Ultrasound and SWE-based transfer learning for predicting fibrotic NASH
Fei Xia, Kun Wang, Yuhe Wang, Chaoxue Zhang, Junli Wang · 2025
Read Ultrasound and SWE-based transfer learning for predicting fibrotic NASH by Fei Xia, Kun Wang, Yuhe Wang, Chaoxue Zhang, Junli Wang (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-12749606.txt.
Description
Fatty liver disease turns dangerous when scarring joins the fat, and catching that turn without a biopsy is a standing goal. Fei Xia and co-authors trained a deep learning model on rats with diet-induced liver disease. Three versions competed: one reading ordinary ultrasound, one reading stiffness maps from elastography, and one combining both image types with clinical data.
The combined model won clearly, with the best discrimination score of the three. Decision analysis showed it would help clinicians across most risk thresholds. Calibration checks said its probabilities meant what they said. The authors present the multimodal recipe as the way forward for spotting fibrotic fatty liver early.
Catalog record
| CREATOR | Fei Xia, Kun Wang, Yuhe Wang, Chaoxue Zhang, Junli Wang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |