RESUMO
Alzheimer's Disease (AD) is an irreversible neurodegenerative disease that results in a progressive decline in cognitive abilities. Since AD starts several years before the onset of the symptoms, its early detection is challenging due to subtle changes in biomarkers mainly detectable in different neuroimaging modalities. Developing computer-aided diagnostic models based on deep learning can provide excellent opportunities for the analysis of different neuroimage modalities along with other non-image biomarkers. In this survey, we perform a comparative analysis of about 100 published papers since 2019 that employ basic deep architectures such as CNN, RNN, and generative models for AD diagnosis. Moreover, about 60 papers that have applied a trending topic or architecture for AD are investigated. Explainable models, normalizing flows, graph-based deep architectures, self-supervised learning, and attention mechanisms are considered. The main challenges in this body of literature have been categorized and explained from data-related, methodology-related, and clinical adoption aspects. We conclude our paper by addressing some future perspectives and providing recommendations to conduct further studies for AD diagnosis.
