초록/요약

Objective: A radiomics nomogram for pretreatment prediction of TACE refractoriness was developed and validated for hepatocellular carcinoma (HCC) without extrahepatic metastasis or macrovascular invasion. Materials and methods: This study included 80 patients with HCC without extrahepatic metastasis or macrovascular involvement treated with TACE between July 2016 and November 2018. The datasets were divided into a training set (80%) and a test set (20%) for feature selection and tenfold cross-validation. Forty radiomic features were extracted from arterial-phase computed tomography (CT) using the Local Image Features Extraction software. The Lasso regression model was used for radiomics signature selection. The Lasso regression model was used for radiomics signature selection and the selected signatures were validated using the Mann–Whitney U-test. The radiomics nomogram was developed based on a multivariate logistic regression model incorporating the Rad-score, CT imaging factors, and clinical factors, and it was validated. Results: The Rad-score, which consists of the Gray-Level Zone Length Matrix (GLZLM)—Long-Zone Low Gray-Level Emphasis (LZLGE) and GLZLM—Gray-Level Non-Uniformity (GLNU), T-stage, log α-fetoprotein (AFP), and bilobar distribution were significantly associated with TACE refractoriness (p < 0.05). Predictors in the radiomics nomogram were the Rad-score and T-stage (Rad-score + T-stage), Rad-score and bilobar distribution (Rad-score + bilobar distribution), or Rad-score and logAFP (Rad-score + logAFP). The multivariate logistic regression model showed a good predictive performance (Rad-score + T-stage, AUC, 0.95; Rad-score + bilobar distribution, AUC 0.91; and Rad-score + logAFP, AUC, 0.91). Conclusion: The radiomics nomogram could be used for the pretreatment prediction of TACE refractoriness. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC part of Springer Nature.