A pre-trained foundation model framework for multiplanar MRI classification of extramural vascular invasion and mesorectal fascia invasion in rectal cancer
Yumeng Zhang, Shruti Atul Mali, Danial Khan, Sina Amirrajab, Eduardo Ibor-Crespo, Ana Jimenez-Pastor, Gloria Ribas, Silvia Flor-Arnal, Marta Zerunian, Christophe Aubé, Luis Martí-Bonmatí, Zohaib Salahuddin, Philippe Lambin · 2026
Read A pre-trained foundation model framework for multiplanar MRI classification of extramural vascular invasion and mesorectal fascia invasion in rectal cancer by Yumeng Zhang, Shruti Atul Mali, Danial Khan, Sina Amirrajab, Eduardo Ibor-Crespo, Ana Jimenez-Pastor, Gloria Ribas, Silvia Flor-Arnal, Marta Zerunian, Christophe Aubé, Luis Martí-Bonmatí, Zohaib Salahuddin, Philippe Lambin (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-13197564.txt.
Description
Yumeng Zhang and colleagues built a 2026 AI framework to read rectal cancer scans. Doctors must judge whether cancer has entered nearby veins or reached the sheet that bounds the rectum. Eye reads vary by reader and hospital, so an automated read could steady care choices.
The team gathered 331 scans from three European hospitals. A signal tuning step cut scanner-to-scanner drift. Three classifiers were trained on most scans and tested on the rest. The best vein-invasion score came from blending two scan angles with a pre-trained medical model. The best sheet-invasion score came from one angle after tuning. Heat maps showed the models looked at the right zones. Results beat a prior contest benchmark.
Catalog record
| CREATOR | Yumeng Zhang, Shruti Atul Mali, Danial Khan, Sina Amirrajab, Eduardo Ibor-Crespo, Ana Jimenez-Pastor, Gloria Ribas, Silvia Flor-Arnal, Marta Zerunian, Christophe Aubé, Luis Martí-Bonmatí, Zohaib Salahuddin, Philippe Lambin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |