Parkinson's Disease (PD) is a progressive neurological disorder that develops through several stages, including suggestive symptoms, stage 1, stage 2, and stage 3. Identifying the severity of PD and predicting its progression can be challenging due to the limitations of medical settings. Consequently, there is a need for novel techniques to facilitate early-stage classification of PD, potentially addressing the financial and time constraints associated with determining disease stages. Recent research has focused on employing supervised and unsupervised machine learning algorithms for the reliable diagnosis of PD, stage identification, and trajectory prediction using clinical and preclinical data. The diagnosis of PD may be improved by incorporating various techniques, including deep learning and machine learning approaches. This study proposes a Deep Convolutional Neural Networks (DCNN) approach based on MRI data to enhance the accuracy of PD classification. The paper presents several key contributions. Initially, a DCNN model was developed to classify Parkinson's Disease. Subsequently, the main objective was to identify the network topology that yielded optimal accuracy and recall. To achieve this, various network structures were examined, and several topological variants were determined. The proposed model was trained using features from the Parkinson's Progression Markers Initiative (PPMI) database, achieving an accuracy of 95% for the PPMI data. The results obtained through applying the proposed model on the PPMI datasets demonstrate its superior performance compared to traditional methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.