Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • 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
Development of Algorithms for Digital Image Cytometry
Uppsala University, Interfaculty Units, Centre for Image Analysis.
2002 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

This thesis presents work in digital image cytometry applied to fluorescence microscope images of cultivated cells. Focus has been on the development and compilation of robust image analysis tools, enabling quantitative measurements of various properties of cells and cell structures. A significant part of the work has consisted of developing robust segmentation methods for fluorescently labelled cells. This, in combination with effort applied in the areas of feature extraction and statistical data analysis, has enabled the compilation of a complete chain of processing steps to produce a system capable of performing fully automatic segmentation and classification of fluorescently labelled cells according to their level of activation.

Two sequences of processing steps, both leading to automatic cytoplasm segmentation of fluorescence microscopy cell images are presented. In one of the sequences, an additional image of the nuclei of the cells is segmented. The nuclei are then used as seeds for the segmentation of the cytoplasm image. This solves the problem of over-segmentation of the cytoplasms in an efficient way. The other sequence uses merge and split algorithms on the cytoplasm image, in conjunction with statistical analysis of descriptive features. This analysis is used in a feedback system to improve the segmentation performance, and to give an overall quality measure of the segmentation.

A classification method that separates individual cells into three classes, depending on their level of activation, is described. The method is based on analysis of time series of images. Using both general purpose features and carefully designed problem specific features, in combination with a floating feature selection procedure, a Bayesian classifier is built. Evaluation showed that the performance of the fully automatic classification procedure was very close to the performance of skilled manual classification.

A novel method for performing estimation of intensity nonuniformites of microscope images is presented. Methods to solve many other problems related to image analysis of cell images are discussed and evaluated. All methods presented in this work are applicable to real-world situations. The two main projects of the thesis work have been performed in close cooperation with and according to demands of the biomedical industry.

Place, publisher, year, edition, pages
Uppsala: Acta Universitatis Upsaliensis , 2002. , p. 67
Series
Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology, ISSN 1104-232X ; 789
Keywords [en]
Bildanalys
Keywords [sv]
Bildanalys
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Analysis
Identifiers
URN: urn:nbn:se:uu:diva-3239ISBN: 91-554-5497-6 (print)OAI: oai:DiVA.org:uu-3239DiVA, id: diva2:162268
Public defence
2003-01-17, Häggsalen (room 10132), Ångströmlaboratoriet, Uppsala, 10:15
Opponent
Available from: 2002-12-19 Created: 2002-12-19 Last updated: 2018-01-13Bibliographically approved
List of papers
1. Image Analysis for Automatic Segmentation of Cytoplasms and Classification of Rac1 Activation
Open this publication in new window or tab >>Image Analysis for Automatic Segmentation of Cytoplasms and Classification of Rac1 Activation
2004 (English)In: Cytometry, ISSN 0196-4763, E-ISSN 1097-0320, Vol. 57A, no 1, p. 22-23Article in journal (Refereed) Published
Abstract [en]

BACKGROUND:

Rac1 is a GTP-binding molecule involved in a wide range of cellular processes. Using digital image analysis, agonist-induced translocation of green fluorescent protein (GFP) Rac1 to the cellular membrane can be estimated quantitatively for individual cells.

METHODS:

A fully automatic image analysis method for cell segmentation, feature extraction, and classification of cells according to their activation, i.e., GFP-Rac1 translocation and ruffle formation at stimuli, is described. Based on training data produced by visual annotation of four image series, a statistical classifier was created.

RESULTS:

The results of the automatic classification were compared with results from visual inspection of the same time sequences. The automatic classification differed from the visual classification at about the same level as visual classifications performed by two different skilled professionals differed from each other. Classification of a second image set, consisting of seven image series with different concentrations of agonist, showed that the classifier could detect an increased proportion of activated cells at increased agonist concentration.

CONCLUSIONS:

Intracellular activities, such as ruffle formation, can be quantified by fully automatic image analysis, with an accuracy comparable to that achieved by visual inspection. This analysis can be done at a speed of hundreds of cells per second and without the subjectivity introduced by manual judgments.

National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:uu:diva-90085 (URN)10.1002/cyto.a.10107 (DOI)14699602 (PubMedID)
Available from: 2002-12-19 Created: 2002-12-19 Last updated: 2018-01-13Bibliographically approved
2. Algorithms for cytoplasm segmentation of fluorescence labeled cells
Open this publication in new window or tab >>Algorithms for cytoplasm segmentation of fluorescence labeled cells
Show others...
2002 (English)In: Analytical Cellular Pathology, ISSN 0921-8912, E-ISSN 1878-3651, Vol. 24, no 2-3, p. 101-111Article in journal (Refereed) Published
Abstract [en]

Automatic cell segmentation has various applications in cytometry, and while the nucleus is often very distinct and easy to identify, the cytoplasm provides a lot more challenge. A new combination of image analysis algorithms for segmentation of cells imaged by fluorescence microscopy is presented. The algorithm consists of an image pre-processing step, a general segmentation and merging step followed by a segmentation quality measurement. The quality measurement consists of a statistical analysis of a number of shape descriptive features. Objects that have features that differ to that of correctly segmented single cells can be further processed by a splitting step. By statistical analysis we therefore get a feedback system for separation of clustered cells. After the segmentation is completed, the quality of the final segmentation is evaluated. By training the algorithm on a representative set of training images, the algorithm is made fully automatic for subsequent images created under similar conditions. Automatic cytoplasm segmentation was tested on CHO-cells stained with calcein. The fully automatic method showed between 89% and 97% correct segmentation as compared to manual segmentation.

National Category
Biological Sciences
Identifiers
urn:nbn:se:uu:diva-90086 (URN)12446959 (PubMedID)
Available from: 2002-12-19 Created: 2002-12-19 Last updated: 2017-12-14Bibliographically approved
3. Statistical quality control for segmentation of fluorescence labeled cells
Open this publication in new window or tab >>Statistical quality control for segmentation of fluorescence labeled cells
Show others...
2001 (English)In: In Proceedings of the 5th Korea-Germany Joint Workshop on Advanced Medical Image Processing, Seoul, KoreaArticle in journal (Refereed) Published
Identifiers
urn:nbn:se:uu:diva-90087 (URN)
Available from: 2002-12-19 Created: 2002-12-19 Last updated: 2010-03-01Bibliographically approved
4. A comparison of methods for estimation of intensity nonuniformities in 2D and 3D microscope images of fluorescence stained cells
Open this publication in new window or tab >>A comparison of methods for estimation of intensity nonuniformities in 2D and 3D microscope images of fluorescence stained cells
2001 (English)In: In Proceedings of the 12th Scandinavian Conference on Image Analysis (SCIA), Bergen, Norway, p. 264-271Article in journal (Refereed) Published
Identifiers
urn:nbn:se:uu:diva-90088 (URN)
Available from: 2002-12-19 Created: 2002-12-19 Last updated: 2010-03-01Bibliographically approved
5. Histogram thresholding using kernel density estimates
Open this publication in new window or tab >>Histogram thresholding using kernel density estimates
2000 (English)In: In Proceedings of the Swedish Society for Automated Image Analysis (SSAB) Symposium on Image Analysis, Halmstad, Sweden, p. 41-44Article in journal (Refereed) Published
Identifiers
urn:nbn:se:uu:diva-90089 (URN)
Available from: 2002-12-19 Created: 2002-12-19 Last updated: 2010-03-01Bibliographically approved

Open Access in DiVA

fulltext(917 kB)4483 downloads
File information
File name FULLTEXT01.pdfFile size 917 kBChecksum MD5
6622f9a1b3a4790caf59470b4cabcd3d705ed4a13fb68d22bea0d8edf3abc788e9cca0ab
Type fulltextMimetype application/pdf
Buy this publication >>

By organisation
Centre for Image Analysis
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 4483 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: 1523 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • 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