Hybrid deep learning model for brain age prediction using time-distributed convolutional and bidirectional LSTM networks
Eslam Mahmoud, Nada M. Elshennawy, Amr Elkholy · 2026
Read Hybrid deep learning model for brain age prediction using time-distributed convolutional and bidirectional LSTM networks by Eslam Mahmoud, Nada M. Elshennawy, Amr Elkholy (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/PMC13263332.txt.
Description
Eslam Mahmoud and co-authors present a 2026 journal article on estimating brain age from MRI scans with deep learning. Brain age prediction compares a scan against typical aging, and the gap from real age is linked to several brain disorders. Their model mixes convolutional layers, which read image patterns, with memory-style LSTM layers.
The team trained on the OpenBHB dataset after steps such as outlier removal, image augmentation, and slice selection. Their model predicted brain age with a mean absolute error of just over three years. That beat earlier published methods on the same kind of data. The authors credit both the hybrid network design and the careful preprocessing for the gain.
Catalog record
| CREATOR | Eslam Mahmoud, Nada M. Elshennawy, Amr Elkholy |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 96032 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |