Contrastive learning for regression in multi-site brain age prediction
This addresses the challenge of building accurate and generalizable brain age prediction models for neuroimaging, which could aid in understanding neurodegenerative disorders and finding biomarkers, though it is incremental in applying contrastive learning to regression.
The paper tackled the problem of site-related noise degrading generalization in multi-site brain age prediction from MRI scans by proposing a novel contrastive learning regression loss, achieving state-of-the-art performance on the OpenBHB challenge with improved generalization and robustness.
Building accurate Deep Learning (DL) models for brain age prediction is a very relevant topic in neuroimaging, as it could help better understand neurodegenerative disorders and find new biomarkers. To estimate accurate and generalizable models, large datasets have been collected, which are often multi-site and multi-scanner. This large heterogeneity negatively affects the generalization performance of DL models since they are prone to overfit site-related noise. Recently, contrastive learning approaches have been shown to be more robust against noise in data or labels. For this reason, we propose a novel contrastive learning regression loss for robust brain age prediction using MRI scans. Our method achieves state-of-the-art performance on the OpenBHB challenge, yielding the best generalization capability and robustness to site-related noise.