Exploring the Efficacy of CNN Models of Diagnostic Modalities for Parkinson’s Disease

Parkinson’s disease is a neurodegenerative condition that results in both motor and non-motor symptoms due to the death of dopaminergic neurons in the brain. Effective illness management and therapy depend on an early and precise diagnosis. The study evaluated various imaging modalities, including deep learning-based magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and single-photon emission computed tomography dopamine transporter (SPECT DAT) scans. To determine the best way to diagnose PD. These imaging techniques were analyzed using convolutional neural networks (CNNs), and significant differences were found in their diagnostic accuracies. The CNN model revealed that fMRI had an accuracy of up to 95%, outperforming MRI and SPECT DAT, which had 89.3% and 83.5% accuracy, respectively. As the most dependable method for an early and precise diagnosis of Parkinson’s disease, these results demonstrate the potential for fMRI to be a significant part of clinical practice.