Published Paper Details:

Parkinson's disease (PD) is one of the more common neurodegenerative disorders, with two stages of progression: normal and severe. With all of the shortcomings in clinical settings, identifying the stage of PD severity and predicting its progression course can be difficult. As a result, it appears that there is an increasing need to use supervised and unsupervised artificial intelligence and machine learning methods on clinical and paraclinical datasets to accurately diagnose Parkinson's disease, identify its stage, and predict its course. MRI-related data are regarded as useful in detecting various pathologies in the brain in today's neuro-medicine practises. Furthermore, the field has recently seen an increase in the use of deep learning methods in image processing, often with excellent results. In this study, we used Artificial Neural Networks (ANN) to develop a model for distinguishing different stages of Parkinson's disease. The results demonstrated that our current MRI-based CNN model could potentially be used as a suitable method for distinguishing PD stages with a high accuracy rate.