Development and validation of a Random Forest prediction model integrating clinical and ultrasound radiomics features for microvascular invasion in hepatocellular carcinoma patients: a retrospective study
Aman Makeshati, Yuying Du, Halida Xiaerfuhazi, Xiaoping Yang · 2026
Read Development and validation of a Random Forest prediction model integrating clinical and ultrasound radiomics features for microvascular invasion in hepatocellular carcinoma patients: a retrospective study by Aman Makeshati, Yuying Du, Halida Xiaerfuhazi, Xiaoping Yang (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-13357099.txt.
Description
Aman Makeshati built a sound-scan model to predict vessel invasion before liver cancer surgery, in a 2026 retrospective study. Tiny vessel invasion drives return of disease after liver tumor removal, yet it is hard to foresee before the operation. CT and MRI models exist but cost more, need scarce machines, or expose patients to radiation.
The team combined patient data with ultrasound texture patterns in a Random Forest model, trained on 157 patients and tested on 67. Tumor size, alpha-fetoprotein, and VEGF emerged as independent patient predictors, alongside four texture patterns. In testing, the model reached 0.908 area under the curve with 79.2 percent sensitivity, offering surgeons a cheaper bedside planning aid.
Catalog record
| CREATOR | Aman Makeshati, Yuying Du, Halida Xiaerfuhazi, Xiaoping Yang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |