Skip to Main content Skip to Navigation
Conference papers

Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classification

Abstract : Traditional supervised learning with deep neural networks requires a tremendous amount of labelled data to converge to a good solution. For 3D medical images, it is often impractical to build a large homogeneous annotated dataset for a specific pathology. Self-supervised methods offer a new way to learn a representation of the images in an unsupervised manner with a neural network. In particular, contrastive learning has shown great promises by (almost) matching the performance of fully-supervised CNN on vision tasks. Nonetheless, this method does not take advantage of available meta-data, such as participant's age, viewed as prior knowledge. Here, we propose to leverage continuous proxy metadata, in the contrastive learning framework, by introducing a new loss called y-Aware InfoNCE loss. Specifically, we improve the positive sampling during pre-training by adding more positive examples with similar proxy meta-data with the anchor, assuming they share similar discriminative semantic features.With our method, a 3D CNN model pre-trained on 10 4 multi-site healthy brain MRI scans can extract relevant features for three classification tasks: schizophrenia, bipolar diagnosis and Alzheimer's detection. When fine-tuned, it also outperforms 3D CNN trained from scratch on these tasks, as well as state-of-the-art self-supervised methods. Our code is made publicly available here.
Complete list of metadata
Contributor : Pietro Gori Connect in order to contact the contributor
Submitted on : Wednesday, June 16, 2021 - 1:51:07 PM
Last modification on : Monday, March 21, 2022 - 5:22:04 PM
Long-term archiving on: : Friday, September 17, 2021 - 6:50:56 PM


Files produced by the author(s)


  • HAL Id : hal-03262256, version 1


Benoit Dufumier, Pietro Gori, Julie Victor, Antoine Grigis, Michel Wessa, et al.. Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classification. MICCAI, Sep 2021, Strasbourg (virtuel), France. ⟨hal-03262256⟩



Record views


Files downloads