POPOVICI, Vlad, Eva BUDINSKÁ, Ladislav DUŠEK, Michal KOZUBEK a Fred BOSMAN. Image-based surrogate biomarkers for molecular subtypes of colorectal cancer. Bioinformatics, Oxford: Oxford University Press, 2017, roč. 33, č. 13, s. 2002-2009. ISSN 1367-4803. doi:10.1093/bioinformatics/btx027.
Další formáty:   BibTeX LaTeX RIS
Základní údaje
Originální název Image-based surrogate biomarkers for molecular subtypes of colorectal cancer
Autoři POPOVICI, Vlad (642 Rumunsko, garant, domácí), Eva BUDINSKÁ (703 Slovensko, domácí), Ladislav DUŠEK (203 Česká republika, domácí), Michal KOZUBEK (203 Česká republika, domácí) a Fred BOSMAN (528 Nizozemsko).
Vydání Bioinformatics, Oxford, Oxford University Press, 2017, 1367-4803.
Další údaje
Originální jazyk angličtina
Typ výsledku Článek v odborném periodiku
Obor 10201 Computer sciences, information science, bioinformatics
Stát vydavatele Spojené království
Utajení není předmětem státního či obchodního tajemství
Impakt faktor Impact factor: 5.481
Kód RIV RIV/00216224:14310/17:00097868
Organizační jednotka Přírodovědecká fakulta
Doi http://dx.doi.org/10.1093/bioinformatics/btx027
UT WoS 000404054700013
Klíčová slova anglicky digital pathology; bioinformatics; molecular subtypes
Štítky cbia-web, NZ, rivok
Příznaky Mezinárodní význam, Recenzováno
Změnil Změnila: Ing. Nicole Zrilić, učo 240776. Změněno: 5. 4. 2018 11:32.
Anotace
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.
Návaznosti
4SGA8736, interní kód MUNázev: Computational framework for joint analysis of histopathology images and gene expression data (Akronym: HIGEX)
Investor: Jihomoravský kraj, SoMoPro, Granty pro zahraniční vědce
VytisknoutZobrazeno: 20. 1. 2020 21:29