CD-DPE: Dual-Prompt Expert Network based on Convolutional Dictionary Feature Decoupling for Multi-Contrast MRI Super-Resolution

2025-11-17

AI Summary

In multi-contrast MRI super-resolution, insufficient utilization of textural information from reference images arises due to inter-modal contrast discrepancies. Method: This paper proposes a dual-prompt expert network with convolutional dictionary-based feature disentanglement. Specifically, we design a Convolutional Dictionary Feature Disentanglement Module (CD-FDM) to separate cross-contrast and intra-contrast features, and a Dual-Prompt Feature Fusion Expert Module (DP-FFEM) that incorporates frequency-guided and adaptive routing prompts for dynamic, selective feature integration. Results: Extensive experiments on public multi-contrast MRI datasets demonstrate that our method significantly outperforms state-of-the-art approaches in reconstructing fine anatomical details. Moreover, it exhibits strong generalization and robustness under unseen scanning protocols and hardware configurations, establishing a novel paradigm for clinical multi-contrast MRI high-resolution reconstruction.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Multi-contrast magnetic resonance imaging (MRI) super-resolution intends to reconstruct high-resolution (HR) images from low-resolution (LR) scans by leveraging structural information present in HR reference images acquired with different contrasts. This technique enhances anatomical detail and soft tissue differentiation, which is vital for early diagnosis and clinical decision-making. However, inherent contrasts disparities between modalities pose fundamental challenges in effectively utilizing reference image textures to guide target image reconstruction, often resulting in suboptimal feature integration. To address this issue, we propose a dual-prompt expert network based on a convolutional dictionary feature decoupling (CD-DPE) strategy for multi-contrast MRI super-resolution. Specifically, we introduce an iterative convolutional dictionary feature decoupling module (CD-FDM) to separate features into cross-contrast and intra-contrast components, thereby reducing redundancy and interference. To fully integrate these features, a novel dual-prompt feature fusion expert module (DP-FFEM) is proposed. This module uses a frequency prompt to guide the selection of relevant reference features for incorporation into the target image, while an adaptive routing prompt determines the optimal method for fusing reference and target features to enhance reconstruction quality. Extensive experiments on public multi-contrast MRI datasets demonstrate that CD-DPE outperforms state-of-the-art methods in reconstructing fine details. Additionally, experiments on unseen datasets demonstrated that CD-DPE exhibits strong generalization capabilities.

Problem

• Reconstructing high-resolution MRI images from low-resolution multi-contrast scans
• Addressing contrast disparities between modalities for effective feature integration
• Enhancing anatomical detail and tissue differentiation for clinical diagnosis

Innovation

• Convolutional dictionary decouples cross-contrast MRI features
• Dual-prompt module fuses frequency and routing guidance
• Adaptive routing optimizes reference-target feature integration