Metraipolis › archive › dc_fc400fa9c8db

Brain2Vec: A Self-Supervised 3D Foundation Model for Structural Brain MRI — arXiv:2610.28411

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.28411
License (as archived): CC0-1.0
Archived: 2026-10-21T07:08:29.628Z
SHA-256 of the archived text: e070e977b8fb13f11cb229554a8301639158f9b9e2bc493389e3cb0634012d8f
Stable URL of this page: https://metraipolis.com/documento/dc_fc400fa9c8db

How to cite

Brain2Vec: A Self-Supervised 3D Foundation Model for Structural Brain MRI — arXiv:2610.28411 — arXiv (en), https://arxiv.org/abs/2610.28411 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc400fa9c8db (Metraipolis archive dc_fc400fa9c8db, sha256 e070e977b8fb13f11cb229554a8301639158f9b9e2bc493389e3cb0634012d8f)

BibTeX

@misc{dcfc400fa9c8db,
  title = {Brain2Vec: A Self-Supervised 3D Foundation Model for Structural Brain MRI — arXiv:2610.28411},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.28411},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc400fa9c8db; sha256 e070e977b8fb13f11cb229554a8301639158f9b9e2bc493389e3cb0634012d8f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.28411. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep learning models have become essential tools in medical imaging, yet training them end-to-end for diverse tasks remains challenging due to limited labeled data and computational constraints. To address this, we introduce Brain2Vec, a foundation model pre-trained on 74,425 T1-weighted Magnetic Resonance Imaging (MRI) scans pooled from multiple studies. Brain2Vec can serve both as a weight initialization backbone for fine-tuning downstream tasks and as a standalone feature extractor. We evaluated Brain2Vec in three tasks: downstream predictive performance, convergence speed, and embedding quality. Using Brain2Vec's pretrained weights as initialization and fine-tuning on labeled data for a brain age prediction task, results demonstrate improved final accuracy and faster convergence compared to random initialization. Additionally, its frozen embeddings outperform anatomically defined volumetric features on four of five downstream classification tasks and perform competitively with a state-of-the-art foundation model pre-trained on substantially more data. Lastly, we show that Brain2Vec encodes information primarily from a spatially localized and neuroanatomically meaningful set of brain regions, and that manipulating a subset of latent features produces monotonic, region-specific effects on the reconstructed anatomy. Brain2Vec code and trained models are available as an open-source package on this https URL . Users can apply Brain2Vec locally by installing the package, or directly through the NiChart cloud platform this https URL , where Brain2Vec features can be derived without requiring local installation or specialized infrastructure.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.28411 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-21T07:05:43.651Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).