^(18)F-FDG PET图像结合影像组学在帕金森病与非典型性帕金森综合征鉴别诊断中的应用价值  

Application of combining ^(18)F-FDG PET imaging and radiomics in the diagnosis of Parkinson′s disease and atypical parkinsonian syndromes

作　　者：孙晓鸣 王敏[1] 李玲 鲁佳荧 葛璟洁 吴平 张慧玮 左传涛 蒋皆恢[1] Sun Xiaoming;Wang Min;Li Ling;Lu Jiaying;Ge Jingjie;Wu Ping;Zhang Huiwei;Zuo Chuantao;Jiang Jiehui(Shanghai Institute of Advanced Communication and Data Science,Shanghai University,Shanghai 200444,China;PET Center,Huashan Hospital,Fudan University,Shanghai 200235,China)

机构地区：[1]上海大学先进通信与数据科学研究院,上海200444 [2]复旦大学附属华山医院PET中心,上海200235

出　　处：《中华核医学与分子影像杂志》2022年第10期583-587,共5页Chinese Journal of Nuclear Medicine and Molecular Imaging

基　　金：国家自然科学基金(81671239);上海市老龄化和妇儿健康研究专项(2020YJZX0111)。

摘　　要：目的探究^(18)F-FDG PET图像结合影像组学在原发性帕金森病(PD)和非典型性帕金森综合征(APS)鉴别诊断中的应用价值。方法该横断面研究纳入2015年3月至2020年8月间复旦大学附属华山医院2个队列(训练组和测试组)共154例受试者,包括正常对照(NC)组40名[男23名、女17名,年龄(60.2±10.5)岁]、PD组40例[男、女各20例,年龄(64.7±6.3)岁]、进行性核上性麻痹(PSP)组40例[男、女各20例,年龄(64.1±5.9)岁]、多系统萎缩(MSA)组34例[男19例、女15例,年龄(65.0±9.2)岁],采集所有受试者的^(18)F-FDG PET图像以及临床量表信息,不同组间量表评分的比较采用单因素方差分析。提取影像组学特征并进行特征筛选;基于logistic回归分别构建二分类和三分类模型,分别计算临床量表模型、影像组学模型和联合模型在PD/MSA/PSP/NC组间两两分类的ROC曲线。在2个队列中进行独立分类测试,并采用100次5折交叉验证。结果2个队列各组间的统一PD评定量表(UPDRS)评分和Hoehn-Yahr分级量表(H&Y)评分差异有统计学意义(F值:4.83~17.95,均P<0.05)。每个受试者共提取2444个影像组学特征,经特征筛选后得到15个特征构建用于分类模型。在二分类实验中,3种模型在PD/MSA/PSP/NC组间两两分类的AUC分别为0.56~0.68、0.74~0.93、0.72~0.93,其中影像组学模型分类效果优于临床模型(z值:1.71~2.85,均P<0.05)。在PD、MSA、PSP三分类实验中,影像组学模型鉴别灵敏度分别为80%、80%和77%。结论^(18)F-FDG PET图像结合影像组学方法具备对PD和APS鉴别诊断的潜力。Objective To explore the potential application of combining ^(18)F-FDG PET imaging and radiomics in the diagnosis of Parkinson′s disease(PD)and atypical parkinsonian syndromes(APS).Methods A total of 154 subjects of two cohorts(training set and validation set)were enrolled from Huashan Hospital,Fudan University from March 2015 to August 2020 in this cross-sectional study,including 40 normal controls(NC;23 males and 17 females,age:(60.2±10.5)years),40 PD patients(20 males and 20 females,age:(64.7±6.3)years),40 progressive supranuclear palsy(PSP)patients(20 males and 20 females,age:(64.1±5.9)years),and 34 multiple system atrophy(MSA)patients(19 males and 15 females,age:(65.0±9.2)years).^(18)F-FDG PET images and clinical scale were selected,and one-way analysis of variance was used to compare differences of clinical scale among groups.Radiomic features extraction and feature selection were carried out.Two and three classification models were constructed based on logistic regression,and the ROC curves of clinical model,radiomics model and combined model were calculated.Independent classification tests were conducted 100 times with 5-fold cross validation in two cohorts.Results There were significant differences in the scores of unified PD Rating Scale(UPDRS)and Hoehn-Yahr rating scale(H&Y)among different groups in cohort 1 and cohort 2 respectively(F values:4.83-17.95,all P<0.05).A total of 2444 imaging features were extracted from each subject,and after features selection,15 features for classification were obtained.In the two classification experiment,the AUCs of the three models in binary classification of PD/MSA/PSP/NC group were 0.56-0.68,0.74-0.93 and 0.72-0.93,respectively.The classification effects of the radiomics model were significantly better than those of the clinical model(z values:1.71-2.85,all P<0.05).In the three classification experiment,the sensitivity of the radiomics model reached 80%,80%and 77%for PD,MSA and PSP,respectively.Conclusion ^(18)F-FDG imaging combined with radiomics has potenti

关 键 词：帕金森病 帕金森障碍 正电子发射断层显像术 氟脱氧葡萄糖F18 影像组学 

分 类 号：R742.5[医药卫生—神经病学与精神病学] R817.4[医药卫生—临床医学]