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

作者机构：School of Computer Science and TechnologyChangchun University of Science and TechnologyChangchun 130022China Suzhou Institute of Biomedical Engineering and TechnologyChinese Academy of SciencesSuzhou 215163JiangsuChina School of Biomedical Engineering(SooChow)University of Science and Technology of ChinaSuzhou 215163JiangsuChina Department of RadiologyThe First Afiliated Hospital of Soochow UniversitySuzhou 215006JiangsuChina 

出 版 物：《Journal of Shanghai Jiaotong university(Science)》 (上海交通大学学报（英文版）)

年 卷 期：2024年第29卷第1期

页      面：109-119页

核心收录：

学科分类：1305[艺术学-设计学（可授艺术学、工学学位）] 13[艺术学] 1002[医学-临床医学] 081104[工学-模式识别与智能系统] 08[工学] 0804[工学-仪器科学与技术] 100214[医学-肿瘤学] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 10[医学] 

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) 

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

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 *** noninvasively evaluate GG,an automatic prediction method is proposed based on multi-scale convolutional neural network of the ensemble attention module trained with curriculum ***,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 ***,the feature pyramid network is combined to make the network better learn the multi-scale information of the lesion ***,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 ***-perimental results show that the proposed method is better than the traditional network model in predicting GG *** quadratic weighted Kappa is 0.4711 and the positive predictive value for predicting clinically significant cancer is 0.9369.