Deep learning methods to detect Alzheimer's disease from MRI: A systematic review

Abstract

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative condi tion in the brain that affects memory, thinking, and behaviour. To overcome this problem, which according to the World Health Organization, is on the rise, creating strategies is essential to identify and predict the disease in its early stages before clin ical manifestation. In addition to cognitive and mental tests, neuroimaging is promis ing in this field, especially in assessing brain matter loss. Therefore, computer-aided diagnosis systems have been imposed as fundamental tools to help imaging techni cians as the diagnosis becomes less subjective and time-consuming. Thus, machine learning and deep learning (DL) techniques have come into play. In recent years, arti cles addressing the topic of Alzheimer's diagnosis through DL models are increasingly popular, with an exponential increase from year to year with increasingly higher accu racy values. However, the disease classification remains a challenging and pro gressing issue, not only in distinguishing between healthy controls and AD patients but mainly in differentiating intermediate stages such as mild cognitive impairment. Therefore, there is a need to develop more valuable and innovative techniques. This article presents an up-to-date systematic review of deep models to detect AD and its intermediate phase by evaluating magnetic resonance images. The DL models chosen by different authors are analysed, as well as their approaches regarding the used dataset and the data pre-processing and analysis techniques.