Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking

Published: 25 Sept 2024, Last Modified: 06 Nov 2024NeurIPS 2024 spotlightEveryoneRevisionsBibTeXCC BY-NC-SA 4.0
Keywords: foundation model, fMRI
TL;DR: Brain-JEPA is a state-of-the-art brain dynamics foundation model enhancing brain activity analysis, it achieves superior performance on different downstream tasks with broad applicability.
Abstract: We introduce *Brain-JEPA*, a brain dynamics foundation model with the Joint-Embedding Predictive Architecture (JEPA). This pioneering model achieves state-of-the-art performance in demographic prediction, disease diagnosis/prognosis, and trait prediction through fine-tuning. Furthermore, it excels in off-the-shelf evaluations (e.g., linear probing) and demonstrates superior generalizability across different ethnic groups, surpassing the previous large model for brain activity significantly. Brain-JEPA incorporates two innovative techniques: **Brain Gradient Positioning** and **Spatiotemporal Masking**. Brain Gradient Positioning introduces a functional coordinate system for brain functional parcellation, enhancing the positional encoding of different Regions of Interest (ROIs). Spatiotemporal Masking, tailored to the unique characteristics of fMRI data, addresses the challenge of heterogeneous time-series patches. These methodologies enhance model performance and advance our understanding of the neural circuits underlying cognition. Overall, Brain-JEPA is paving the way to address pivotal questions of building brain functional coordinate system and masking brain activity at the AI-neuroscience interface, and setting a potentially new paradigm in brain activity analysis through downstream adaptation.
Primary Area: Neuroscience and cognitive science (neural coding, brain-computer interfaces)
Submission Number: 5961
Loading