Abstract: Recent decade, Parkinson's disease (PD), which impairs the life quality for millions of older people worldwide, has quickly emerged serious condition affecting the brain and spinal cord. Appropriate treatment and management of the disease depend on early discover y and an accurate diagnosis. Due to PD's close resemblance to other neurological disorders, the precise diagnosis of PD has until now bee a difficult. These same characteristics account for 25% of incorrect manual PD diagnosis. Brain MRI (Magnetic Resonance Imaging) has shown great potential in the detection and diagnosis of Parkinson's disease. Proposed study uses convolutional neural networks (CNN), a type of deep neural network architecture, to classify Parkinson disease in order to differentiate between PD patients and healthy controls. Parkinson Progression Markers Initiati ve (PPMI)dataset is used as input to classify the disease. Here, the median filtering technique is used to remove the noise from the images and preser ve the edges which help to provide a better image and able to predict it easily. The Parkinson disease recognition system is done by using CNN. Accuracy, sensitivity, s pecificity, and AUC (Area Under Curve) used to assess the performance of the suggested approach.
Keywords: Parkinson, MRI (Magnetic Imaging), Convolutional Neural Networks (CNN), AUC (Area Under Curve).
|
DOI:
10.17148/IJARCCE.2024.134225
