Robust multi‐modality segmentation of medial temporal lobe subregions using both 3‐tesla and 7‐tesla magnetic resonance imaging
Yue Li, Pulkit Khandelwal, Long Xie, Christopher D Brown, Xueying Lyu, Amanda E Denning, Mengjin Dong, Sandhitsu R Das, David A Wolk, Paul A Yushkevich · 2025
Read Robust multi‐modality segmentation of medial temporal lobe subregions using both 3‐tesla and 7‐tesla magnetic resonance imaging by Yue Li, Pulkit Khandelwal, Long Xie, Christopher D Brown, Xueying Lyu, Amanda E Denning, Mengjin Dong, Sandhitsu R Das, David A Wolk, Paul A Yushkevich (2025) 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-11714761.txt.
Description
Measuring small subregions of the medial temporal lobe in brain scans can track Alzheimer's disease, but poor scan quality makes the measures unreliable. Yue Li and co-authors built a segmentation model in 2025 that reads scans from both standard and ultra-high-field MRI machines at once. When one scan type is weak, the others can fill in, which single-scan models cannot do.
The model was trained on hand-labeled high-quality scans and taught with random noise swaps to use all inputs. On mixed-quality data it segmented subregions well where a single-scan model failed. Its volume measures also separated early Alzheimer's patients from healthy peers better and stayed more stable over repeat visits.
Catalog record
| CREATOR | Yue Li, Pulkit Khandelwal, Long Xie, Christopher D Brown, Xueying Lyu, Amanda E Denning, Mengjin Dong, Sandhitsu R Das, David A Wolk, Paul A Yushkevich |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |