Citation

Jegadeesan, Ezhilarasi and Thillaigovindan, Senthil Kumar and Roslee, Mardeni (2026) Transforming neuroimaging analysis for early detection of Parkinson’s disease with an Integrated YOLOv5-FMRCNN framework and improved optimization techniques. Neural Computing and Applications, 38 (10). ISSN 0941-0643

Text s00521-026-12100-4.pdf - Published Version Restricted to Repository staff only Download (3MB)

Abstract

Millions of people worldwide suffer from Parkinson’s disease (PD), a neurological disorder often leading to cognitive decline and movement impairment. Early detection and accurate characterization of PD are crucial for improving patient outcomes and developing personalized treatment strategies. The manual processing of medical images in current diagnostic approaches is time-consuming and prone to errors. The study proposes a new method for examining medical images that uses the advanced YOLOv5-FMRCNN design along with the Faster Mask Region-based Convolutional Neural Network Model (FMRCNN). It does this with an Improved Weighted Quantum Particle Swarm Optimization (IWQPSO) technique to help find and classify PD earlier. The primary objectives are to improve PD detection accuracy and reduce computational time without compromising reliability. The method uses YOLOv5-FMRCNN’s advanced machine-learning skills for quickly finding and identifying objects, while also using IWQPSO to pick out important features and fine-tune settings. The proposed model evaluates the method using publicly available healthcare imaging datasets, including MRI scans. The results demonstrate that the proposed system outperforms traditional techniques in terms of robustness to variations in image resolution, recognition speed, and classification accuracy. This comprehensive system not only introduces a new approach for diagnosing PD but also lays the groundwork for future advancements in medical imaging analysis for neurodegenerative disorders

Item Type:	Article
Uncontrolled Keywords:	Parkinson’s disease, deep learning, early detection
Subjects:	R Medicine > R Medicine (General) > R856-857 Biomedical engineering. Electronics. Instrumentation
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	05 Jun 2026 03:05
Last Modified:	05 Jun 2026 03:05
URII:	http://shdl.mmu.edu.my/id/eprint/15992

Downloads

Edit (login required)