Self-supervised learning improves dMMR/MSI detection from histology slides across multiple cancers

Charlie Saillard, Olivier Dehaene, Tanguy Marchand, Olivier Moindrot, Aurélie Kamoun, Benoit Schmauch, Simon Jegou
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 156:191-205, 2021.

Abstract

Microsatellite instability (MSI) is a tumor phenotype whose diagnosis largely impacts patient care in colorectal cancers (CRC), and is associated with response to immunotherapy in all solid tumors. Deep learning models detecting MSI tumors directly from H&E stained slides have shown promise in improving diagnosis of MSI patients. Prior deep learning models for MSI detection have relied on neural networks pretrained on ImageNet dataset, which does not contain any medical image. In this study, we leverage recent advances in self-supervised learning by training neural networks on histology images from the TCGA dataset using MoCo V2. We show that these networks consistently outperform their counterparts pretrained using ImageNet and obtain state-of-the-art results for MSI detection with AUCs of 0.92 and 0.83 for CRC and gastric tumors, respectively. These models generalize well on an external CRC cohort (0.97 AUC on PAIP) and improve transfer from one organ to another. Finally we show that predictive image regions exhibit meaningful histological patterns, and that the use of MoCo features highlighted more relevant patterns according to an expert pathologist.

Cite this Paper

BibTeX
@InProceedings{pmlr-v156-saillard21a, title = {Self-supervised learning improves dMMR/MSI detection from histology slides across multiple cancers}, author = {Saillard, Charlie and Dehaene, Olivier and Marchand, Tanguy and Moindrot, Olivier and Kamoun, Aur\'elie and Schmauch, Benoit and Jegou, Simon}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {191--205}, year = {2021}, editor = {Atzori, Manfredo and Burlutskiy, Nikolay and Ciompi, Francesco and Li, Zhang and Minhas, Fayyaz and Müller, Henning and Peng, Tingying and Rajpoot, Nasir and Torben-Nielsen, Ben and van der Laak, Jeroen and Veta, Mitko and Yuan, Yinyin and Zlobec, Inti}, volume = {156}, series = {Proceedings of Machine Learning Research}, month = {27 Sep}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v156/saillard21a/saillard21a.pdf}, url = {https://proceedings.mlr.press/v156/saillard21a.html}, abstract = {Microsatellite instability (MSI) is a tumor phenotype whose diagnosis largely impacts patient care in colorectal cancers (CRC), and is associated with response to immunotherapy in all solid tumors. Deep learning models detecting MSI tumors directly from H&E stained slides have shown promise in improving diagnosis of MSI patients. Prior deep learning models for MSI detection have relied on neural networks pretrained on ImageNet dataset, which does not contain any medical image. In this study, we leverage recent advances in self-supervised learning by training neural networks on histology images from the TCGA dataset using MoCo V2. We show that these networks consistently outperform their counterparts pretrained using ImageNet and obtain state-of-the-art results for MSI detection with AUCs of 0.92 and 0.83 for CRC and gastric tumors, respectively. These models generalize well on an external CRC cohort (0.97 AUC on PAIP) and improve transfer from one organ to another. Finally we show that predictive image regions exhibit meaningful histological patterns, and that the use of MoCo features highlighted more relevant patterns according to an expert pathologist.} }
Endnote
%0 Conference Paper %T Self-supervised learning improves dMMR/MSI detection from histology slides across multiple cancers %A Charlie Saillard %A Olivier Dehaene %A Tanguy Marchand %A Olivier Moindrot %A Aurélie Kamoun %A Benoit Schmauch %A Simon Jegou %B Proceedings of the MICCAI Workshop on Computational Pathology %C Proceedings of Machine Learning Research %D 2021 %E Manfredo Atzori %E Nikolay Burlutskiy %E Francesco Ciompi %E Zhang Li %E Fayyaz Minhas %E Henning Müller %E Tingying Peng %E Nasir Rajpoot %E Ben Torben-Nielsen %E Jeroen van der Laak %E Mitko Veta %E Yinyin Yuan %E Inti Zlobec %F pmlr-v156-saillard21a %I PMLR %P 191--205 %U https://proceedings.mlr.press/v156/saillard21a.html %V 156 %X Microsatellite instability (MSI) is a tumor phenotype whose diagnosis largely impacts patient care in colorectal cancers (CRC), and is associated with response to immunotherapy in all solid tumors. Deep learning models detecting MSI tumors directly from H&E stained slides have shown promise in improving diagnosis of MSI patients. Prior deep learning models for MSI detection have relied on neural networks pretrained on ImageNet dataset, which does not contain any medical image. In this study, we leverage recent advances in self-supervised learning by training neural networks on histology images from the TCGA dataset using MoCo V2. We show that these networks consistently outperform their counterparts pretrained using ImageNet and obtain state-of-the-art results for MSI detection with AUCs of 0.92 and 0.83 for CRC and gastric tumors, respectively. These models generalize well on an external CRC cohort (0.97 AUC on PAIP) and improve transfer from one organ to another. Finally we show that predictive image regions exhibit meaningful histological patterns, and that the use of MoCo features highlighted more relevant patterns according to an expert pathologist.
APA
Saillard, C., Dehaene, O., Marchand, T., Moindrot, O., Kamoun, A., Schmauch, B. & Jegou, S.. (2021). Self-supervised learning improves dMMR/MSI detection from histology slides across multiple cancers. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 156:191-205 Available from https://proceedings.mlr.press/v156/saillard21a.html.

Related Material