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

no code implementations • MICCAI Workshop COMPAY 2021 • Charlie Saillard, Olivier Dehaene, Tanguy Marchand, Olivier Moindrot, Aurélie Kamoun, Benoit Schmauch, Simon Jegou

Prior deep learning models for MSI detection have relied on neural networks pretrained on ImageNet dataset, which does not contain any medical image.

Self-Supervised Learning

Using StyleGAN for Visual Interpretability of Deep Learning Models on Medical Images

no code implementations • 19 Jan 2021 • Kathryn Schutte, Olivier Moindrot, Paul Hérent, Jean-Baptiste Schiratti, Simon Jégou

We validate our approach on histology and radiology images, and demonstrate its ability to provide meaningful explanations that are more informative than GradCAM heatmaps.

Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology

no code implementations • 7 Dec 2020 • Olivier Dehaene, Axel Camara, Olivier Moindrot, Axel de Lavergne, Pierre Courtiol

We identify this as a key weakness and propose to train an in-domain feature extractor on histology images using MoCo v2, a recent self-supervised learning algorithm.

BIG-bench Machine Learning Self-Supervised Learning +1