BrainDINO: A Brain MRI Foundation Model for Generalizable Clinical Representation Learning

TL;DR

BrainDINO is a large-scale self-supervised model trained on millions of unlabeled brain MRI slices, capable of generalizing across diverse neuroimaging tasks with minimal supervision and no need for volumetric pretraining.

Contribution

This work introduces BrainDINO, a self-distilled foundation model trained on extensive unlabeled MRI data, enabling versatile and data-efficient neuroimaging analysis.

Findings

Supports multiple neuroimaging tasks with a frozen encoder.

Outperforms existing self-supervised MRI baselines, especially with limited labels.

Reveals anatomically organized and pathology-sensitive features.

Abstract

Brain MRI underpins a wide range of neuroscientific and clinical applications, yet most learning-based methods remain task-specific and require substantial labeled data. Here we show that a single self-supervised representation can generalize across heterogeneous brain MRI endpoints. We trained BrainDINO, a self-distilled foundation model, on approximately 6.6 million unlabeled axial slices from 20 datasets encompassing broad variation in population, disease, and acquisition setting. Using a frozen encoder with lightweight task heads, BrainDINO supported transfer across tumor segmentation, neurodegenerative and neurodevelopmental conditions classification, brain age estimation, post-stroke temporal prediction, molecular status prediction, MRI sequence classification, and survival modeling. Across tasks and supervision regimes, BrainDINO consistently equaled or exceeded natural-image and MRI-specific self-supervised baselines, with particularly strong advantages under label scarcity. Representation analyses further showed anatomically organized and pathology-sensitive feature structure in the absence of task-specific supervision. Our findings indicate that large-scale slice-wise self-supervised learning can yield a unified brain MRI representation that supports diverse neuroimaging tasks without volumetric pretraining or full-network fine-tuning, establishing a scalable foundation for robust and data-efficient brain imaging analysis.