Generalized Multiple Instance Learning for Cancer Detection in Digital Histopathology

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00341724" target="_blank" >RIV/68407700:21230/20:00341724 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-50516-5_24" target="_blank" >https://doi.org/10.1007/978-3-030-50516-5_24</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-50516-5_24" target="_blank" >10.1007/978-3-030-50516-5_24</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Generalized Multiple Instance Learning for Cancer Detection in Digital Histopathology

Popis výsledku v původním jazyce

We address the task of detecting cancer in histological slide images based on training with weak, slide- and patch-level annotations, which are considerably easier to obtain than pixel-level annotations. we use CNN based patch-level descriptors and formulate the image classification task as a generalized multiple instance learning (MIL) problem. The generalization consists of requiring a certain number of positive instances in positive bags, instead of just one as in standard MIL. The descriptors are learned on a small number of patch-level annotations, while the MIL layer uses only image-level patches for training. We evaluate multiple generalized MIL methods on the H&E stained images of lymphatic nodes from the CAMELYON dataset and show that generalized MIL methods improve the classification results and outperform no-MIL methods in terms of slide-level AUC. Best classification results were achieved by the MI-SVM(k) classifier in combination with simple spatial Gaussian aggregation, achieving AUC 0.962. However, MIL did not outperform methods trained on pixel-level segmentations.

Název v anglickém jazyce

Generalized Multiple Instance Learning for Cancer Detection in Digital Histopathology

Popis výsledku anglicky

We address the task of detecting cancer in histological slide images based on training with weak, slide- and patch-level annotations, which are considerably easier to obtain than pixel-level annotations. we use CNN based patch-level descriptors and formulate the image classification task as a generalized multiple instance learning (MIL) problem. The generalization consists of requiring a certain number of positive instances in positive bags, instead of just one as in standard MIL. The descriptors are learned on a small number of patch-level annotations, while the MIL layer uses only image-level patches for training. We evaluate multiple generalized MIL methods on the H&E stained images of lymphatic nodes from the CAMELYON dataset and show that generalized MIL methods improve the classification results and outperform no-MIL methods in terms of slide-level AUC. Best classification results were achieved by the MI-SVM(k) classifier in combination with simple spatial Gaussian aggregation, achieving AUC 0.962. However, MIL did not outperform methods trained on pixel-level segmentations.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Image Analysis and Recognition,17th International Conference, ICIAR 2020, Póvoa de Varzim, Portugal, June 24–26, 2020, Proceedings, Part II

ISBN

978-3-030-50515-8

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

9

Strana od-do

274-282

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Póvoa de Varzim

Datum konání akce

24. 6. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—