Project Team


Students

Saatvik Pradhan
Computer Science
Penn State University Park






Faculty Mentors

Sayed Mohsin Reza
Penn State Harrisburg
Department of Computer Science










Project




https://sites.psu.edu/mcreu/files/formidable/2/2024-07-23/MCREU_Poster_Saatvik_Pradhan.pdf



Project Video




video player icon




Project Abstract


Parkinson’s Disease (PD) remains a challenging neurodegenerative disorder to diagnose early, primarily due to the subtlety and variability of early symptoms. Existing diagnostic methods often fail to detect the disease until significant neurological damage has occurred. This study addresses the critical gap in early detection of PD by leveraging advanced machine learning (ML) algorithms to classify MRI scans into four distinct groups: PD, Control, SWEDD, and Prodromal. Utilizing data from the Parkinson’s Progression Markers Initiative (PPMI), MRI scans were preprocessed to ensure consistent alignment and normalization. Three ML models—Support Vector Machine (SVM), Random Forest (RF), and Convolutional Neural Network (CNN) with VGG16 architecture—were trained and evaluated. The Random Forest model achieved the highest accuracy in both binary and multiclass classifications, highlighting its robustness for this task. SVM also demonstrated strong performance, particularly in identifying patient’s with parkinson’s disease from the healthy controls. The CNN model showed potential, though it requires further optimization. These findings underscore the importance of model selection and optimization in medical imaging tasks. Future work will focus on enhancing the CNN model through data augmentation and transfer learning, as well as exploring the integration of Cryo-Electron Microscopy data to improve early detection methods for Parkinson’s Disease.




Evaluate this Project


Use this form link to provide feedback to the presenters, and add your project evaluation for award(s) consideration.