Ensemble Attention Guided Multi-SEANet Trained with Curriculum Learning for Noninvasive Prediction of Gleason Grade Groups from MRI  

作　　者：沈傲 胡冀苏 金鹏飞 周志勇 钱旭升 郑毅 包婕 王希明 戴亚康 SHEN Ao;HU Jisu;JIN Pengfei;ZHOU Zhiyong;QIAN Xusheng;ZHENG Yi;BAO Jie;WANG Ximing;DAI Yakang(School of Computer Science and Technology,Changchun University of Science and Technology,Changchun 130022,China;Suzhou Institute of Biomedical Engineering and Technology,Chinese Academy of Sciences,Suzhou 215163,Jiangsu,China;School of Biomedical Engineering(SooChow),University of Science and Technology of China,Suzhou 215163,Jiangsu,China;Department of Radiology,The First Afiliated Hospital of Soochow University,Suzhou 215006,Jiangsu,China)

机构地区：[1]School of Computer Science and Technology,Changchun University of Science and Technology,Changchun 130022,China [2]Suzhou Institute of Biomedical Engineering and Technology,Chinese Academy of Sciences,Suzhou 215163,Jiangsu,China [3]School of Biomedical Engineering(SooChow),University of Science and Technology of China,Suzhou 215163,Jiangsu,China [4]Department of Radiology,The First Afiliated Hospital of Soochow University,Suzhou 215006,Jiangsu,China

出　　处：《Journal of Shanghai Jiaotong university(Science)》2024年第1期109-119,共11页上海交通大学学报（英文版）

基　　金：Foundation item:the Suzhou Municipal Health and Family Planning Commission's Key Diseases Diagnosis and Treatment Program(No.LCzX202001);the Science and Technology Development Project ofSuzhou(Nos.SS2019012andSKY2021031);the Youth Innovation Promotion Association CAS(No.2021324);the Medical Research Project of Jiangsu Provincial Health and Family Planning Commission(No.M2020068)。

摘　　要：The Gleason grade group(GG)is an important basis for assessing the malignancy of prostate can-cer,but it requires invasive biopsy to obtain pathology.To noninvasively evaluate GG,an automatic prediction method is proposed based on multi-scale convolutional neural network of the ensemble attention module trained with curriculum learning.First,a lesion-attention map based on the image of the region of interest is proposed in combination with the bottleneck attention module to make the network more focus on the lesion area.Second,the feature pyramid network is combined to make the network better learn the multi-scale information of the lesion area.Finally,in the network training,a curriculum based on the consistency gap between the visual evaluation and the pathological grade is proposed,which further improves the prediction performance of the network.Ex-perimental results show that the proposed method is better than the traditional network model in predicting GG performance.The quadratic weighted Kappa is 0.4711 and the positive predictive value for predicting clinically significant cancer is 0.9369.

关 键 词：prostate cancer Gleason grade groups(GGs) bi-parametric magnetic resonance imaging deep learn-ing curriculum learning 

分 类 号：R737.25[医药卫生—肿瘤] TP391.4[医药卫生—临床医学]