A Study on Computer Aided Neurological Disorder Detection and Classification from fMRI Data

Machine Learning (ML) systems, particularly analytical modelling and medical imaging have emerged over the years as one of the key techniques aiding researchers in developing algorithms for resolving challenging diagnostic issues. Deep Learning (DL) is a sophisticated approach that consider higher level of features for categorization. In neuro-developmental and mental disorders, Attention Deficit Hyperactivity Disorder (ADHD) is categorized as complex issue. Since ADHD cannot be directly diagnosed using a common medical test at the early stages of the disease, researchers have characterized it as a multilayered problem over time. In addition to their physical manifestations, the majority of ADHD patients, according to clinical data, experience academic difficulties. As a result, it is believed that functional Magnetic Resonance Imaging (fMRI) is the best technique for identifying functional activities in various region of brain. Similarly, fMRI can be utilized to comprehend Parkinson's, Alzheimer's, and other brain related abnormalities. By utilizing DL methods, it is possible to improve the accuracy of identifying neurological disorders with fMRI dataset. This study analyzes the available research on DL and ML models for diagnosing neurological diseases. It is anticipated that, the evaluation serves as a catalyst for additional research on different methods for neuro disease diagnosis and monitoring.