Dataset-Specific Encoding of Image Content Underlies Cross-Dataset Failure in Brain MRI Foundation Models

Frozen features from brain MRI foundation models lose accuracy on new datasets, a problem often attributed to dataset encoding. The study shows that the failure stems from the content itself being encoded along different directions in each dataset, rather than from dataset encoding or distribution shifts. Only broadly pretrained models like 3DINO and SAM‑Med3D consistently encode the MRI sequence well enough to transfer, while brain‑specific models such as BrainIAC and BrainFM perform no better than an untrained network.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• safety