Adaptive 3DCNN-Based Interpretable Ensemble Model for Early Diagnosis of Alzheimer's Disease

An adaptive interpretable ensemble model based on a 3-D convolutional neural network (3DCNN) and genetic algorithm (GA), i.e., 3DCNN+EL+GA, was proposed to differentiate the subjects with Alzheimer's disease (AD) or mild cognitive impairment (MCI) and also identify the discriminative brain regions significantly contributing to the classifications in a data-driven way. The testing results on the datasets from both the AD Neuroimaging Initiative (ADNI) and the Open Access Series of Imaging Studies (OASIS) indicated that 3DCNN+EL+GA outperformed other state-of-the-art deep learning algorithms. More importantly, in these identified brain regions, the discriminative brain subregions at a voxel level were further located with a gradient-based attribution method designed for CNN and illustrated intuitively. Besides these, the behavioral domains corresponding to every identified discriminative brain region (e.g., the rostral hippocampus) were analyzed. It was shown that the resultant behavioral domains were consistent with those brain functions (e.g., emotion) impaired early in the AD process. Further research is needed to examine the generalizability of the proposed ideas and methods in identifying discriminative brain regions and subregions for the diagnosis of other brain disorders (especially little-known ones), such as Parkinson's disease, epilepsy, severe depression, autism, Huntington's disease, multiple sclerosis, and amyotrophic lateral sclerosis, using neuroimaging.