Deep learning-based multi-task prediction of response to neoadjuvant chemotherapy using multiscale whole slide images in breast cancer:A multicenter study  

作　　者：Qin Wang Feng Zhao Haicheng Zhang Tongpeng Chu Qi Wang Xipeng Pan Yuqian Chen Heng Zhou Tiantian Zheng Ziyin Li Fan Lin Haizhu Xie Heng Ma Lan Liu Lina Zhang Qin Li Weiwei Wang Yi Dai Ruijun Tang Jigang Wang Ping Yang Ning Mao 

机构地区：[1]School of Information and Electronic Engineering,Shandong Technology and Business University,Yantai 264005,China [2]Big Data and Artificial Intelligence Laboratory,Yantai Yuhuangding Hospital of Qingdao University,Yantai 264000,China [3]Shandong Provincial Key Medical and Health Laboratory of Intelligent Diagnosis and Treatment for Women’s Diseases,Yantai Yuhuangding Hospital,Yantai 264000,China [4]Department of Radiology,Yantai Yuhuangding Hospital of Qingdao University,Yantai 264000,China [5]School of Computer Science and Technology,Shandong Technology and Business University,Yantai 264005,China [6]School of Computer Science and Information Security,Guilin University of Electronic Technology,Guilin 541004,China [7]School of Medical Imaging,Binzhou Medical University,Yantai 264003,China [8]Department of Radiology,Jiangxi Cancer Hospital,the Second Affiliated Hospital of Nanchang Medical College,Nanchang 330006,China [9]Department of Radiology,the First Affiliated Hospital of China Medical University,Shenyang 400042,China [10]Department of Radiology,Weifang Hospital of Traditional Chinese Medicine,Weifang 262600,China [11]Department of Medical Imaging,Affiliated Hospital of Jining Medical University,Jining 272029,China [12]Department of Radiology,the Peking University Shenzhen Hospital,Shenzhen 518036,China [13]Department of Pathology,Guilin Traditional Chinese Medicine Hospital,Guilin 541002,China [14]Department of Pathology,the Affiliated Hospital of Qingdao University,Qingdao 266555,China [15]Department of Pathology,Yantai Yuhuangding Hospital of Qingdao University,Yantai 264000,China

出　　处：《Chinese Journal of Cancer Research》2025年第1期28-47,共20页中国癌症研究(英文版)

基　　金：supported by the National Natural Science Foundation of China(No.82371933);the National Natural Science Foundation of Shandong Province of China(No.ZR2021MH120);the Taishan Scholars Project(No.tsqn202211378);the Shandong Provincial Natural Science Foundation for Excellent Young Scholars(No.ZR2024YQ075).

摘　　要：Objective:Early predicting response before neoadjuvant chemotherapy(NAC)is crucial for personalized treatment plans for locally advanced breast cancer patients.We aim to develop a multi-task model using multiscale whole slide images(WSIs)features to predict the response to breast cancer NAC more finely.Methods:This work collected 1,670 whole slide images for training and validation sets,internal testing sets,external testing sets,and prospective testing sets of the weakly-supervised deep learning-based multi-task model(DLMM)in predicting treatment response and pCR to NAC.Our approach models two-by-two feature interactions across scales by employing concatenate fusion of single-scale feature representations,and controls the expressiveness of each representation via a gating-based attention mechanism.Results:In the retrospective analysis,DLMM exhibited excellent predictive performance for the prediction of treatment response,with area under the receiver operating characteristic curves(AUCs)of 0.869[95%confidence interval(95%CI):0.806−0.933]in the internal testing set and 0.841(95%CI:0.814−0.867)in the external testing sets.For the pCR prediction task,DLMM reached AUCs of 0.865(95%CI:0.763−0.964)in the internal testing and 0.821(95%CI:0.763−0.878)in the pooled external testing set.In the prospective testing study,DLMM also demonstrated favorable predictive performance,with AUCs of 0.829(95%CI:0.754−0.903)and 0.821(95%CI:0.692−0.949)in treatment response and pCR prediction,respectively.DLMM significantly outperformed the baseline models in all testing sets(P<0.05).Heatmaps were employed to interpret the decision-making basis of the model.Furthermore,it was discovered that high DLMM scores were associated with immune-related pathways and cells in the microenvironment during biological basis exploration.Conclusions:The DLMM represents a valuable tool that aids clinicians in selecting personalized treatment strategies for breast cancer patients.

关 键 词：Artificial intelligence breast cancer digital pathology whole slide images 

分 类 号：R737.9[医药卫生—肿瘤]