Enhanced Early Parkinson's Disease Detection Using Resnet-101 Based On MRI Images

Early recognition of this indicated disease is thought to be determining in preventing the course and giving patients an opportunity for disease-modifying therapy. One of the best chances for such identification comes with the premotor phase when mild signs can signal the onset of the disease. Classic methods have applied the SVM algorithm in anticipating PD onset; still, they are very restrictive in their ability in image data processing. This is a major setback since image data, i.e., MRI scans or other medical imaging, are very important in coming up with precise diagnoses. In an attempt to overcome this weakness, we apply the ResNet-101 deep learning algorithm. ResNet-101 is highly effective due to its nature as a CNN, which is a great network for image processing since its deep structure has 101 layers. This level of depth ensures that it can recognize intricate patterns and features from medical images, greatly enhancing prediction accuracy compared to SVM. We will make it possible for early diagnosis of PD by image data, which also means diagnosis at a premotor stage with much higher precision using ResNet-101. This solution increases the accuracy in predictions but also creates a strong tool for the early diagnosis by the clinicians so that interventions may be provided at a timely and potentially life-altering point. The suggested results are improved and outperformed well compared to the current methods. This work enhances prediction accuracy 96.0%, Sensitivity 97.5%, Specificity 96.8%, Precision 94.5%, F1-Score 92.7%, ROC-AUC 98.0%.