Radiomics signature:A potential biomarker forβ-arrestin1 phosphorylation prediction in hepatocellular carcinoma

作     者：Feng Che Qing Xu Qian Li Zi-Xing Huang Cai-Wei Yang Li Ye Wang Yi Wei Yu-Jun Shi Bin Song 

作者机构：Department of RadiologyWest China HospitalSichuan UniversityChengdu 610041Sichuan ProvinceChina Institute of Clinical PathologyWest China HospitalSichuan UniversityChengdu 610041Sichuan ProvinceChina Department of Research and DevelopmentShanghai United Imaging Intelligence Co.LtdShanghai 200232China 

出 版 物：《World Journal of Gastroenterology》 (世界胃肠病学杂志（英文版）)

年 卷 期：2022年第28卷第14期

页      面：1479-1493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] 

基　　金：Supported by the Science and Technology Support Program of Sichuan Province,No.2021YFS0144 and No.2021YFS0021 China Postdoctoral Science Foundation,No.2021M692289 National Natural Science Foundation of China,No.81971571 

主　　题：Hepatocellular carcinoma Sorafenib resistance β-Arrestin1 phosphorylation Radiomics Computed tomography Overall survival 

摘      要：BACKGROUND The phosphorylation status ofβ-arrestin1 influences its function as a signal strongly related to sorafenib *** retrospective study aimed to develop and validate radiomics-based models for predictingβ-arrestin1 phosphorylation in hepatocellular carcinoma(HCC)using whole-lesion radiomics and visual imaging features on preoperative contrast-enhanced computed tomography(CT)*** To develop and validate radiomics-based models for predictingβ-arrestin1 phosphorylation in HCC using radiomics with contrast-enhanced *** Ninety-nine HCC patients(training cohort:n=69;validation cohort:n=30)receiving systemic sorafenib treatment after surgery were enrolled in this retrospective ***-dimensional whole-lesion regions of interest were manually delineated along the tumor margins on portal venous CT *** features were generated and selected to build a radiomics score using logistic regression *** features were evaluated by two radiologists *** these features were combined to establish clinico-radiological(CR)and clinico-radiological-radiomics(CRR)models by using multivariable logistic regression *** diagnostic performance and clinical usefulness of the models were measured by receiver operating characteristic and decision curves,and the area under the curve(AUC)was *** association with prognosis was evaluated using the Kaplan-Meier *** Four radiomics features were selected to construct the radiomics *** the multivariate analysis,alanine aminotransferase level,tumor size and tumor margin on portal venous phase images were found to be significant independent factors for predictingβ-arrestin1 phosphorylation-positive HCC and were included in the CR *** CRR model integrating the radiomics score with clinico-radiological risk factors showed better discriminative performance(AUC=0.898,95%CI,0.820 to 0.977)than the CR model(AUC=0.794,95%CI,0.686 to 0.901;P=0.011),wit