Deep learning for diagnosing Alzheimer disease through the analysis of MRI (#670)

Authors

Acevedo, Elena

Orantes, Dinora

Acevedo, Marco

Abstract

Alzheimer's disease is a progressive brain disorder that affects memory, reasoning ability, and, eventually, the ability to perform simple daily tasks. People diagnosed with this dementia have a life expectancy of up to twenty years from diagnosis. A deep learning-based approach is presented for the classification and diagnosis of Alzheimer's disease using magnetic resonance imaging (MRI) scans. The dataset was obtained from the Kaggle platform, and the metrics of accuracy, recall, and F1 score were applied. Each of these metrics showed a percentage close to 100%, resulting in an average accuracy of 99.52%.