基于术前IVIM影像组学预测老年胶质瘤MGMT甲基化状态  

Prediction of MGMT methylation status in elderly gliomas patients based on preoperative IVIM imaging radiomics

作　　者：孙联稀 杨一风 李佳津 杜宁芳 阳丹萍 方旭昊 唐枫 邓尧 叶瑶 毛仁玲 傅彩霞 李仕红 林光武 Sun Lianxi;Yang Yifeng;Li Jiajin;Du Ningfang;Yang Danping;Fang Xuhao;Tang Feng;Deng Yao;Ye Yao;Mao Renling;Fu Caixia;Li Shihong;Lin Guangwu(Department of Radiology,Huadong Hospital,Fudan University,Shanghai,200040,P.R.China;Department of Radiology,Second Affiliated Hospital of Soochow University,Suzhou,Jiangsu,215004,P.R.China;Department of Neurosurgery,Huadong Hospital,Fudan University,Shanghai,200040,P.R.China;Department of Pathology,Huadong Hospital,Fudan University,Shanghai,200040,P.R.China;Siemens(Shenzhen)Magnetic Resonance Ltd.,Shenzhen,Guangdong,518057,P.R.China)

机构地区：[1]复旦大学附属华东医院放射科,上海200040 [2]苏州大学附属第二医院放射科,江苏苏州215004 [3]复旦大学附属华东医院神经外科,上海200040 [4]复旦大学附属华东医院病理科,上海200040 [5]西门子(深圳)磁共振有限公司,广东深圳518057

出　　处：《老年医学与保健》2025年第1期14-19,共6页Geriatrics & Health Care

基　　金：上海市申康医院发展中心申康--医企融合创新协同专项(SHDC2022CRT025);上海市申康医院发展中心--联影联合科研发展计划项目(SKLY2022CRT402)。

摘　　要：目的本研究采用机器学习算法,探讨体素内不相干运动(intravoxel incoherent motion,IVIM)对老年胶质瘤患者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预测价值。方法回顾性分析39例经病理确诊的老年胶质瘤病例。通过3D slicer软件在真实扩散系数(true diffusion coefficient,D)参数图上勾画肿瘤感兴趣区,使用Python从D、快扩散系数(pseudo-diffusion coefficient,D*)、灌注分数(perfusion fraction,f)图中分别提取影像组学特征,用F-test和最小绝对收缩和选择算子法(least absolute shrinkage and selection operator,LASSO)对影像组学特征降维和筛选。分别采用8个机器学习算法构建单个弥散指标模型和联合模型,对老年胶质瘤MGMT启动子甲基化状态进行预测。使用留一验证法(leave-one-out cross-validation,LOOCV),通过平衡准确率(balanced accuracy,BA)、召回率(recall,REC)、精确率(precision,PRE)、F1分数(F1 score,F1)和受试者工作特征曲线下面积(area under the receiver operating characteristic curve,AUC)评价各模型的诊断效能。结果对于老年胶质瘤患者MGMT启动子甲基化状态的预测,性能最佳的机器学习算法为朴素贝叶斯(naive bayes,NB)(AUC均达0.850以上)。基于NB算法构建的IVIM预测模型中,D的预测效能最高(BA:0.841,REC:0.870;PRE:0.870;F1:0.870;AUC:0.902)。结论基于术前IVIM影像组学的机器学习模型可有效预测老年胶质瘤患者MGMT启动子甲基化状态。Objective To explore the predictive value of intravoxel incoherent movement(IVIM)on the methylation status of O6-methylguanine-DNA methyltransferase(MGMT)promoter in elderly glioma patients based on machine learning algorithm.Methods A retrospective analysis was conducted on 39 pathologically confirmed elderly glioma cases.3D slicer software was used to delineate the tumor region of interest on the true diffusion coefficient(D)parameter maps.Python was used to extract radiomics features from D,pseudo-diffusion coefficient(D*),and perfusion fraction(f)maps,respectively.F-test and least absolute shrinkage and selection operator(LASSO)were used to reduce and screen the radiomics features.Eight machine learning algorithms were used to construct single dispersion index models and a combined model,respectively,to predict the methylation status of MGMT promoter in elderly gliomas patients.The leave-one-out cross-validation(LOOCV)was employed,and the diagnostic performance of each model was evaluated by balancing accuracy(BA),recall(REC),precision(PRE),F1 score(F1),and area under the receiver operating characteristic curve(AUC).Results For predicting the methylation status of MGMT promoter in elderly glioma patients,the naive Bayes(NB)algorithm demonstrated the best performance(AUC≥0.850).Among the IVIM prediction models constructed based on NB algorithm,the D parameter achieved the highest prediction performance(BA:0.841,REC:0.870;PRE:0.870;F1:0.870;AUC:0.902).Conclusion The machine learning model based on preoperative IVIM radiomics can effectively predict MGMT promoter methylation status in elderly glioma patients.

关 键 词：老年 胶质瘤 体素内不相干运动 O6-甲基鸟嘌呤-DNA甲基转移酶 机器学习 预测价值 

分 类 号：R73[医药卫生—肿瘤]