Deep learning-assisted LI-RADS grading and distinguishing hepatocellular carcinoma (HCC) from non-HCC based on multiphase CT: a two-center study

作者全名："Xu, Yang; Zhou, Chaoyang; He, Xiaojuan; Song, Rao; Liu, Yangyang; Zhang, Haiping; Wang, Yudong; Fan, Qianrui; Chen, Weidao; Wu, Jiangfen; Wang, Jian; Guo, Dajing"

作者地址："[Xu, Yang; He, Xiaojuan; Song, Rao; Liu, Yangyang; Zhang, Haiping; Guo, Dajing] Chongqing Med Univ, Affiliated Hosp 2, Dept Radiol, Chongqing 400010, Peoples R China; [Zhou, Chaoyang; Wang, Jian] Army Mil Med Univ, Affiliated Hosp 1, Dept Radiol, Chongqing 400038, Peoples R China; [Wang, Yudong; Fan, Qianrui; Chen, Weidao; Wu, Jiangfen] InferVision, Ocean Int Ctr, Inst Res, Beijing 100025, Peoples R China"

通信作者："Guo, DJ (通讯作者)，Chongqing Med Univ, Affiliated Hosp 2, Dept Radiol, Chongqing 400010, Peoples R China.; Wang, J (通讯作者)，Army Mil Med Univ, Affiliated Hosp 1, Dept Radiol, Chongqing 400038, Peoples R China."

来源：EUROPEAN RADIOLOGY

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001020230900002

JCR分区：Q1

影响因子：5.9

年份：2023

卷号：　

期号：　

开始页：　

结束页：　

文献类型：Article; Early Access

关键词：Hepatocellular carcinoma (HCC); The Liver Imaging Reporting and Data System (LI-RADS); Deep learning (DL); Transformer; Computed tomography (CT)

摘要："ObjectivesTo develop a deep learning (DL) method that can determine the Liver Imaging Reporting and Data System (LI-RADS) grading of high-risk liver lesions and distinguish hepatocellular carcinoma (HCC) from non-HCC based on multiphase CT.MethodsThis retrospective study included 1049 patients with 1082 lesions from two independent hospitals that were pathologically confirmed as HCC or non-HCC. All patients underwent a four-phase CT imaging protocol. All lesions were graded (LR 4/5/M) by radiologists and divided into an internal (n = 886) and external cohort (n = 196) based on the examination date. In the internal cohort, Swin-Transformer based on different CT protocols were trained and tested for their ability to LI-RADS grading and distinguish HCC from non-HCC, and then validated in the external cohort. We further developed a combined model with the optimal protocol and clinical information for distinguishing HCC from non-HCC.ResultsIn the test and external validation cohorts, the three-phase protocol without pre-contrast showed & kappa; values of 0.6094 and 0.4845 for LI-RADS grading, and its accuracy was 0.8371 and 0.8061, while the accuracy of the radiologist was 0.8596 and 0.8622, respectively. The AUCs in distinguishing HCC from non-HCC were 0.865 and 0.715 in the test and external validation cohorts, while those of the combined model were 0.887 and 0.808.ConclusionThe Swin-Transformer based on three-phase CT protocol without pre-contrast could feasibly simplify LI-RADS grading and distinguish HCC from non-HCC. Furthermore, the DL model have the potential in accurately distinguishing HCC from non-HCC using imaging and highly characteristic clinical data as inputs."

基金机构：Chongqing Health Commission [2022ZDXM026]; Chongqing Science and Technology Bureau [2022ZDXM026]

基金资助正文：This study has received funding by Chongqing medical scientific research project (Joint project of Chongqing Health Commission and Science and Technology Bureau) (Grant No. 2022ZDXM026).