Metraipolis › archive › dc_c1aa979ddac5
GenFAR: A generalized representation of brain structure, derived from 49,246 multi-cohort MRIs via deep learning — arXiv:2608.12185
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12185
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:49:41.762Z
- SHA-256 of the archived text
7e95fd222a4d27d396a48ff89f73cc48148347e5720a0f522236c5bab4eeca19- Stable URL of this page
https://metraipolis.com/documento/dc_c1aa979ddac5
How to cite
GenFAR: A generalized representation of brain structure, derived from 49,246 multi-cohort MRIs via deep learning — arXiv:2608.12185 — arXiv (en), https://arxiv.org/abs/2608.12185 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c1aa979ddac5 (Metraipolis archive dc_c1aa979ddac5, sha256 7e95fd222a4d27d396a48ff89f73cc48148347e5720a0f522236c5bab4eeca19)
BibTeX
@misc{dcc1aa979ddac5,
title = {GenFAR: A generalized representation of brain structure, derived from 49,246 multi-cohort MRIs via deep learning — arXiv:2608.12185},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12185},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c1aa979ddac5; sha256 7e95fd222a4d27d396a48ff89f73cc48148347e5720a0f522236c5bab4eeca19},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12185. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deep learning models for neuroimaging have largely been developed for individual tasks, limiting knowledge transfer across applications. Here we introduce GenFAR, a modular deep learning framework that learns general, clinically informed features from brain MRIs. We trained this modular architecture on 49,246 individuals across 11 cohorts, using 17 diverse classification and regression tasks spanning cognition, clinical, diagnosis, demographics, and biomarkers. This yields aggregated, focused feature sets that capture rich, clinically- and biologically-relevant brain representations. We developed a sequential learning approach where tasks progressively build on previously learned representations. Through an analysis of 5,000 task sequences, we identified an optimal sequence length of six tasks and introduced a Donor Score metric to quantify each task's contribution to downstream performance. This analysis revealed five consistently strong donor tasks (Age, AD/MCI, MMSE, Hypertension, Hyperlipidemia) that formed the base of our sequential model. We demonstrated the utility of our learned representation, in various tasks beyond those included in the training set, to serve as the foundation for specialized secondary predictors. We further showed that using the learned feature representation can substantially increase the sample efficiency of secondary deep learning training tasks and models, as well as improve their accuracy. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-13 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.12185 — 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 2026-10-19T05:42:25.918Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).