MR Brain Screening using Optimization Techniques - A Survey

Alzheimer's disease (AD) is associated with Dementia, and it is also a memory syndrome in the brain. It affects the brain tissues and causes major changes in day-to-day activities. Aging is a major cause of Alzheimer's disease. AD is characterized by two pathological hallmarks, Amyloid β protein and neurofibrillary tangles of hyperphosphorylated tau protein. The imaging hallmarks for Alzheimer's disease are swelling, shrinkage of brain tissues due to cell loss, and atrophy in the brain due to protein dissemination. Based on the survey, 60% to 80% of dementia patients belong to Alzheimer's disease.

AD is now becoming an important brain disease. The goal of AD pathology is to cause changes/damage in brain tissues. Alzheimer's disease is thought to begin 20 years or more before symptoms appear, with tiny changes in the brain that are undetectable to the person affected. The changes in a person's brain after a few years are noticeable through symptoms such as language difficulties and memory loss. Neurons in different parts of the brain have detected symptoms such as cognitive impairments and learning disabilities. In this case, neuroimaging tools are necessary to identify the development of pathology which relates to the clinical symptoms.

Several approaches have been tried during the last two decades for brain screening to analyse AD using pre-processing, segmentation, and classification. Different individuals, such as Grey Wolf optimization, Lion Optimization, Ant Lion Optimization, etc., have been attempted in the proposed study. Similarly, hybrid optimization techniques are also attempted to segment the brain sub-regions, which helps in identifying the biomarkers to analyse AD.

This study discusses a review of neuroimaging technologies for diagnosing Alzheimer's disease, as well as the discovery of hallmarks for the disease and the methodologies for finding hallmarks from brain images to evaluate AD. According to the literature review, most of the techniques predicted higher accuracy (more than 90%), which is beneficial for assessing and screening neurodegenerative disease, particularly Alzheimer's disease.