Adaptive neighborhoods in contrastive regression learning for brain age prediction

Träuble, Jakob, Hiscox, Lucy V. ORCID: https://orcid.org/0000-0001-6296-7442, Johnson, Curtis L., Schönlieb, Carola-Bibiane, Kaminski Schierle, Gabriele S. and Aviles-Rivero, Angelica I. 2024. Adaptive neighborhoods in contrastive regression learning for brain age prediction. Presented at: NeurIPS 2024 Workshop: Self-Supervised Learning - Theory and Practice, Vancouver, Canada, 09 - 15 December 2024.

Preview

PDF - Presentation Download (850kB) | Preview

Abstract

In neuroimaging, accurate brain age prediction is key to understanding brain aging and early neurodegenerative signs. Recent advancements in self-supervised learning, particularly contrastive learning, have shown robustness with complex datasets but struggle with non-uniformly distributed data common in medical imaging. We introduce a novel contrastive loss that dynamically adapts during training, focusing on localized sample neighborhoods. Additionally, we incorporate brain stiffness, a mechanical property sensitive to aging. Our approach outperforms state-of-the-art methods and opens new directions for brain aging research.

Item Type:	Conference or Workshop Item (Paper)
Status:	Unpublished
Schools:	Psychology Cardiff University Brain Research Imaging Centre (CUBRIC)
Date of First Compliant Deposit:	28 October 2024
Last Modified:	19 Nov 2024 12:16
URI:	https://orca.cardiff.ac.uk/id/eprint/173426

Actions (repository staff only)

Edit Item