Deep learning-based radiomics based on contrast-enhanced ultrasound predicts early recurrence and survival outcome in hepatocellular carcinoma

作     者：Zhe Huang Zhu Shu Rong-Hua Zhu Jun-Yi Xin Ling-Ling Wu Han-Zhang Wang Jun Chen Zhi-Wei Zhang Hong-Chang Luo Kai-Yan Li 

作者机构：Department of Medical UltrasoundTongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030Hubei ProvinceChina Institute of Hepato-pancreato-bililary SurgeryTongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030Hubei ProvinceChina PDx Advanced ApplicationsGE HealthcareShanghai 200020China 

出 版 物：《World Journal of Gastrointestinal Oncology》 (世界胃肠肿瘤学杂志（英文版）（电子版）)

年 卷 期：2022年第14卷第12期

页      面：2380-2392页

核心收录：

学科分类：1002[医学-临床医学] 100214[医学-肿瘤学] 10[医学] 

主　　题：Hepatocellular carcinoma Deep learning Overall survival Early recurrence Contrast-enhanced ultrasound 

摘      要：BACKGROUND Hepatocellular carcinoma(HCC)is the most common primary liver *** To predict early recurrence(ER)and overall survival(OS)in patients with HCC after radical resection using deep learning-based radiomics(DLR).METHODS A total of 414 consecutive patients with HCC who underwent surgical resection with available preoperative grayscale and contrast-enhanced ultrasound images were *** clinical,DLR,and clinical+DLR models were then designed to predict ER and *** The DLR model for predicting ER showed satisfactory clinical benefits[area under the curve(AUC=0.819 and 0.568 in the training and testing cohorts,respectively)],similar to the clinical model(AUC=0.580 and 0.520 in the training and testing cohorts,respectively;P0.05).The C-index of the clinical+DLR model in the prediction of OS in the training and testing cohorts was 0.800 and 0.759,*** clinical+DLR model and the DLR model outperformed the clinical model in the training and testing cohorts(P0.001 for all).We divided patients into four categories by dichotomizing predicted ER and *** patients in class 1(high ER rate and low risk of OS),retreatment(microwave ablation)after recurrence was associated with improved survival(hazard ratio=7.895,P=0.005).CONCLUSION Compared to the clinical model,the clinical+DLR model significantly improves the accuracy of predicting OS in HCC patients after radical resection.