B-mode ultrasound and contrast-enhanced ultrasound-based radiomics interpretable analysis for the prediction of macrotrabecular-massive subtype of hepatocellular carcinoma

Abstract

Background: This study aimed to develop and validate an interpretable radiomics model using quantitative features from B-mode ultrasound (BMUS) and contrast-enhanced ultrasound (CEUS) for predicting macrotrabecular-massive (MTM) hepatocellular carcinoma (HCC). Methods: From October 2020 to September 2023, 344 patients (mean age: 58.20 ± 10.70 years; 275 men) with surgically resected HCC were retrospectively enrolled from three medical centers. Radiomics features were extracted from BMUS and CEUS, followed by a multiple-step feature selection process. BMUSR model (based on BMUS radiomics features), BM + CEUSR model (based on BMUS and CEUS radiomics features) and hybridR+C model (integrated clinical indicators and radiomic features) were established. These radiomics models’ performance was compared with conventional clinic-radiological (CC+R) model using area under the receiver operating characteristic curve (AUC). SHapley Additive exPlanations (SHAP) method was used to interpret model performance. The model’s potential for predicting recurrence-free survival (RFS) was further analyzed. Results: Among ten distinct machine learning classifiers evaluated, the AdaBoost algorithm demonstrated the highest classification performance. The AUCs of the BM + CEUSR model for identifying MTM-HCC were higher than the BMUSR model and the conventional clinic-radiological model in both validation (0.880 vs. 0.720 and 0.658, both p < 0.05) and test sets (0.878 vs. 0.605 and 0.594, both p < 0.05). No statistical differences were observed between the BM + CEUSR model and the hybridR+C model in either set (p > 0.05). Additionally, the AdaBoost-based BM + CEUSR model showed promising in stratifying early recurrence-free survival, with p < 0.001. Conclusion: The AdaBoost-based BM + CEUSR model shows promise as a tool for preoperatively identifying MTM-HCC and may also be beneficial in predicting prognosis.