Robust multitask feature learning for amnestic mild cognitive impairment diagnosis based on multidimensional surface measures

Abstract

Previous studies have shown that amnestic mild cognitive impairment (aMCI) involves in the morphological abnormalities of multiple regions, including cortical thickness, sulcus depth, surface area, gray matter volume, jacobian metric and average curvature. All the measures have unique neuropathological and genetic meanings. However, most existing methods simply average or concatenate these measures when constructing the classifiers, which may include redundant information and ignore the relationships among them. In this study, we treat each measure as a task in our multitask learning framework. Considering the actual situation that we do not know the correlation between tasks in advance, we use a robust multitask feature learning (rMTFL) method to select a group of features among correlated measures and provide additional information by identifying outlier tasks at the same time. Then, we train several SVM classifiers and for each measure, we input the selected features into the corresponding SVM classifier. Finally, we use an ensemble classification strategy to combine the results of these classifiers based on the accuracy to make the final prediction. We use the leave-one-out cross-validation to evaluate our proposed method with 46 amnestic mild cognitive impairment (aMCI) and 52 normal controls (NC). The results show that rMTFL algorithm is superior to the group lasso method and average curvature is the outlier task based on multidimensional surface measures.

Keywords

• aMCI
• Ensemble classification
• Feature selection
• Multitask learning
• Outlier measurement detection