A Diffusion-Driven Temporal Super-Resolution and Spatial Consistency Enhancement Framework for 4D MRI imaging

2025-06-04

AI Summary

To address motion distortion and inter-slice inconsistency arising from the spatiotemporal resolution trade-off under large deformations in 4D MRI, this paper proposes TSSC-Net, an end-to-end generative framework. Methodologically, it introduces— for the first time—a diffusion-model-driven temporal super-resolution paradigm enabling single-step 6× temporal interpolation; designs a tri-directional Mamba module to capture long-range voxel dependencies; and pioneers the integration of state-space models into 4D MRI for inter-slice error correction. Additionally, it incorporates start-end-frame guidance and joint spatiotemporal reconstruction. Evaluated on the ACDC cardiac and real-world knee 4D MRI datasets, TSSC-Net achieves a 3.2 dB PSNR gain and a 5.7% Dice score improvement over prior methods, significantly enhancing structural fidelity and 3D spatial consistency—enabling high-fidelity dynamic imaging under rapid, large-deformation scenarios.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

In medical imaging, 4D MRI enables dynamic 3D visualization, yet the trade-off between spatial and temporal resolution requires prolonged scan time that can compromise temporal fidelity--especially during rapid, large-amplitude motion. Traditional approaches typically rely on registration-based interpolation to generate intermediate frames. However, these methods struggle with large deformations, resulting in misregistration, artifacts, and diminished spatial consistency. To address these challenges, we propose TSSC-Net, a novel framework that generates intermediate frames while preserving spatial consistency. To improve temporal fidelity under fast motion, our diffusion-based temporal super-resolution network generates intermediate frames using the start and end frames as key references, achieving 6x temporal super-resolution in a single inference step. Additionally, we introduce a novel tri-directional Mamba-based module that leverages long-range contextual information to effectively resolve spatial inconsistencies arising from cross-slice misalignment, thereby enhancing volumetric coherence and correcting cross-slice errors. Extensive experiments were performed on the public ACDC cardiac MRI dataset and a real-world dynamic 4D knee joint dataset. The results demonstrate that TSSC-Net can generate high-resolution dynamic MRI from fast-motion data while preserving structural fidelity and spatial consistency.

Problem

• Enhance temporal resolution in 4D MRI during rapid motion
• Address spatial inconsistencies from large deformations in MRI
• Improve volumetric coherence and correct cross-slice errors

Innovation

• Diffusion-based temporal super-resolution network
• Tri-directional Mamba-based module
• Preserves spatial consistency in MRI