An early-stage Alzheimer's disease detection using various imaging modalities and techniques – A mini-review

Abstract

Alzheimer's is a disease that affects the brain parts and leads the cells of the brain to die. It is a permanent disorder that causes danger in memory and loss the responsiveness related to the environment. The brain network plays a significant part in the identification of (Alzheimer's Disease) AD and (Mild Cognitive Impairment) MCI disorders. Since the Alzheimer's Association cautioned that Alzheimer’s disease will affect 1 in 85 people by 2050, it is highly essential to have a role play to get a faster diagnosis and a prognosis. The biomarker used to diagnose the disease for distinguishing across various dementia causes needs early detection. Machine learning (ML) uses a variety of techniques to allow (Normal Controls) NCs to benefit from high dimensional data sets. This paper presents a study in early-stage identification or classification of AD using different transferred ML techniques with different modalities and their critical assessment and analysis.