What does this research mean for the field?

The Lite HGWA-Net model enables early diagnosis of Parkinson's disease with an F1-score of 0.8762, outperforming existing models in MRI analysis. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The study aims to develop a lightweight deep learning model for early diagnosis of Parkinson's Disease using MRI data.

February 16, 2026Open Access

Early Diagnosis of Parkinson’s Disease Through Lite HGWA-Net Model: A Hybrid CNN Based on Wavelet Transform and Attention Mechanism

Key Points

The study aims to develop a lightweight deep learning model for early diagnosis of Parkinson's Disease using MRI data.
Utilizes a hybrid CNN architecture integrating GhostNet and ensemble learning.
Employs wavelet-based frequency feature extraction for improved biomarker identification.
Incorporates an attention module to enhance focus on critical image regions.
Classifies subjects into PD patients or healthy controls based on T2-weighted MRI.
Achieved an F1-score of 0.8762, indicating strong model performance.
Outperformed existing models with fewer parameters and lower computational load.
Demonstrated significant improvements across multiple evaluation metrics (p < 0.001).
Identified novel texture and frequency patterns in MRI data.

Abstract

Background/Objectives: Parkinson’s disease (PD) is a progressive neurodegenerative disorder in ageing populations, yet early diagnosis before motor symptoms remains critical. Reliable identification of subtle nigral alterations at early stages of the disease on magnetic resonance imaging (MRI) remains challenging. This limitation is mainly attributed to the subjective and low sensitivity of manual image interpretation in early PD. Here, we demonstrate a deep learning-based framework to enhance early PD detection. The study’s novelty is a lightweight deep learning framework that captures spatial, textural, and frequency-domain PD biomarkers without heavy network architectures or manual region delineation. Methods: The model integrates GhostNet with ensemble learning to combine local and global spatial information. This model employs wavelet-based frequency feature extraction rather than downsampling and incorporates an attention module to focus on relevant image regions, particularly changes in the substantia nigra (SN) region. Segmentation is employed solely as an auxiliary intermediate step to localize the SN and guide discriminative feature extraction. The final output is a binary classification that distinguishes PD patients from healthy controls. T2-weighted MRI data from the PPMI database are employed. Results: The proposed model achieved an F1-score of 0.8762, demonstrating robust performance under class imbalance, outperforming state-of-the-art models with only 2.03 million parameters and 4.36 Giga Floating Point Operations (GFLOPs). The architecture uncovered texture and frequency patterns previously inaccessible with conventional CNN pipelines. Model comparisons demonstrated consistent gains across all evaluated metrics (all p < 0.001), establishing robust diagnostic improvement. Conclusions: These findings establish an efficient, high-performing framework for reliable MRI-based PD identification. The approach provides automated early detection and supports clinically scalable, computationally lightweight screening tools.

Mark Helpful

Bookmark

Relay

View Full Paper