A Comprehensive Analysis on Neuro-Degenerative Disorders using Machine Learning Techniques

Abstract

A class of illnesses known as neurodegenerative diseases mainly impacts the brain and nervous system's structure and function over time. Deterioration of nerve cells, brought on by these diseases, leads to a loss of cognitive function, malfunction of the motor systems, and, in extreme situations, substantial difficulty with everyday tasks. Amyotrophic lateral sclerosis (ALS), Parkinson's disease, Alzheimer's disease, Retinal and Huntington's disease are among the most common neurodegenerative illnesses. Many variables, including heredity, the environment, and aging, contribute to the development of these illnesses. In this review, we look at automated retinal layer segmentation methods, discussing their uses and recent developments as they pertain to different types of neurodegenerative diseases. With the increasing frequency of these ailments, non-invasive imaging techniques, especially those that target the retina, are vital for the early identification and tracking of these conditions. Automatic retinal layer segmentation in various neurodegenerative situations is covered in this review, along with state-of-the-art algorithms, techniques, and technology. This survey paper reviews 42 research papers for neurodegenerative disorders detection and explores the potential of computer-assisted methods for neurodegenerative disorders and staging. The survey's goal is to shed light on the present state of this dynamic area by analyzing it thoroughly and drawing attention to noteworthy developments, obstacles, and possible future research directions. Contributing to the continuous efforts to improve diagnosis accuracy and patient care for neurodegenerative diseases, the collected data helps provide light on the strengths and weaknesses of current automated segmentation methods.