Analysis of Brain Images for Detection and Classification of Disorders using Deep Learning Models

Abstract

Significant advances have been made in the field of deep learning and neuroimaging for the detection of neurological disorders and diseases. Non-invasive imaging modalities, such as functional magnetic resonance imaging (fMRI) and magnetic resonance imaging (MRI), make it easier to determine the composition and operations of the brain. Analytical evaluation of neuroimaging data can be beneficial not only in boosting the efficacy of diagnosing neuronal disorders but also in revealing the complexities of the brain when using deep learning techniques. This thesis aims to provide a theoretical and experimental foundation for the classification of brain disorders and brain activity of the datasets fMRI and MRI, including deep learning models, deep learning visualization approaches, data encoding fMRI, and feature extraction.