{"paper":{"title":"GenFAR: A generalized representation of brain structure, derived from 49,246 multi-cohort MRIs via deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew J. Saykin, Christos Davatzikos, Colin L. Masters, Daniel S. Marcus, David A. Wolk, Duygu Tosun, Gareth Harman, Guray Erus, Haochang Shou, Ilya M. Nasrallah, John C. Morris, Junhao Wen, Jurgen Fripp, Li Shen, Marilyn S. Albert, Mark Espeland, Murat Bilgel, Pamela Lamontagne, Paul Maruff, Paul M. Thompson, Pratik Chaudhari, Randa Melhem, R. Nick Bryan, Sindhuja Govindarajan Tirumalai, Sterling C. Johnson, Susan M. Resnick, Susan R. Heckbert, Tammie Benzinger, Timothy J. Hohman, Vishnu M. Bashyam, Yang An, Yong Fan","submitted_at":"2026-08-12T15:40:29Z","abstract_excerpt":"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 develo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12185","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.12185/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}