Optimizing Parkinson's disease Classification in MRI Scans Using a Modified ResNet50 Architecture

Abstract

The PD’s (Parkinson’s disease) is considered as the advanced neurodegenerative disorder which affects the movements as the dopamine producing neurons in the substantia nigra location present in the brain gets reduced. Since, the accurate basis of PD is the mixture of genetic and environmental factors, the PD results in the motor-related symptoms. However, the earlier detection is significant for the management of indications and slow growth, the diagnosis is difficult because of the identical with several neurodegenerative situations. The conventional techniques includes the clinical assessments, patients’ profiles and the MRI, SPECT and PET scans. Since, the MRI’s focus on the structural differences restricts the efficiency in the earlier phase of PD detection. Therefore, the ML and DL models are utilized in the classification of MRI scan images, as they face issues in the computations of features through several medical images and classification. Despite the enhancements, several difficulties such as restricted, labeled and noisy datasets. Hence, the study proposes a modified ResNet50 with CSAM (Channel Specific Attention Module) for the detection of PD in MRI scans with the utilization of PPMI and NTUA Parkinson’s Disease dataset. In contrast to the existing models, the proposed Modified ResNet50 with Channel-Specific Attention Module (CSAM) achieves high performance and early detection. The proposed Modified ResNet50 with Channel-Specific Attention Module (CSAM) is evaluated using the performance metrics such as accuracy, precision, recall, and F1 score in which the proposed model obtains higher metrics values.