Recent advancements in deep learning (DL) have made possible new methodologies for analyzing massive datasets with intriguing implications in healthcare. Convolutional neural networks (CNN), which have proven to be successful supervised algorithms for classifying imaging data, are of particular interest in the neuroscience community for their utility in the classification of Alzheimer’s disease (AD). AD is the leading cause of dementia in the aging population. There remains a critical unmet need for early detection of AD pathogenesis based on non-invasive neuroimaging techniques, such as magnetic resonance imaging (MRI) and positron emission tomography (PET). In this comprehensive review, we explore potential interdisciplinary approaches for early detection and provide insight into recent advances on AD classification using 3D CNN architectures for multi-modal PET/MRI data. We also consider the application of generative adversarial networks (GANs) to overcome pitfalls associated with limited data. Finally, we discuss increasing the robustness of CNNs by combining them with ensemble learning (EL).

Amyotrophic Lateral Sclerosis (ALS) is a complex polygenetic neurodegenerative disorder. Establishing a diagnosis for ALS is a challenging and lengthy process. By the time a diagnosis is made, the lifespan prognosis is only about two to 5 years. Genetic testing can be critical in assessing a patient’s risk for ALS, provided they have one of the known familial genes. However, the vast majority of ALS cases are sporadic and have no known associated genetic signatures. Our analysis of the whole genome sequencing data from ALS patients and healthy controls from the Answer ALS Consortium has uncovered twenty-three novel mutations in twenty-two protein-coding genes associated with sporadic ALS cases. The results show the majority of patients with the sporadic form of ALS have at least one or more mutation(s) in the 22 genes we have identified with probabilities of developing ALS ranging from 25–99%, depending on the number of mutations a patient has among the identified genes. Moreover, we have identified a subset of the ALS cohort that has >17 mutations in the 22 identified. In this case, a patient with this mutation profile has a 99% chance of developing ALS and could be classified as being at high risk for the disease. These genetic biomarkers can be used as an early ALS disease diagnostic tool with a rapid and non-invasive technique.