Robust automated detection of microstructural white matter degeneration in Alzheimer's disease using machine learning classification of multicenter DTI data.
Robust automated detection of microstructural white matter degeneration in Alzheimer's disease using machine learning classification of multicenter DTI data.
复制标题
DOI：
10.1371/journal.pone.0064925
复制
发表时间：
2013
期刊：
影响因子：
3.7
通讯作者：
EDSD study group
中科院分区：
文献类型：
--
作者：
Dyrba M;Ewers M;Wegrzyn M;Kilimann I;Plant C;Oswald A;Meindl T;Pievani M;Bokde AL;Fellgiebel A;Filippi M;Hampel H;Klöppel S;Hauenstein K;Kirste T;Teipel SJ;EDSD study group
基于扩散张量成像（DTI）的白色纤维束完整性评估可以支持阿尔茨海默病（AD）的诊断。然而，使用DTI作为生物标志物取决于其在多中心环境中的适用性，以解释不同MRI扫描仪的影响。我们将多变量机器学习（ML）应用于最近创建的欧洲痴呆症DTI研究（EDSD）框架的大型多中心样本。我们假设ML方法可以修正多中心采集的效果。我们纳入了137例临床上可能患有AD的患者（MMSE 20.6 ± 5.3）和143名健康老年人对照，在9种不同的扫描仪中进行扫描。对于诊断分类，我们使用DTI指数各向异性分数（FA）和平均扩散率（MD），并进行比较，灰质和白色物质密度图从解剖MRI。使用支持向量机（SVM）和朴素贝叶斯（NB）分类器对数据进行分类。我们使用了两种交叉验证方法，（i）从整个数据集中随机抽取的测试和训练样本（合并交叉验证）和（ii）来自每个扫描仪的数据作为测试集，以及来自其余扫描仪的数据作为训练集（扫描仪特定交叉验证）。在合并交叉验证中，SVM对FA的准确率为80%，对MD的准确率为83%。NB的准确性明显较低，范围在68%至75%之间。去除扫描仪使用主成分分析产生的方差分量并没有显着改变两个分类器的分类结果。对于扫描仪特定的交叉验证，SVM和NB的分类精度都降低了。平均值校正后，分类准确性达到了一个水平，从合并交叉验证获得的结果。我们的研究结果支持这样一种观点，即机器学习分类允许对来自多个扫描仪的DTI数据集进行鲁棒分类，即使新的数据集来自不属于训练样本的扫描仪。
Diffusion tensor imaging (DTI) based assessment of white matter fiber tract integrity can support the diagnosis of Alzheimer’s disease (AD). The use of DTI as a biomarker, however, depends on its applicability in a multicenter setting accounting for effects of different MRI scanners. We applied multivariate machine learning (ML) to a large multicenter sample from the recently created framework of the European DTI study on Dementia (EDSD). We hypothesized that ML approaches may amend effects of multicenter acquisition. We included a sample of 137 patients with clinically probable AD (MMSE 20.6±5.3) and 143 healthy elderly controls, scanned in nine different scanners. For diagnostic classification we used the DTI indices fractional anisotropy (FA) and mean diffusivity (MD) and, for comparison, gray matter and white matter density maps from anatomical MRI. Data were classified using a Support Vector Machine (SVM) and a Naïve Bayes (NB) classifier. We used two cross-validation approaches, (i) test and training samples randomly drawn from the entire data set (pooled cross-validation) and (ii) data from each scanner as test set, and the data from the remaining scanners as training set (scanner-specific cross-validation). In the pooled cross-validation, SVM achieved an accuracy of 80% for FA and 83% for MD. Accuracies for NB were significantly lower, ranging between 68% and 75%. Removing variance components arising from scanners using principal component analysis did not significantly change the classification results for both classifiers. For the scanner-specific cross-validation, the classification accuracy was reduced for both SVM and NB. After mean correction, classification accuracy reached a level comparable to the results obtained from the pooled cross-validation. Our findings support the notion that machine learning classification allows robust classification of DTI data sets arising from multiple scanners, even if a new data set comes from a scanner that was not part of the training sample.
登录
查看更多内容
影响因子：
5.7
作者：
Gaser, C;Volz, HP;Sauer, H
通讯作者：
Sauer, H
影响因子：
4
作者：
Friese, Uwe;Meindl, Thomas;Teipel, Stefan J.
通讯作者：
Teipel, Stefan J.
影响因子：
2.5
作者：
Grana, M.;Termenon, M.;Besga, A.
通讯作者：
Besga, A.
影响因子：
4.2
作者：
Fellgiebel, A;Müller, MJ;Stoeter, P
通讯作者：
Stoeter, P
影响因子：
5.7
作者：
Abdulkadir, Ahmed;Mortamet, Benedicte;Vemuri, Prashanthi;Jack, Clifford R., Jr.;Krueger, Gunnar;Kloeppel, Stefan
通讯作者：
Kloeppel, Stefan