Citation

T., Gayathri Devi and A., Srinivasan and S., Sudha and Anuar, Khairil (2024) Enhanced Parkinson's Disease Detection Using Neural Brain Image. In: 2024 Multimedia University Engineering Conference (MECON), 23-25 July 2024, Cyberjaya, Malaysia.

Text Enhanced Parkinson's Disease Detection Using Neural Brain Image.pdf - Published Version Restricted to Repository staff only Download (586kB)

Abstract

A brain disorder called Parkinson's disease (PD) is fairly frequent and damages cells that produce dopamine. Doctors can typically diagnose it by looking at movement problems and a patient's medical history. However, these traditional methods rely on interpreting subtle movements, which can be subjective and prone to error. This paper explores the application of deep learning for improved Parkinson's disease (PD) diagnosis using magnetic resonance imaging (MRI). This work proposes a novel method employing pretrained convolutional neural networks (CNNs) - ResNet50 and VGG16 - alongside image resizing and Stochastic Gradient Descent with Momentum (SGDM) optimization. The models were trained and evaluated on an MRI dataset encompassing PD patients and healthy controls. The proposed method achieved outstanding accuracy in classifying Parkinson's disease. Notably, ResNet50 achieved 95.06% accuracy, while VGG16 reached an impressive 96.30% in correctly identifying PD compared to healthy participants. Additionally, the performance measures such as sensitivity, specificity and precision are assessed to provide a more comprehensive evaluation. This research demonstrates that deep learning techniques can effectively analyze MRI scans to detect Parkinson's disease. However, further studies are warranted to validate these findings on larger datasets and assess the model's generalizability for clinical use.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Convolutional neural network
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	07 Feb 2025 02:35
Last Modified:	07 Feb 2025 02:36
URII:	http://shdl.mmu.edu.my/id/eprint/13392

Downloads

Edit (login required)