Image-based surrogate biomarkers for molecular subtypes of
colorectal cancer

POPOVICI, Vlad, Eva BUDINSKÁ, Ladislav DUŠEK, Michal KOZUBEK and Fred BOSMAN. Image-based surrogate biomarkers for molecular subtypes of colorectal cancer. Online. Bioinformatics. Oxford: Oxford University Press, 2017, vol. 33, No 13, p. 2002-2009. ISSN 1367-4803. Available from: https://dx.doi.org/10.1093/bioinformatics/btx027. [citováno 2024-04-23]

Other formats: BibTeX LaTeX RIS

TY  - JOUR
ID  - 1392199
AU  - Popovici, Vlad - Budinská, Eva - Dušek, Ladislav - Kozubek, Michal - Bosman, Fred
PY  - 2017
TI  - Image-based surrogate biomarkers for molecular subtypes of colorectal cancer
JF  - Bioinformatics
VL  - 33
IS  - 13
SP  - 2002-2009
EP  - 2002-2009
PB  - Oxford University Press
SN  - 13674803
KW  - digital pathology
KW  - bioinformatics
KW  - molecular subtypes
N2  - Motivation: Whole genome expression profiling of large cohorts of different types of cancer led to the identification of distinct molecular subcategories (subtypes) that may partially explain the observed inter-tumoral heterogeneity. This is also the case of colorectal cancer (CRC) where several such categorizations have been proposed. Despite recent developments, the problem of subtype definition and recognition remains open, one of the causes being the intrinsic heterogeneity of each tumor, which is difficult to estimate from gene expression profiles. However, one of the observations of these studies indicates that there may be links between the dominant tumor morphology characteristics and the molecular subtypes. Benefiting from a large collection of CRC samples, comprising both gene expression and histopathology images, we investigated the possibility of building image-based classifiers able to predict the molecular subtypes. We employed deep convolutional neural networks for extracting local descriptors which were then used for constructing a dictionary-based representation of each tumor sample. A set of support vector machine classifiers were trained to solve different binary decision problems, their combined outputs being used to predict one of the five molecular subtypes. Results: A hierarchical decomposition of the multi-class problem was obtained with an overall accuracy of 0.84 (95% CI = 0.79-0.88). The predictions from the image-based classifier showed significant prognostic value similar to their molecular counterparts.
ER  -

Basic information
Original name	Image-based surrogate biomarkers for molecular subtypes of colorectal cancer
Authors	POPOVICI, Vlad (642 Romania, guarantor, belonging to the institution), Eva BUDINSKÁ (703 Slovakia, belonging to the institution), Ladislav DUŠEK (203 Czech Republic, belonging to the institution), Michal KOZUBEK (203 Czech Republic, belonging to the institution) and Fred BOSMAN (528 Netherlands)
Edition	Bioinformatics, Oxford, Oxford University Press, 2017, 1367-4803.

Other information
Original language	English
Type of outcome	Article in a journal
Field of Study	10201 Computer sciences, information science, bioinformatics
Country of publisher	United Kingdom of Great Britain and Northern Ireland
Confidentiality degree	is not subject to a state or trade secret
Impact factor	Impact factor: 5.481
RIV identification code	RIV/00216224:14310/17:00097868
Organization unit	Faculty of Science
Doi	http://dx.doi.org/10.1093/bioinformatics/btx027
UT WoS	000404054700013
Keywords in English	digital pathology; bioinformatics; molecular subtypes
Tags	cbia-web, NZ, rivok
Tags	International impact, Reviewed
Changed by	Changed by: Ing. Nicole Zrilić, učo 240776. Changed: 5/4/2018 11:32.

Abstract

Motivation: Whole genome expression profiling of large cohorts of different types of cancer led to the identification of distinct molecular subcategories (subtypes) that may partially explain the observed inter-tumoral heterogeneity. This is also the case of colorectal cancer (CRC) where several such categorizations have been proposed. Despite recent developments, the problem of subtype definition and recognition remains open, one of the causes being the intrinsic heterogeneity of each tumor, which is difficult to estimate from gene expression profiles. However, one of the observations of these studies indicates that there may be links between the dominant tumor morphology characteristics and the molecular subtypes. Benefiting from a large collection of CRC samples, comprising both gene expression and histopathology images, we investigated the possibility of building image-based classifiers able to predict the molecular subtypes. We employed deep convolutional neural networks for extracting local descriptors which were then used for constructing a dictionary-based representation of each tumor sample. A set of support vector machine classifiers were trained to solve different binary decision problems, their combined outputs being used to predict one of the five molecular subtypes. Results: A hierarchical decomposition of the multi-class problem was obtained with an overall accuracy of 0.84 (95% CI = 0.79-0.88). The predictions from the image-based classifier showed significant prognostic value similar to their molecular counterparts.

Links
4SGA8736, interní kód MU	Name: Computational framework for joint analysis of histopathology images and gene expression data (Acronym: HIGEX)
4SGA8736, interní kód MU	Investor: South-Moravian Region, Incoming grants

PrintDisplayed: 23/4/2024 14:03

Image-based surrogate biomarkers for molecular subtypes of colorectal cancer

Other applications