DM-PAFNet: A Dual-Stage Deep Learning Framework for Parkinson's Disease Staging Prediction via Multi-modal MRI and Clinical Prior Fusion
- 11 April 2026
- journal article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (20)
Abstract
The early diagnosis and precise staging of disease severity in Parkinson's disease (PD) represent significant challenges in current clinical practice, primarily limited by the subjectivity and instability of traditional assessment methods. In recent years, deep learning methods based on multimodal neuroimaging have offered a new avenue for objective and automated assessment; however, they still face key bottlenecks such as inefficient fusion of heterogeneous modalities and insufficient clinical plausibility of the models. To address these limitations, this study proposes an innovative two-stage multimodal deep learning framework, DM-PAFNet, which integrates a dual-branch multi-modal classification network (DB-MCNet) and a medical prior-guided attention fusion network (MP-AFNet). The framework is centered on a progressive strategy of "diagnosis for pre-training, staging for fine-tuning," modeling PD assessment as a hierarchical knowledge transfer process. In the first stage, we construct the DB-MCNet, which introduces a dual-stream adaptive fusion (DSAF) module to efficiently integrate information from T1-weighted imaging (T1-MRI) and diffusion tensor imaging (DTI). This stage achieves high-precision PD diagnosis and yields an image feature encoder with strong generalization capabilities. In the second stage, we propose the MP-AFNet. Building upon the inherited pre-trained weights, it utilizes a gated cross-modal attention (GCA) module to fuse imaging features with clinical variables. Furthermore, it innovatively introduces a medically-informed constraint (MIC) module, which embeds clinical knowledge as a soft constraint during training to enhance the credibility and stability of the staging predictions. Experimental results on the public PPMI dataset demonstrate the outstanding performance of our framework. The first-stage DB-MCNet achieved an accuracy of 95.85% in the PD vs. healthy control classification task, with the learned imaging encoder subsequently transferred to initialize the second stage. In the more challenging Hoehn and Yahr (H&Y) staging prediction across 410 subjects (H&Y stages 0–3), the complete framework achieved an accuracy of 88.3%, significantly outperforming several mainstream baseline methods. In conclusion, by virtue of its two-stage structural design, efficient multimodal fusion mechanisms, and clinical prior-guided strategy, the DM-PAFNet provides an accurate, objective, and clinically interpretable solution for the automated diagnosis and fine-grained staging of PD.Keywords
Funding Information
- Sichuan University of Science and Engineering (Y2024296)
- Intelligent Perception and Control Key Laboratory of Sichuan Province (2024RYY09)
- The Sichuan Province Key Laboratory of Intelligent Medicine and Health Big Data (ZNYX2507)
- Natural Science Foundation of Sichuan Province (2025ZNSFSC0477)
This publication has 46 references indexed in Scilit:
- Global trends and projections of Parkinson’s disease incidence: a 30-year analysis using GBD 2021 dataJournal of Neurology, 2025
- Diagnosis of Parkinson’s disease based on 3D ResNet: The frontal lobe is crucialBiomedical Signal Processing and Control, 2023
- Age Cutoff for Early‐Onset Parkinson's Disease: Recommendations from the International Parkinson and Movement Disorder Society Task Force on Early Onset Parkinson's DiseaseMovement Disorders Clinical Practice, 2022
- Diffusion tensor imaging for the differential diagnosis of Parkinsonism by machine learningBiomedical Journal, 2022
- International Multicenter Analysis of Brain Structure Across Clinical Stages of Parkinson's DiseaseMovement Disorders, 2021
- Diagnosis and Treatment of Parkinson DiseaseJAMA, 2020
- Deep learning in medical imaging and radiation therapyMedical Physics, 2018
- Machine learning on brain MRI data for differential diagnosis of Parkinson's disease and Progressive Supranuclear PalsyJournal of Neuroscience Methods, 2014
- Magnetic resonance support vector machine discriminates between Parkinson disease and progressive supranuclear palsyMovement Disorders, 2013
- Movement Disorder Society Task Force report on the Hoehn and Yahr staging scale: Status and recommendations The Movement Disorder Society Task Force on rating scales for Parkinson's diseaseMovement Disorders, 2004