Metraipolis › archive › dc_fb5c99f96fc6
Comparative Study of Anatomical and Learned Features in AI Models for Structural Brain MRI — arXiv:2609.06807
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06807
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:09:23.274Z
- SHA-256 of the archived text
bb51368901bee63580aaa76282e09678fca80f98c50c104861deea01ba1b5f5b- Stable URL of this page
https://metraipolis.com/documento/dc_fb5c99f96fc6
How to cite
Comparative Study of Anatomical and Learned Features in AI Models for Structural Brain MRI — arXiv:2609.06807 — arXiv (en), https://arxiv.org/abs/2609.06807 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fb5c99f96fc6 (Metraipolis archive dc_fb5c99f96fc6, sha256 bb51368901bee63580aaa76282e09678fca80f98c50c104861deea01ba1b5f5b)
BibTeX
@misc{dcfb5c99f96fc6,
title = {Comparative Study of Anatomical and Learned Features in AI Models for Structural Brain MRI — arXiv:2609.06807},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06807},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fb5c99f96fc6; sha256 bb51368901bee63580aaa76282e09678fca80f98c50c104861deea01ba1b5f5b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06807. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In this work, we comprehensively evaluate three popular feature-extraction paradigms in AI-based neuroimaging modeling: (1) computation of anatomical surfaces and volumes, (2) supervised learning with convolutional neural networks (CNNs), and (3) unsupervised pretraining of vision transformer (ViT) foundation models, followed by supervised finetuning. Our study is based on 18 publicly available datasets containing 3D structural T1-weighted MRI scans from approximately 80,000 participants across seven distinct clinical tasks. We observe that a linear model based on anatomical features matches the diagnostic performance of complex nonlinear features learned by sophisticated AI frameworks, including foundation models trained on thousands of scans. Conversely, CNNs and pretrained ViTs learn features that implicitly capture relevant anatomical information, bypassing the need for explicit feature extraction. Building upon these insights, we propose Anatomy Segmentation Pretraining (ASP), a novel method to incorporate anatomical information during foundation-model pretraining, which outperforms existing models in biological age estimation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.06807 — 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 2026-10-16T14:49:57.131Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).