Predicting intrahepatic recurrence of colorectal cancer liver metastases after curative hepatectomy using a machine learning model with data integration of ultrasound radiomics and clinicopathological
4 hours ago
- #radiomics
- #colorectal cancer
- #machine learning
- A machine learning model was developed to predict intrahepatic recurrence in colorectal cancer liver metastases (CRLM) patients post-hepatectomy.
- The study included 278 patients from two centers, divided into a main cohort (n=224) and an external cohort (n=54).
- Models developed: clinical, radiomics, and a combined clinical-radiomics (cRadiomics) model.
- Key predictors included six clinical parameters and seven radiomics features.
- The cRadiomics model outperformed others with AUC values of 0.811 (main cohort) and 0.784 (external cohort).
- The model aims to improve clinical decision-making and personalized management for CRLM patients.