An MRI-based deep learning approach for accurate detection of Alzheimer's disease

Alzheimer's disease (AD) is the most prevalent type of dementia of the nervous system that causes many brain functions to weaken (eg, memory loss). Non-invasive early diagnosis of AD has attracted a lot of research attention nowadays as early diagnosis is the most important factor in improving patient care and treatment results. This research develops a deep learning-based pipeline for accurate diagnosis and stratification of AD stages. The proposed analysis pipeline utilizes shallow Convolutional Neural Network (CNN) architecture and 2D T1-weighted Magnetic Resonance (MR) brain images. The proposed pipeline not only introduces a fast and accurate AD diagnosis module but also provides a global classification (i.e., normal vs. Mild Cognitive Impairment (MCI) vs. AD) as well as local classification. The latter deals with an even more challenging task to stratify MCI into a Very Mild Dementia (VMD), mild dementia (MD), and Moderate Dementia (MoD) as the prodromal AD stage. In addition, we compare our approach to cutting-edge deep learning architectures, e.g., DenseNet121, ResNet50, VGG 16, EfficientNetB7, and InceptionV3. The reported results documented the high accuracy and the suggested method's resilience, as evidenced by the overall testing accuracy of 99.68%. (c) 2022 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engineering, Alexandria University. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).