3D Convolutional Neural Networks for Diagnosis of Alzheimer’s Disease via structural MRI

Alzheimer’s Disease (AD) is a widespread neurodegenerative disease caused by structural changes in the brain and leads to deterioration of cognitive functions. Patients usually experience diagnostic symptoms at later stages after irreversible neural damage occurs. Early detection of AD is crucial in maximizing patients' quality of life and to start treatments to decelerate the progress of the disease. Early detection may be possible via computer-assisted systems using neuroimaging data. Among all, deep learning utilizing magnetic resonance imaging (MRI) have become a prominent tool due to its capability to extract high-level features through local connectivity, weight sharing, and spatial invariance. This paper describes our investigation of the classification accuracy based on two publicly available data sets, namely, ADNI and OASIS, by building a 3D VGG variant convolutional network (CNN). We used 3D models to avoid information loss, which occurs during the process of slicing 3D MRI into 2D images and analyzing them by 2D convolutional filters. We also conducted a pre-processing of the data to enhance the effectiveness and classification performance of the model. The proposed model achieved 73.4% classification accuracy on ADNI and 69.9% on OASIS dataset with 5-fold cross-validation (CV). These results are comparable to other studies using various convolutional models. However, our subject-based divided dataset has only one MRI of a single patient to prevent possible data leakage whereas some other studies have different screenings of the same patients "over a time period'" in their datasets.