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 Analysis Methods and Tools for Digital Histopathology Applications Relevant to Breast Cancer Diagnosis
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.
2014 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

In 2012, more than 1.6 million new cases of breast cancer were diagnosed and about half a million women died of breast cancer. The incidence has increased in the developing world. The mortality, however, has decreased. This is thought to partly be the result of advances in diagnosis and treatment. Studying tissue samples from biopsies through a microscope is an important part of diagnosing breast cancer. Recent techniques include camera-equipped microscopes and whole slide scanning systems that allow for digital high-throughput scanning of tissue samples. The introduction of digital pathology has simplified parts of the analysis, but manual interpretation of tissue slides is still labor intensive and costly, and involves the risk for human errors and inconsistency. Digital image analysis has been proposed as an alternative approach that can assist the pathologist in making an accurate diagnosis by providing additional automatic, fast and reproducible analyses. This thesis addresses the automation of conventional analyses of tissue, stained for biomarkers specific for the diagnosis of breast cancer, with the purpose of complementing the role of the pathologist. In order to quantify biomarker expression, extraction and classification of sub-cellular structures are needed. This thesis presents a method that allows for robust and fast segmentation of cell nuclei meeting the need for methods that are accurate despite large biological variations and variations in staining. The method is inspired by sparse coding and is based on dictionaries of local image patches. It is implemented in a tool for quantifying biomarker expression of various sub-cellular structures in whole slide images. Also presented are two methods for classifying the sub-cellular localization of staining patterns, in an attempt to automate the validation of antibody specificity, an important task within the process of antibody generation.  In addition, this thesis explores methods for evaluation of multimodal data. Algorithms for registering consecutive tissue sections stained for different biomarkers are evaluated, both in terms of registration accuracy and deformation of local structures. A novel region-growing segmentation method for multimodal data is also presented. In conclusion, this thesis presents computerized image analysis methods and tools of potential value for digital pathology applications.

Place, publisher, year, edition, pages
Uppsala: Acta Universitatis Upsaliensis, 2014. , 129 p.
Series
Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology, ISSN 1651-6214 ; 1128
Keyword [en]
image analysis, breast cancer diagnosis, digital histopathology, immunohistochemistry, biomarker quantification
National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
URN: urn:nbn:se:uu:diva-219306ISBN: 978-91-554-8889-5 (print)OAI: oai:DiVA.org:uu-219306DiVA: diva2:699154
Public defence
2014-04-11, Room 2446, Polacksbacken, Lägerhyddsvägen 2, Uppsala, 10:15 (English)
Opponent
Supervisors
Available from: 2014-03-20 Created: 2014-02-26 Last updated: 2014-07-21
List of papers
1. Learning histopathological patterns
Open this publication in new window or tab >>Learning histopathological patterns
2012 (English)In: Journal of Pathology Informatics, ISSN 2229-5089, E-ISSN 2153-3539, Vol. 2, 12- p.Article in journal (Refereed) Published
Abstract [en]

Aims: The aim was to demonstrate a method for automated image analysis of immunohistochemically stained tissue samples for extracting features that correlate with patient disease. We address the problem of quantifying tumor tissue and segmenting and counting cell nuclei. Materials and Methods: Our method utilizes a flexible segmentation method based on sparse coding trained from representative image samples. Nuclei counting is based on a nucleus model that takes size, shape, and nucleus probability into account. Nuclei clustering and overlays are resolved using a gray-weighted distance transform. We obtain a probability measure for pixels belonging to a nucleus from our segmentation procedure. Experiments are carried out on two sets of immunohistochemically stained images - one set based on the estrogen receptor (ER) and the other on antigen KI-67. For the nuclei separation we have selected 207 ER image samples from 58 tissue micro array-cores corresponding to 58 patients and 136 KI-67 image samples also from 58 cores. The images are hand-annotated by marking the center position of each nucleus. For the ER data we have a total of 1006 nuclei and for the KI-67 we have 796 nuclei. Segmentation performance was evaluated in terms of missing nuclei, falsely detected nuclei, and multiple detections. The proposed method is compared to state-of-the-art Bayesian classification. Statistical analysis used: The performance of the proposed method and a state-of-the-art algorithm including variations thereof is compared using the Wilcoxon rank sum test. Results: For both the ER experiment and the KI-67 experiment the proposed method exhibits lower error rates than the state-of-the-art method. Total error rates were 4.8 % and 7.7 % in the two experiments, corresponding to an average of 0.23 and 0.45 errors per image, respectively. The Wilcoxon rank sum tests show statistically significant improvements over the state-of-the-art method. Conclusions: We have demonstrated a method and obtained good performance compared to state-of-the-art nuclei separation. The segmentation procedure is simple, highly flexible, and we demonstrate how it, in addition to the nuclei separation, can perform precise segmentation of cancerous tissue. The complexity of the segmentation procedure is linear in the image size and the nuclei separation is linear in the number of nuclei. Additionally the method can be parallelized to obtain high-speed computations.

Keyword
Computer-aided classification, digital histopathology, flexible learning-based segmentation, image segmentation
National Category
Medical Image Processing
Research subject
Computerized Image Analysis; Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-167255 (URN)10.4103/2153-3539.92033 (DOI)
Available from: 2012-01-19 Created: 2012-01-24 Last updated: 2014-05-24Bibliographically approved
2. The Vectorial Minimum Barrier Distance
Open this publication in new window or tab >>The Vectorial Minimum Barrier Distance
2012 (English)In: International Conference on Pattern Recognition, ISSN 1051-4651, 792-795 p.Article in journal, Meeting abstract (Refereed) Published
Abstract [en]

We introduce the vectorial Minimum Barrier Distance (MBD), a method for computing a gray-weighted distance transform while also incorporating information from vectorial data. Compared to other similar tools that use vectorial data, the proposed method requires no training and does not assume having only one background class. We describe a region growing algorithm for computing the vectorial MBD efficiently.

The method is evaluated on two types of multi-channel images: color images and textural features. Different path-cost functions for calculating the multi-dimensional path-cost distance are also compared.

The results show that by combining multi-channel images into vectorial information the performance ofthe vectorial MBD segmentation is improved compared to when one channel is used. This implies that the method can be a good way of incorporating multi-channel information in interactive segmentation.

National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-190013 (URN)978-1-4673-2216-4 (ISBN)
Conference
International Conference on Pattern Recognition, 2012
Available from: 2013-01-07 Created: 2013-01-07 Last updated: 2014-04-29Bibliographically approved
3. Automated classification of immunostaining patterns in breast tissue from the Human Protein Atlas
Open this publication in new window or tab >>Automated classification of immunostaining patterns in breast tissue from the Human Protein Atlas
Show others...
2013 (English)In: Journal of Pathology Informatics, ISSN 2229-5089, E-ISSN 2153-3539, Vol. 4, no 14Article in journal (Refereed) Published
Abstract [en]

Background:

The Human Protein Atlas (HPA) is an effort to map the location of all human proteins (http://www.proteinatlas.org/). It contains a large number of histological images of sections from human tissue. Tissue micro arrays (TMA) are imaged by a slide scanning microscope, and each image represents a thin slice of a tissue core with a dark brown antibody specific stain and a blue counter stain. When generating antibodies for protein profiling of the human proteome, an important step in the quality control is to compare staining patterns of different antibodies directed towards the same protein. This comparison is an ultimate control that the antibody recognizes the right protein. In this paper, we propose and evaluate different approaches for classifying sub-cellular antibody staining patterns in breast tissue samples.

Materials and Methods:

The proposed methods include the computation of various features including gray level co-occurrence matrix (GLCM) features, complex wavelet co-occurrence matrix (CWCM) features, and weighted neighbor distance using compound hierarchy of algorithms representing morphology (WND-CHARM)-inspired features. The extracted features are used into two different multivariate classifiers (support vector machine (SVM) and linear discriminant analysis (LDA) classifier). Before extracting features, we use color deconvolution to separate different tissue components, such as the brownly stained positive regions and the blue cellular regions, in the immuno-stained TMA images of breast tissue.

Results:

We present classification results based on combinations of feature measurements. The proposed complex wavelet features and the WND-CHARM features have accuracy similar to that of a human expert.

Conclusions:

Both human experts and the proposed automated methods have difficulties discriminating between nuclear and cytoplasmic staining patterns. This is to a large extent due to mixed staining of nucleus and cytoplasm. Methods for quantification of staining patterns in histopathology have many applications, ranging from antibody quality control to tumor grading.

National Category
Medical Image Processing
Research subject
Behavioural Neuroscience; Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-212564 (URN)10.4103/2153-3539.109881 (DOI)
Available from: 2013-12-11 Created: 2013-12-11 Last updated: 2015-03-25Bibliographically approved
4. A histopathological tool for quantification of biomarkers with sub-cellular resolution
Open this publication in new window or tab >>A histopathological tool for quantification of biomarkers with sub-cellular resolution
Show others...
2015 (English)In: Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, ISSN 2168-1163, Vol. 3, no 1, 25-46 p.Article in journal (Refereed) Published
National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-219287 (URN)10.1080/21681163.2014.885120 (DOI)
Available from: 2014-02-27 Created: 2014-02-26 Last updated: 2015-03-12Bibliographically approved
5. Multimodal histological image registration using locally rigid transforms
Open this publication in new window or tab >>Multimodal histological image registration using locally rigid transforms
2014 (English)In: IEEE Transactions on Biomedical Engineering, ISSN 0018-9294, E-ISSN 1558-2531Article in journal (Other academic) Submitted
Abstract [en]

Evaluating multimodal histological images is animportant task within cancer diagnosis and research. Newmethods are currently under development, such as multiplexingand destaining/restaining protocols, but comparing data fromconsecutive monomodal sections is still the most common methodfor acquiring multimodal data. To allow for comparison of con-secutive sections, registration of the sections is needed. Becauseof the spatial distance between the sections as well as non-uniform deformations, due to mechanical and chemical stressduring handling and staining, this is not a trivial task. Inthis paper, we confirm that deformable transforms outperformlinear transforms when it comes to registration quality. However,large deformations can result in a poor viewing experience forthe pathologist when evaluating the slides, as local structuresare distorted and may look unnatural. The deformations alsoaffect measurements made on the deformed image. We presenta method for locally approximating the global deformabletransform with a rigid transform, and we introduce a gradeof rigidity term that enables a trade-off between registrationquality and measurement distortion. We use a strategy of dividingthe registration in an offline and online step, which gives usthe possibility to perform the approximation in real-time. Thisability offers the viewer with the possibility to quickly switchbetween a view that has optimal registration and a view wheremeasurements are not distorted and where structures ”lookright”. To facilitate further research within the subject, wepresent a registration tool that provides an intuitive interfacefor making comparisons between global deformable transformsand locally rigid approximations with varying degree of rigidity.

Keyword
Multimodal registration, digital histopathology, locally rigid transforms
National Category
Other Computer and Information Science
Research subject
Computerized Image Analysis; Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-219290 (URN)
Available from: 2014-02-26 Created: 2014-02-26 Last updated: 2014-04-29Bibliographically approved

Open Access in DiVA

fulltext(4041 kB)3770 downloads
File information
File name FULLTEXT01.pdfFile size 4041 kBChecksum SHA-512
9ccbf7f2db4dd0031ef65cc67ad4fe75a65c16dc15eb12ecf3219a0a7e40733438da541b17bb901445a21861cf6e0a5513da47bd3993ded9ada4f9ec7d8cfbe7
Type fulltextMimetype application/pdf
Buy this publication >>

Search in DiVA

By author/editor
Kårsnäs, Andreas
By organisation
Division of Visual Information and InteractionComputerized Image Analysis and Human-Computer Interaction
Medical Image Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 3770 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

Total: 1152 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