基于多序列MRI的卷积神经网络预测胶质瘤MGMT启动子甲基化状态  

Multi-sequence MRI-based convolutional neural network predicts the methylation status of MGMT promoter in glioma

作　　者：陈晓华 张若弟 周云舒 刘世莉 王卓 张少茹 陈志强[1,2,3] CHEN Xiaohua;ZHANG Ruodi;ZHOU Yunshu;LIU Shili;WANG Zhuo;ZHANG Shaoru;CHEN Zhiqiang(Department of Radiology,General Hospital of Ningxia Medical University,Yinchuan 750004,China;Department of Radiology,the First Hospital Affiliated to Hainan Medical College,Haikou 570102,China;College of Clinical Medicine,Ningxia Medical University,Yinchuan 750004,China)

机构地区：[1]宁夏医科大学总医院放射科,银川750004 [2]海南医学院第一附属医院放射科,海口570102 [3]宁夏医科大学临床医学院,银川750004

出　　处：《磁共振成像》2023年第8期34-39,78,共7页Chinese Journal of Magnetic Resonance Imaging

基　　金：宁夏回族自治区重点研发计划项目(编号:2019BEG03033);宁夏自然科学基金(编号:2022AAC03472);教育部春晖项目(编号:Z2012002)。

摘　　要：目的 探讨基于多序列MRI的卷积神经网络模型预测脑胶质瘤O6-甲基鸟嘌呤-DNA-甲基转移酶(O6-methylguanine-DNA methyltransferase, MGMT)启动子甲基化状态的价值。材料与方法 回顾性分析宁夏医科大学总医院2015年11月至2022年6月经手术病理证实的161例胶质瘤患者的临床及MRI影像资料,其中MGMT启动子甲基化型80例,未甲基化型81例。收集术前MRI的T2WI、T2液体衰减反转恢复(T2 fluid attenuated inversion recovery, T2-FLAIR)及对比增强T1WI (contrast enhanced T1WI, CE-T1WI)序列,对所有图像预处理后,勾画感兴趣区(region of interest, ROI)。对图像进行标注后按照7∶3随机分为训练集和验证集。使用34层残差神经网络(34-layer-residual convolutional neural network, ResNet34)分别建立基于T2WI、T2-FLAIR、CE-T1WI的单序列模型T2-net、T2f-net、TC-net和多序列融合模型TS-net,预测MGMT启动子甲基化状态。采用受试者工作特征曲线下面积(area under the receiver operating characteristic, AUROC)、精确度-召回率曲线下面积(area under the precision-recall curve, AUPRC)、准确度、特异度和敏感度评估模型效能,通过DeLong检验比较模型间的预测效能。结果 四个预测模型T2-net、T2f-net、TC-net、TS-net均有良好的预测效能,TS-net的AUROC值均高于T2-net、T2f-net、TC-net(训练集:0.930 vs. 0.859、0.877、0.920;验证集:0.910 vs. 0.812、0.840、0.854),TS-net的AUPRC值均高于T2-net、T2f-net、TC-net(训练集:0.912 vs. 0.860、0.864、0.908;验证集:0.896 vs. 0.796、0.826、0.839)。验证集中TS-net的AUROC值均高于T2-net、T2f-net、TC-net,差异均有统计学意义,训练集中与T2-net、T2f-net相比差异有统计学意义(DeLong检验,P<0.05)。结论 基于多序列MRI融合的卷积神经网络模型,可以准确、无创地预测胶质瘤MGMT甲基化状态,优于单一序列模型,为指导临床治疗决策和评估胶质瘤患者预后提供可靠依据。Objective:To investigate the value of a convolutional neural network model based on multi-sequence MRI to predict the promoter methylation status of O6-methylguanine-DNA-methyltransferase(MGMT)in glioma.Materials and Methods:Retrospective analysis of clinical and MRI data of 161 patients with glioma confirmed by surgical pathology from November 2015 to June 2022 at Ningxia Medical University General Hospital,including 80 cases of MGMT promoter methylation type and 81 cases of unmethylated type.T2WI,T2 fluid-attenuated inversion recovery(T2-FLAIR)and contrast enhanced T1‐weighted imaging(CE-T1WI)of preoperative MRI were collected,and regions of interest(ROI)were outlined after preprocessing of all images.The images were randomly divided into training and validation sets according to 7∶3 after labeling.A 34-layer-residual neural network(ResNet34)was used to build T2WI,T2-FLAIR,enhanced T1WI and multiple sequence fusion models T2-net,T2f-net,TC-net and TS-net,respectively,to predict the methylation status of MGMT promoters.The area under the receiver operating characteristic(AUROC),area under the precision-recall curve(AUPRC),accuracy,specificity and sensitivity were used to assess model efficacy,and the predictive power was compared between models by DeLong test.Results:All four prediction models T2-net,T2f-net,TC-net,and TS-net had good prediction efficacy,and the AUROC values of TS-net were higher than those of T2-net,T2f-net,and TC-net(training set:0.930 vs.0.859,0.877,0.920;validation set:0.910 vs.0.812,0.840,0.854).The AUPRC values of TS-net were higher than those of T2-net,T2f-net,and TC-net(training set:0.912 vs.0.860,0.864,0.908;validation set:0.896 vs.0.796,0.826,0.839).The AUROC values of TS-net in the validation set were all higher than those of T2-net,T2f-net,and TC-net,and the differences were all statistically significant.In addition,the differences in the training set were statistically significant compared with T2-net and T2f-net(DeLong test,P<0.05).Conclusions:Convolutional neural network model

关 键 词：成人弥漫胶质瘤 磁共振成像 深度学习 卷积神经网络 O6-甲基鸟嘌呤-DNA-甲基转移酶 分子分型 

分 类 号：R445.2[医药卫生—影像医学与核医学] R730.264[医药卫生—诊断学]