HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
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

https://hal.telecom-paris.fr/hal-03262256
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

File

Age_Aware_Contrastive_Learning...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03262256, version 1

Citation

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⟩

Share

Metrics

Record views

147

Files downloads

301