Large-scale modality-invariant foundation models for brain MRI analysis: Application to lesion segmentation
This work addresses the challenge of applying foundation models to neuroimaging tasks like stroke and epilepsy lesion segmentation, but it is incremental as it builds on existing SSL frameworks.
The paper tackled the problem of adapting self-supervised learning for multi-modal brain MRI analysis by proposing a modality-invariant representation learning setup, and found that lesion segmentation benefits more from preserving modality-specific features rather than cross-modality alignment.
The field of computer vision is undergoing a paradigm shift toward large-scale foundation model pre-training via self-supervised learning (SSL). Leveraging large volumes of unlabeled brain MRI data, such models can learn anatomical priors that improve few-shot performance in diverse neuroimaging tasks. However, most SSL frameworks are tailored to natural images, and their adaptation to capture multi-modal MRI information remains underexplored. This work proposes a modality-invariant representation learning setup and evaluates its effectiveness in stroke and epilepsy lesion segmentation, following large-scale pre-training. Experimental results suggest that despite successful cross-modality alignment, lesion segmentation primarily benefits from preserving fine-grained modality-specific features. Model checkpoints and code are made publicly available.