A Brief Review on EEG-based Diagnosis of Parkinson's Disease using Deep Learning Models

It is obvious that early and precise detection of Parkinson's disease (PD) is crucial to avoid the progress in this neurodevelopmental brain disease. To assess PD diagnosis quantitatively, there is a growing interest in PD detection by analyzing electroencephalogram (EEG) signals using neural deep learning methods. In this study, a short review over the methods which have been used in PD diagnosis either in end-to-end approaches (e.g., deep neural network structures) or extracting informative time-frequency features from EEG signals and then apply these feature images to deep learning methods. This review addresses the challenges and offer new solutions to overcome them.