Feasibility and effectiveness of automatic deep learning network and radiomics models for differentiating tumor stroma ratio in pancreatic ductal adenocarcinoma

作者全名："Liao, Hongfan; Yuan, Jiang; Liu, Chunhua; Zhang, Jiao; Yang, Yaying; Liang, Hongwei; Jiang, Song; Chen, Shanxiong; Li, Yongmei; Liu, Yanbing"

作者地址："[Liao, Hongfan; Liu, Yanbing] Chongqing Med Univ, Coll Med Informat, Chongqing 400016, Peoples R China; [Liao, Hongfan; Liang, Hongwei; Li, Yongmei] Chongqing Med Univ, Dept Orthoped, Affiliated Hosp 1, Chongqing 400016, Peoples R China; [Yuan, Jiang; Chen, Shanxiong] Southwest Univ, Coll Comp & Informat Sci, Chongqing 400715, Peoples R China; [Liu, Chunhua] Army Med Univ, Daping Hosp, Dept Radiol, Chongqing, Peoples R China; [Zhang, Jiao] Chongqing Med Univ, Dept Orthoped, Affiliated Hosp 3, Chongqing, Peoples R China; [Yang, Yaying] Chongqing Med Univ, Mol Med & Canc Res Ctr, Dept Pathol, Chongqing 400016, Peoples R China; [Jiang, Song] Chongqing Ping Med Imaging Diag Ctr, Dept Radiol, Chongqing, Peoples R China"

通信作者："Liu, YB (通讯作者)，Chongqing Med Univ, Coll Med Informat, Chongqing 400016, Peoples R China.; Li, YM (通讯作者)，Chongqing Med Univ, Dept Orthoped, Affiliated Hosp 1, Chongqing 400016, Peoples R China.; Chen, SX (通讯作者)，Southwest Univ, Coll Comp & Informat Sci, Chongqing 400715, Peoples R China."

来源：INSIGHTS INTO IMAGING

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001129322100001

JCR分区：Q1

影响因子：4.1

年份：2023

卷号：14

期号：1

开始页：　

结束页：　

文献类型：Article

关键词：Machine learning; Radiomics; Deep learning; Tumor stroma ratio; Pancreatic ductal adenocarcinoma

摘要："ObjectiveThis study aims to compare the feasibility and effectiveness of automatic deep learning network and radiomics models in differentiating low tumor stroma ratio (TSR) from high TSR in pancreatic ductal adenocarcinoma (PDAC).MethodsA retrospective analysis was conducted on a total of 207 PDAC patients from three centers (training cohort: n = 160; test cohort: n = 47). TSR was assessed on hematoxylin and eosin-stained specimens by experienced pathologists and divided as low TSR and high TSR. Deep learning and radiomics models were developed including ShuffulNetV2, Xception, MobileNetV3, ResNet18, support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF), and logistic regression (LR). Additionally, the clinical models were constructed through univariate and multivariate logistic regression. Kaplan-Meier survival analysis and log-rank tests were conducted to compare the overall survival time between different TSR groups.ResultsTo differentiate low TSR from high TSR, the deep learning models based on ShuffulNetV2, Xception, MobileNetV3, and ResNet18 achieved AUCs of 0.846, 0.924, 0.930, and 0.941, respectively, outperforming the radiomics models based on SVM, KNN, RF, and LR with AUCs of 0.739, 0.717, 0.763, and 0.756, respectively. Resnet 18 achieved the best predictive performance. The clinical model based on T stage alone performed worse than deep learning models and radiomics models. The survival analysis based on 142 of the 207 patients demonstrated that patients with low TSR had longer overall survival.ConclusionsDeep learning models demonstrate feasibility and superiority over radiomics in differentiating TSR in PDAC. The tumor stroma ratio in the PDAC microenvironment plays a significant role in determining prognosis.Critical relevance statementThe objective was to compare the feasibility and effectiveness of automatic deep learning networks and radiomics models in identifying the tumor-stroma ratio in pancreatic ductal adenocarcinoma. Our findings demonstrate deep learning models exhibited superior performance compared to traditional radiomics models.Key points center dot Deep learning demonstrates better performance than radiomics in differentiating tumor-stroma ratio in pancreatic ductal adenocarcinoma.center dot The tumor-stroma ratio in the pancreatic ductal adenocarcinoma microenvironment plays a protective role in prognosis.center dot Preoperative prediction of tumor-stroma ratio contributes to clinical decision-making and guiding precise medicine.Key points center dot Deep learning demonstrates better performance than radiomics in differentiating tumor-stroma ratio in pancreatic ductal adenocarcinoma.center dot The tumor-stroma ratio in the pancreatic ductal adenocarcinoma microenvironment plays a protective role in prognosis.center dot Preoperative prediction of tumor-stroma ratio contributes to clinical decision-making and guiding precise medicine.Key points center dot Deep learning demonstrates better performance than radiomics in differentiating tumor-stroma ratio in pancreatic ductal adenocarcinoma.center dot The tumor-stroma ratio in the pancreatic ductal adenocarcinoma microenvironment plays a protective role in prognosis.center dot Preoperative prediction of tumor-stroma ratio contributes to clinical decision-making and guiding precise medicine."

基金机构：Intelligent Medicine Research Project of Chongqing Medical University

基金资助正文：No Statement Available