GateFuseNet: An Adaptive 3D Multimodal Neuroimaging Fusion Network for Parkinson's Disease Diagnosis

2025-10-25

AI Summary

Diagnosing Parkinson’s disease (PD) via MRI remains challenging due to symptom variability and pathological heterogeneity. To address this, we propose an adaptive 3D multimodal neuroimaging fusion network that jointly leverages T1-weighted images and quantitative susceptibility mapping (QSM) to precisely characterize key pathological features—particularly iron deposition in deep gray matter. Our method introduces a novel gated fusion module integrating modality-specific attention weights and channel-wise gating, enabling region-of-interest (ROI)-guided multi-level feature enhancement and suppression of task-irrelevant signals. The architecture combines 3D convolutional neural networks (CNNs), Grad-CAM-based interpretability, and end-to-end training. On an independent test set, it achieves 85.00% classification accuracy and 92.06% AUC—outperforming state-of-the-art methods. Ablation studies and visualization analyses validate the efficacy of each component and confirm strong clinical interpretability.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Accurate diagnosis of Parkinson's disease (PD) from MRI remains challenging due to symptom variability and pathological heterogeneity. Most existing methods rely on conventional magnitude-based MRI modalities, such as T1-weighted images (T1w), which are less sensitive to PD pathology than Quantitative Susceptibility Mapping (QSM), a phase-based MRI technique that quantifies iron deposition in deep gray matter nuclei. In this study, we propose GateFuseNet, an adaptive 3D multimodal fusion network that integrates QSM and T1w images for PD diagnosis. The core innovation lies in a gated fusion module that learns modality-specific attention weights and channel-wise gating vectors for selective feature modulation. This hierarchical gating mechanism enhances ROI-aware features while suppressing irrelevant signals. Experimental results show that our method outperforms three existing state-of-the-art approaches, achieving 85.00% accuracy and 92.06% AUC. Ablation studies further validate the contributions of ROI guidance, multimodal integration, and fusion positioning. Grad-CAM visualizations confirm the model's focus on clinically relevant pathological regions. The source codes and pretrained models can be found at https://github.com/YangGaoUQ/GateFuseNet

Problem

• Diagnosing Parkinson's disease using MRI due to symptom variability
• Integrating QSM and T1w MRI modalities for improved PD detection
• Developing adaptive fusion network for selective feature enhancement

Innovation

• Integrates QSM and T1w MRI modalities adaptively
• Uses gated fusion with attention weights for features
• Enhances ROI-aware features while suppressing irrelevant signals