available from: 2016-03-17 Created: 2016-04-01 Last updated: 2019-10-09Bibliographically approved
3. Image-Based Detection of Patient-Specific Drug-Induced Cell-Cycle Effects in Glioblastoma
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
4. A short feature vector for image matching: The Log-Polar Magnitude feature descriptor
Open this publication in new window or tab >>A short feature vector for image matching: The Log-Polar Magnitude feature descriptor
2017 (English)In: PLoS ONE, ISSN 1932-6203, E-ISSN 1932-6203, Vol. 12, no 11, article id e0188496Article in journal (Refereed) Published
Abstract [en]

The choice of an optimal feature detector-descriptor combination for image matching often depends on the application and the image type. In this paper, we propose the Log-Polar Magnitude feature descriptor—a rotation, scale, and illumination invariant descriptor that achieves comparable performance to SIFT on a large variety of image registration problems but with much shorter feature vectors. The descriptor is based on the Log-Polar Transform followed by a Fourier Transform and selection of the magnitude spectrum components. Selecting different frequency components allows optimizing for image patterns specific for a particular application. In addition, by relying only on coordinates of the found features and (optionally) feature sizes our descriptor is completely detector independent. We propose 48- or 56-long feature vectors that potentially can be shortened even further depending on the application. Shorter feature vectors result in better memory usage and faster matching. This combined with the fact that the descriptor does not require a time-consuming feature orientation estimation (the rotation invariance is achieved solely by using the magnitude spectrum of the Log-Polar Transform) makes it particularly attractive to applications with limited hardware capacity. Evaluation is performed on the standard Oxford dataset and two different microscopy datasets; one with fluorescence and one with transmission electron microscopy images. Our method performs better than SURF and comparable to SIFT on the Oxford dataset, and better than SIFT on both microscopy datasets indicating that it is particularly useful in applications with microscopy images.

National Category
Other Engineering and Technologies
Identifiers
urn:nbn:se:uu:diva-335460 (URN)10.1371/journal.pone.0188496 (DOI)000416841900060 ()
Funder
EU, European Research Council, ERC-CoG-2015Swedish Research Council, 2014-6075
Available from: 2017-12-05 Created: 2017-12-05 Last updated: 2019-10-09Bibliographically approved
5. Minimal annotation training for segmentation of microscopy images
Open this publication in new window or tab >>Minimal annotation training for segmentation of microscopy images
2018 (English)In: Proc. 15th International Symposium on Biomedical Imaging, IEEE, 2018, p. 387-390Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
IEEE, 2018
National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-368701 (URN)10.1109/ISBI.2018.8363599 (DOI)000455045600088 ()978-1-5386-3636-7 (ISBN)
Conference
ISBI 2018, April 4–7, Washington, DC
Available from: 2018-12-06 Created: 2018-12-06 Last updated: 2019-10-09Bibliographically approved
6. Reducing the U-Net size for practical scenarios: Virus recognition in electron microscopy images
Open this publication in new window or tab >>Reducing the U-Net size for practical scenarios: Virus recognition in electron microscopy images
2019 (English)In: Computer Methods and Programs in Biomedicine, ISSN 0169-2607, E-ISSN 1872-7565, Vol. 178, p. 31-39Article in journal (Refereed) Published
Abstract [en]

Background and objective: Convolutional neural networks (CNNs) offer human experts-like performance and in the same time they are faster and more consistent in their prediction. However, most of the proposed CNNs require an expensive state-of-the-art hardware which substantially limits their use in practical scenarios and commercial systems, especially for clinical, biomedical and other applications that require on-the-fly analysis. In this paper, we investigate the possibility of making CNNs lighter by parametrizing the architecture and decreasing the number of trainable weights of a popular CNN: U-Net. Methods: In order to demonstrate that comparable results can be achieved with substantially less trainable weights than the original U-Net we used a challenging application of a pixel-wise virus classification in Transmission Electron Microscopy images with minimal annotations (i.e. consisting only of the virus particle centers or centerlines). We explored 4 U-Net hyper-parameters: the number of base feature maps, the feature maps multiplier, the number of the encoding-decoding levels and the number of feature maps in the last 2 convolutional layers. Results: Our experiments lead to two main conclusions: 1) the architecture hyper-parameters are pivotal if less trainable weights are to be used, and 2) if there is no restriction on the trainable weights number using a deeper network generally gives better results. However, training larger networks takes longer, typically requires more data and such networks are also more prone to overfitting. Our best model achieved an accuracy of 82.2% which is similar to the original U-Net while using nearly 4 times less trainable weights (7.8 M in comparison to 31.0 M). We also present a network with < 2M trainable weights that achieved an accuracy of 76.4%. Conclusions: The proposed U-Net hyper-parameter exploration can be adapted to other CNNs and other applications. It allows a comprehensive CNN architecture designing with the aim of a more efficient trainable weight use. Making the networks faster and lighter is crucial for their implementation in many practical applications. In addition, a lighter network ought to be less prone to over-fitting and hence generalize better. (C) 2019 Published by Elsevier B.V.

Place, publisher, year, edition, pages
ELSEVIER IRELAND LTD, 2019
Keywords
Deep learning, Hyper parameter optimization, Hardware integration, Transmission Electron Microscopy
National Category
Computer Engineering
Identifiers
urn:nbn:se:uu:diva-393644 (URN)10.1016/j.cmpb.2019.05.026 (DOI)000480432000004 ()31416558 (PubMedID)
Funder
Swedish Research Council, 2014-6075
Available from: 2019-09-26 Created: 2019-09-26 Last updated: 2019-10-09Bibliographically approved

Open Access in DiVA

fulltext(1086 kB)31 downloads
File information
File name FULLTEXT01.pdfFile size 1086 kBChecksum SHA-512
39e235f95415b92a6f29a7f27e5e2e8d04d1d119707ec938d04bcda716947ac8dc4d29ad0ec021424a46d675905c866e3ad219aaaec130272ca12394d858543a
Type fulltextMimetype application/pdf
Buy this publication >>

Authority records BETA

Matuszewski, Damian J.

Search in DiVA

By author/editor
Matuszewski, Damian J.
By organisation
Division of Visual Information and InteractionComputerized Image Analysis and Human-Computer Interaction
Medical Image Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 31 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 277 hits
CiteExportLink to record
Permanent link

Direct 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