Predicting MCI to AD Conversation Using Integrated sMRI and rs-fMRI: Machine Learning and Graph Theory Approach

Abstract

Background: Graph theory and machine learning have been shown to be effective ways of classifying different stages of Alzheimer's disease (AD). Most previous studies have only focused on inter-subject classification with single-mode neuroimaging data. However, whether this classification can truly reflect the changes in the structure and function of the brain region in disease progression remains unverified. In the current study, we aimed to evaluate the classification framework, which combines structural Magnetic Resonance Imaging (sMRI) and resting-state functional Magnetic Resonance Imaging (rs-fMRI) metrics, to distinguish mild cognitive impairment non-converters (MCInc)/AD from MCI converters (MCIc) by using graph theory and machine learning.

Methods: With the intra-subject (MCInc vs. MCIc) and inter-subject (MCIc vs. AD) design, we employed cortical thickness features, structural brain network features, and sub-frequency (full-band, slow-4, slow-5) functional brain network features for classification. Three feature selection methods [random subset feature selection algorithm (RSFS), minimal redundancy maximal relevance (mRMR), and sparse linear regression feature selection algorithm based on stationary selection (SS-LR)] were used respectively to select discriminative features in the iterative combinations of MRI and network measures. Then support vector machine (SVM) classifier with nested cross-validation was employed for classification. We also compared the performance of multiple classifiers (Random Forest, K-nearest neighbor, Adaboost, SVM) and verified the reliability of our results by upsampling.

Results: We found that in the classifications of MCIc vs. MCInc, and MCIc vs. AD, the proposed RSFS algorithm achieved the best accuracies (84.71, 89.80%) than the other algorithms. And the high-sensitivity brain regions found with the two classification groups were inconsistent. Specifically, in MCIc vs. MCInc, the high-sensitivity brain regions associated with both structural and functional features included frontal, temporal, caudate, entorhinal, parahippocampal, and calcarine fissure and surrounding cortex. While in MCIc vs. AD, the high-sensitivity brain regions associated only with functional features included frontal, temporal, thalamus, olfactory, and angular.

Conclusions: These results suggest that our proposed method could effectively predict the conversion of MCI to AD, and the inconsistency of specific brain regions provides a novel insight for clinical AD diagnosis.

Keywords: classification; graph theoretical analysis; machine learning; mild cognitive impairment; resting-state fMRI; structural MRI.

FIGURE 1

The overall classification framework for predicting the conversion of MCI. (A) Structural feature extraction: preprocessing T1 data, extract MRI features and thickness network features. (B) Functional feature extraction: preprocessing rs-fMRI data, constructing resting-state functional brain network and extracting features. (C) Feature selection and Classification.

FIGURE 2

ROC curves of the three algorithms performed SVM classifier using the top 10 features. (A) MCInc vs. MCIc group at cost = 39%, (B) MCIc vs. AD group at cost = 39%. (C) MCInc vs. MCIc group at cost = 19%, (D) MCIc vs. AD group at cost = 19%.

FIGURE 3

Comparison of AUC scores of three algorithms performed SVM classifier. Subgraphs (A) and (B) represent AUC scores with the number of features K of MCInc vs. MCIc, and MCIc vs. AD. ○ Indicate the classification performance of the RSFS algorithm and SS-LR algorithm is significantly different. Indicate the classification performance of the RSFS algorithm and mRMR algorithm is significantly different. □ Indicate the classification performance of the mRMR algorithm and SS-LR algorithm is significantly different.

FIGURE 4

The location and networks attribution of top 10 brain regions, listed in Tables 6 (A), 7 (B), which might be affected in early stage of MCI.