Automated Parkinson’s Disease Detection from Brain MRI Images Using Deep Convolutional Neural Network

Parkinson’s disease (PD) is a neurodegenerative disorder characterized by motor impairments and cognitive deficits. Early and accurate detection of PD plays a crucial role in improving patient outcomes and tailoring personalized treatment plans. This study proposes a novel approach for detecting Parkinson’s disease from brain MRI images using Convolutional Neural Networks (CNNs). We used the EfficientNetB7 model, a transfer learning-based CNN, which demonstrated outstanding results in the binary classification of Parkinson’s disease. The dataset comprised 210 brain MRI images from PD patients and 600 images from healthy controls. A preprocessing pipeline is applied to standardize the images and extract relevant regions of interest, enhancing model training robustness. After training and evaluation, the CNN achieved an average accuracy of 99%, indicating its remarkable ability. The findings suggest that this automated and data-driven approach could be a valuable tool in clinical settings, aiding timely and accurate diagnoses and improving the quality of care and outcomes for PD patients.