Classification of subjects of Mild Cognitive Impairment and Alzheimer’s Disease through Neuroimaging modalities and Convolutional Neural Networks

Alzheimer's Disease (AD) is an irreversible neurodegenerative disorder that is affecting the elderly population worldwide. The staggering costs associated with this disease merits further research in the diagnosis and prognosis of this disease. Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) are widely used modalities to capture the structural changes in the brain caused by AD in its early stages. Early diagnosis of AD is important from clinical perspective to improve the life of an individual who is at the risk of developing memory deficits. Deep learning architectures such as 2D and 3D Convolutional Neural Networks (CNNs) have shown promising performances in extracting features and building useful representations of data for computer vision tasks. This study is geared towards understanding the performance differences between these architectures. We used transfer and non-transfer learning approaches to study the underlying disease phenomenon. In our experiments on binary classification of early stages of AD, we found the performance of 3D architectures to be better in comparison to their 2D counterparts. For instance, the 3D-CNN architecture which is trained on PET modality data achieved an accuracy of 71.728%, specificity of 73.196%, and sensitivity of 70.213% on the AD class while its 2D-CNN counterpart achieved an accuracy of 56.901%, specificity of 59.764%, and sensitivity of 53.947% on the same class. Further, we found the performance of 3D architecture trained on PET neuroimaging modality data to be the best in terms of performance metrics which shows superior diagnostic power of this type of architecture.