Multi-modal radiomics model to predict treatment response to neoadjuvant chemotherapy for locally advanced rectal cancer

作     者：Zheng-Yan Li Xiao-Dong Wang Mou Li Xi-Jiao Liu Zheng Ye Bin Song Fang Yuan Yuan Yuan Chun-Chao Xia Xin Zhang Qian Li 

作者机构：Department of RadiologyWest China Hospital of Sichuan UniversityChengdu 610041Sichuan ProvinceChina Department of Gastrointestinal SurgeryWest China Hospital of Sichuan UniversityChengdu 610041Sichuan ProvinceChina Life SciencePDxIPM teamGE HealthcareShanghai 210000China 

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

年 卷 期：2020年第26卷第19期

页      面：2388-2402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 Research Grant of National Nature Science Foundation of China,No.81971571 Multimodal MR Imaging and Radiomics of Rectal Cancer,Science and Technology Department of Sichuan Province,No.2019YFS0431 Sichuan University Training Program of Innovation and Entrepreneurship for Undergraduates,No.C2019104739 

主　　题：Radiomics Rectal cancer Neoadjuvant chemotherapy Magnetic resonance imaging Computed tomography 

摘      要：BACKGROUND Neoadjuvant chemotherapy is currently recommended as preoperative treatment for locally advanced rectal cancer(LARC);however,evaluation of treatment response to neoadjuvant chemotherapy is still *** To create a multi-modal radiomics model to assess therapeutic response after neoadjuvant chemotherapy for *** This retrospective study consecutively included 118 patients with LARC who underwent both computed tomography(CT)and magnetic resonance imaging(MRI)before neoadjuvant chemotherapy between October 2016 and June *** findings were used as the reference standard for pathological *** were randomly divided into a training set(n=70)and a validation set(n=48).The performance of different models based on CT and MRI,including apparent diffusion coefficient(ADC),dynamic contrast enhanced T1 images(DCE-T1),high resolution T2-weighted imaging(HR-T2WI),and imaging features,was assessed by using the receiver operating characteristic curve *** was demonstrated as area under the curve(AUC)and accuracy(ACC).Calibration plots with Hosmer-Lemeshow tests were used to investigate the agreement and performance characteristics of the *** Eighty out of 118 patients(68%)achieved a pathological *** an individual radiomics model,HR-T2WI performed better(AUC=0.859,ACC=0.896)than CT(AUC=0.766,ACC=0.792),DCE-T1(AUC=0.812,ACC=0.854),and ADC(AUC=0.828,ACC=0.833)in the validation *** imaging performance for extramural venous invasion detection was relatively low in both the training(AUC=0.73,ACC=0.714)and validation(AUC=0.578,ACC=0.583)*** multi-modal radiomics model reached an AUC of 0.925 and ACC of 0.886 in the training set,and an AUC of 0.93 and ACC of 0.875 in the validation *** the clinical radiomics nomogram,good agreement was found between the nomogram prediction and actual *** A multi-modal nomogram using traditional imaging features and radiomics of preoperati