论文部分内容阅读
目的:探讨磁共振(magnetic resonance，MR)扩散张量成像(diffusion tensor imaging，DTI)自动纤维定量(automatic fiber quantification，AFQ)在阿尔茨海默病(Alzheimer's disease，AD)诊断预测中的应用价值。方法:搜集21例AD患者(AD组)和33例正常对照(NC组)的临床和MR资料。采用AFQ软件分析DTI数据，追踪脑内20根白质纤维束，比较各纤维束各项异性指数(fractional anisotropy，FA)、平均扩散系数(mean diffusivity，MD)值的组间差异。沿每根纤维束走行方向分成100等份，将各等份的FA或MD值作为一个特征。筛选具有组间差异的特征，通过支持向量机(support vector machine，SVM)留一法交叉验证对AD和NC进行分类。采用受试者工作特征(receiver operating characteristic，ROC)曲线评价分类效能。结果:20根纤维束中的11根[左/右丘脑前束(anterior thalamic radiation，ATR)、左/右皮质脊髓束(corticospinal tract，CST)、胼胝体膝部束(corpus callosum，CC Genu)、右下纵束(longitudinal fasciculus，ILF)、右上纵束(superior longitudinal fasciculus，SLF)、左/右钩状束(uncinated fasciculus，UF)和左/右弓形束(arcuate fasciculus，AF)]在所有受检者中被成功追踪。相对NC组而言，AD组2根纤维束(左/右UF)的FA值明显减低(n t＝-2.532，-2.391，均n P<0.05)，7根纤维束(左ATR、左/右CST、右ILF、左/右UF、左AF)的MD值明显升高(n t＝2.569，2.411，2.108，2.357，3.773，3.796，3.492，均n P<0.05)。在11根纤维束的2 200个特征中筛选出412个具有组间差异的分类特征，其中78个FA特征分布于7根纤维束(左ATR、左/右CST、CC Genu、右ILF、左/右UF)，334个MD特征分布于9根纤维束(左/右ATR、左/右CST、CC Genu、右ILF、左/右UF、左AF)。SVM分类准确度为85.19%，敏感性为80.95%，特异性为87.88%，ROC曲线下面积为0.894 7。n 结论:基于DTI的AFQ分析在AD诊断预测中具有较高的应用价值。“,”Objective:To investigate the application value of magnetic resonance (MR) diffusion tensor imaging (DTI) automatic fiber quantification (AFQ) in the diagnosis and prediction of Alzheimer's disease (AD).Methods:Clinical and MR data of 21 patients with AD (AD group) and 33 normal controls (NC group) were collected.AFQ software was used to analyze DTI data, track 20 white matter fiber bundles in the brain, and compare the differences of fractional anisotropy (FA) and mean diffusivity (MD) value of each bundle between groups.Each fiber bundle was divided into 100 equal parts along the direction of travel, and the FA or MD value of each part was taken as a characteristic.Screening the characteristics with statistic differences between groups for classification of AD and NC by support vector machine (SVM) with leave one method for cross validation.Classification effectiveness was evaluated using the receiver operating characteristic (ROC) curve.Results:Eleven (left/right anterior thalamic radiation (ATR), left/right corticospinal tract (CST), genu of corpus callosum (CC Genu), right inferior longitudinal fasciculus (ILF), right superior longitudinal fasciculus (SLF), left/right uncinated fasciculus (UF), and left/right arcuate fasciculus (AF)) of the 20 fiber bundles were successfully tracked in all subjects.Compared with NC group, the FA values of 2 fiber bundles (left/right UF) in AD group were significantly decreased(n t=-2.532, -2.391, both n P<0.05), and the MD values of 7 fiber bundles (left ATR, left/right CST, right ILF, left/right UF, and left AF) were significantly increased (n t=2.569, 2.411, 2.108, 2.357, 3.773, 3.796, 3.492, all n P<0.05). Among the 2 200 characteristics of 11 fiber bundles, 412 classification characteristics with inter-group differences were selected.Among which, 78 FA characteristics were distributed in 7 fiber bundles (left ATR, left/right CST, CC Genu, right ILF, left/right UF), and 334 MD characteristics were distributed in 9 fiber tracts (left/right ATR, left/right CST, CC Genu, right ILF, left/right UF, and left AF). The accuracy of SVM classification was 85.19%, sensitivity was 80.95%, specificity was 87.88%, and area under ROC curve was 0.894 7.n Conclusion:AFQ analysis based on DTI has a high application value in the diagnosis and prediction of AD.