RAUM-GANs: a multi-layer GAN-enhanced framework for accurate multiple sclerosis lesion segmentation in MRI
Ahmed Alsayat, Ayman Mohamed Mostafa, Mahmoud Elmezain, Malak Alamri, Madallah Alruwaili, Mashail N Alkhomsan, Menwa Alshammeri, Mohamed Ezz, Saleh Alharbi, Elsayed Mostafa, Wael Said · 2025
Read RAUM-GANs: a multi-layer GAN-enhanced framework for accurate multiple sclerosis lesion segmentation in MRI by Ahmed Alsayat, Ayman Mohamed Mostafa, Mahmoud Elmezain, Malak Alamri, Madallah Alruwaili, Mashail N Alkhomsan, Menwa Alshammeri, Mohamed Ezz, Saleh Alharbi, Elsayed Mostafa, Wael Said (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-12708764.txt.
Description
Ahmed Alsayat and ten colleagues build a layered system that first repairs brain scans, then outlines multiple sclerosis lesions, in a 2025 paper. Lesion mapping on MRI is hampered by noise, missing slices, and scarce labeled examples.
Three repair layers precede the outlining. A denoising network cleans the images, and a second fills gaps in incomplete scans. A third grows the data set with synthetic scans guarded against collapse and blur. A residual attention U-Net then draws the lesions. On a public challenge data set, the system beat four leading methods, with near ninety-seven percent overlap against expert drawings. The authors pitch the pipeline for other imaging fields facing the same data problems.
Catalog record
| CREATOR | Ahmed Alsayat, Ayman Mohamed Mostafa, Mahmoud Elmezain, Malak Alamri, Madallah Alruwaili, Mashail N Alkhomsan, Menwa Alshammeri, Mohamed Ezz, Saleh Alharbi, Elsayed Mostafa, Wael Said |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 111 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |