Contrastive Learning with Adaptive Neighborhoods for Brain Age Prediction on 3D Stiffness Maps

Jakob Träuble, Lucy V Hiscox, Curtis Johnson, Carola-Bibiane Schönlieb, Gabriele S Kaminski Schierle, Angelica I Aviles-Rivero

Abstract: In the field of neuroimaging, accurate brain age prediction is pivotal for uncovering the complexities of brain aging and pinpointing early indicators of neurodegenerative conditions. Recent advancements in self-supervised learning, particularly in contrastive learning, have demonstrated greater robustness when dealing with complex datasets. However, current approaches often fall short in generalizing across non-uniformly distributed data, prevalent in medical imaging scenarios. To bridge this gap, we introduce a novel contrastive loss that adapts dynamically during the training process, focusing on the localized neighborhoods of samples. Moreover, we expand beyond traditional structural features by incorporating brain stiffness—a mechanical property previously underexplored yet promising due to its sensitiv- ity to age-related changes. This work presents the first application of self-supervised learning to brain mechanical properties, using compiled stiffness maps from various clinical studies to predict brain age. Our approach, featuring dynamic localized loss, consistently outperforms existing state-of-the-art methods, demonstrating superior performance and laying the way for new directions in brain aging research.

Submission Length: Regular submission (no more than 12 pages of main content)

Changes Since Last Submission: Thank you for the valuable feedback. We have addressed the comments accordingly. Particularly, in the conclusion we added a discussion on the limitations of our current work.

Code: https://github.com/CoderJacques/BrainAge_DynLocRep

Assigned Action Editor: ~Stanislaw_Kamil_Jastrzebski1

Submission Number: 3109