Robust Automated Detection of Microstructural White Matter Degeneration in Alzheimer’s Disease Using Machine Learning Classification of Multicenter DTI Data

Abstract

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.

On the early diagnosis of Alzheimer's Disease from multimodal signals: A survey

“…Specifically, 96.3% accuracy was achieved with the combination method, compared to 88.89% accuracy using DTI alone and 70.37% using fMRI alone. Dyrba et al [174] created a diagnosis methodology for AD emphasizing in its real future application and taking into account the variability that can be found in DTI images taken with different MRI scanners. For that, they made use of DTI taken from 9 different scanners and created a methodology to distinguish AD from control subjects.…”

Measuring Cortical Connectivity in Alzheimer’s Disease as a Brain Neural Network Pathology: Toward Clinical Applications

“…Nevertheless, some studies demonstrated acceptable diagnostic potential of resting-state functional connectivity maps. For example, independently from each other Dyrba and colleagues and Wee and colleagues demonstrated that pattern classification of individual functional connectivity matrices of whole brain connectivity separates patients with AD or MCI from healthy controls with accuracy and specificity rates of approximately 70% (Dyrba, Grothe, Kirste, & Teipel, 2015;Wee et al, 2012). However, both studies also found that combining functional und structural connectivity (based on DTI data) substantially increases these rates above 90%, suggesting that multimodal connectivity measures might help in future diagnostic approaches.…”

Perspective on future role of biological markers in clinical therapy trials of Alzheimer's disease: A long-range point of view beyond 2020

“…Longitudinal evaluation of these pattern of atrophy has begun to be used in phase IIa type clinical trials [155]. In addition, multivariate approaches such as machine learning with support vector machines have successfully been employed to derive patterns of brain atrophy that discriminate AD patients from healthy controls and MCI converters from MCI-stable subjects [156][157][158]. By highlighting specific topographical patterns of atrophy, these approaches have the potential to be useful to discriminate between different types of dementia [158].…”