Abstract
Artificial intelligence applied to brain magnetic resonance imaging (MRI) holds potential to advance diagnosis, prognosis and treatment planning for neurological diseases. The field has been constrained, thus far, by limited training data and task-specific models that do not generalize well across patient populations and medical tasks. By leveraging self-supervised learning, pretraining and targeted adaptation, foundation models present a promising paradigm to overcome these limitations. Here we present Brain Imaging Adaptive Core (BrainIAC)-a foundation model designed to learn generalized representations from unlabeled brain MRI data and serve as a core basis for diverse downstream application adaptation. Trained and validated on 48,965 brain MRIs across a broad spectrum of tasks, we demonstrate that BrainIAC outperforms localized supervised training and other pretrained models, particularly in low-data, few-shot, settings and in high-difficulty prediction tasks, allowing for application in scenarios otherwise infeasible. BrainIAC can be integrated into imaging pipelines and multimodal frameworks and may lead to improved biomarker discovery and artificial intelligence clinical translation.