Automatic Recognition of Mild Cognitive Impairment and Alzheimers Disease Using Ensemble based 3D Densely Connected Convolutional Networks

Automatic diagnosis of Alzheimers disease (AD) and mild cognition impairment (MCI) from 3D brain magnetic resonance (MR) images plays an important role in early treatment of dementia disease. Deep learning architectures can extract potential features of dementia disease and capture brain anatomical changes from MRI scans. This paper proposes an ensemble of 3D densely connected convolutional networks (3D-DenseNets) for AD and MCI diagnosis. First, dense connections were introduced to maximize the information flow, where each layer connects with all subsequent layers directly. Then weighted-based fusion method was employed to combine 3D-DenseNets with different architectures. Extensive experiments were conducted to analyze the performance of 3D-DenseNet with different hyper-parameters and architectures. Superior performance of the proposed model was demonstrated on ADNI dataset including 833 subjects.