A combined radiomics and habitat analysis model for predicting early recurrence of HCC after liver transplantation.

Introduction: Hepatocellular carcinoma (HCC) is highly prevalent and ranks as the third leading cause of cancer-related deaths globally, posing a significant threat to public health worldwide. To identify high-risk patients for early recurrence after liver transplantation (LT) promptly, thereby optimizing personalized follow-up and intervention strategies for HCC patients. We aim to develop a combined radiomics and habitat analysis model for predicting early recurrence of HCC After LT. Methods: A retrospective cohort of 140 HCC patients was selected. Arterial-phase CECT images and clinical data were used for region of interest (ROI) segmentation, habitat analysis, feature extraction and selection. Model performance was assessed through receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Results: The accuracy, sensitivity, specificity, and AUC values of the combined model in the training and testing cohorts were 0.847/0.833, 0.830/0.731, 0.867/1.000, and 0.929 (95% CI: 0.883-0.975)/0.882 (95% CI: 0.983-0.982), all outperforming the clinical model, radiomics model, and habitat analysis model. Furthermore, the combined model demonstrated the highest consistency in calibration curves and provided the greatest clinical net benefit in decision curve analysis. Conclusion: The combined model based on radiomics and habitat analysis demonstrates robust applicability and high predictive performance in identifying early postoperative recurrence of HCC. This strategy facilitates proactive and individualized intervention for high-risk patients, thereby improving clinical outcomes.