Artificial intelligence-based Diagnostic Approaches for Alzheimer's Disease Using Medical Imaging

Alzheimer's disease (AD) is a neurodegenerative disorder that causes memory problems as people age. Symptoms worsen over time, ultimately disrupting the patient's daily life. AD is characterized by the accumulation of amyloid-beta proteins and tau fibers in various brain regions, which can be detected through cerebrospinal fluid (CSF) testing. Neuroimaging, especially high-resolution MRI, offers a noninvasive way to examine brain structure and function, aiding early diagnosis. With increasing data availability, artificial intelligence (AI) plays a crucial role in processing and classifying medical images into AD and control groups. Many studies have used AI models with different imaging modalities such as MRI (Magnetic Resonance Imaging), PET (Positron Emission Tomography), and fMRI (Functional Magnetic Resonance Imaging). Machine learning algorithms, process extracted features like volumetric data from affected brain regions such as the medial temporal lobe and hippocampus, which are heavily impacted in AD. Support Vector Machine (SVM) remains a popular classifier in this context. Recently, deep learning models, especially Convolutional Neural Networks (CNN), show promising results in distinguishing AD patients from mild cognitive impairment (MCI) and healthy individuals. This review explores the application of AI in AD diagnosis, highlighting its effectiveness and the challenges faced.

Keywords:

alzheimer disease , artificial intelligence , machine learning , deep learning , magnetic resonance imaging