Parkinson’s Disease Detection using YOLO Algorithm

Parkinson's disease (PD) is a progressive neurodegenerative disorder characterized by motor and non- motor symptoms, which significantly impact patients' quality of life. Early and accurate diagnosis is important for effective management and treatment planning. Recent advancements in deep learning techniques, particularly with the You Only Look Once (YOLO) algorithm, have shown promise in enhancing medical imaging analysis and automated diagnosis. This study explores the use of YOLO, a real-time object detection algorithm, for identifying Parkinson’s disease-related abnormalities in medical images such as MRI and PET scans. The YOLO framework is modified and trained to detect specific biomarkers and structural changes associated with PD in imaging data, which allows for rapid and accurate identification of disease patterns. Results demonstrate that YOLO’s high-speed detection and localization capabilities make it suitable for processing large volumes of medical data, offering an efficient and cost- effective solution for PD screening. This application of YOLO in PD detection may improve early diagnosis, aid in monitoring disease progression, and support the development of individualized treatment strategies. Further research is needed to refine the model for greater accuracy and clinical applicability across diverse patient populations. Keywords—YOLO, F1 Score, Parkinson’s Disease, Convolutional Neural Networks, Neurodegenerative disorder, Parkinson's Progression Markers Initiative (PPMI).