OpenMAP-BrainAge: generalizable and interpretable brain age predictor from MRI
Pengyu Kan, Craig Jones, Kenichi Oishi, Alzheimer’s Disease Neuroimaging Initiative and the Australian Imaging Biomarkers and Lifestyle Flagship Study of Aging · 2026
Read OpenMAP-BrainAge: generalizable and interpretable brain age predictor from MRI by Pengyu Kan, Craig Jones, Kenichi Oishi, Alzheimer’s Disease Neuroimaging Initiative and the Australian Imaging Biomarkers and Lifestyle Flagship Study of Aging (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13387714.txt.
Description
Pengyu Kan's team presents OpenMAP-BrainAge, a transformer-based model that estimates brain age from 3D MRI scans of the brain. The model reads several views plus volume information at once, and the team tested it on large imaging collections covering healthy adults and people with memory decline.
Forecast errors averaged about three and a half years, and the gap between model and real age grew with decline, from near zero in healthy adults to about six years in dementia. That gap also tracked lower scores on two standard memory tests. Brain regions tied to white matter and deep grey matter carried the strongest signals, giving clinicians a readable clue rather than a black-box number.
Catalog record
| CREATOR | Pengyu Kan, Craig Jones, Kenichi Oishi, Alzheimer’s Disease Neuroimaging Initiative and the Australian Imaging Biomarkers and Lifestyle Flagship Study of Aging |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |