Automated Classification of Alzheimer’s Disease and Mild Cognitive Impairment using Deep Neural Networks

Alzheimer’s Disease (AD) is a severe irreversible neurodegenerative disease that has great sufferings on patients and eventually leads to death [1]. Mild cognitive impairment (MCI) is an early stage that AD patients go through. AD destroys brain cells, causing people to lose their memory, mental functions and ability to continue daily activities. It is a severe neurological brain disorder which is not curable, but earlier detection of AD can help for proper treatment and prevent brain tissue damage [39]. Until now, the cause of AD is still unknown. Moreover, doctors can hardly make use of medical images such as Magnetic Resonance Imaging (MRI) for AD clinical diagnosis as there are overlaps in what doctors consider normal age-related changes in the brain and abnormal changes [19].

Recently, Deep Learning (DL) methods have become an attractive and fundamental element of computer-aided analytical techniques and have been widely employed for the automated diagnosis and analysis of neuropsychiatric disorders [64]. In this thesis, we have proposed Spatial-temporal Combined Feature Extraction models for MRI-based automated AD diagnosis. Our models have been trained and evaluated using MRI data from the Open Access Series of Imaging Studies (OASIS)-1 dataset and we have achieved competitive and promising results.