From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction

2025-06-19

AI Summary

MRI 3D reconstruction under motion corruption and k-space undersampling suffers from localized detail loss, global structural aliasing, and degradation of voxel-wise anisotropy. Method: We propose the first progressive implicit neural representation framework explicitly designed for motion-robust anisotropic reconstruction. Our approach unifies motion correction, structural refinement, and volumetric synthesis within a geometry-aware coordinate space by integrating motion-aware diffusion modeling, coordinate-aligned implicit detail restoration, and continuous voxel-level representation. A coordinate-feature alignment mechanism and 3D continuous function modeling ensure anatomical consistency and spatial continuity. Results: Evaluated on five public datasets, our method significantly outperforms state-of-the-art methods, enabling up to 8× acceleration and robustness to 5% rigid-body motion displacement. It achieves substantial improvements in PSNR and SSIM, delivering both high quantitative accuracy and clinically acceptable visual fidelity.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Deep Generative Models & Autoencoders
• Intelligent Robots: Motion and Path Planning

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

In motion-robust magnetic resonance imaging (MRI), slice-to-volume reconstruction is critical for recovering anatomically consistent 3D brain volumes from 2D slices, especially under accelerated acquisitions or patient motion. However, this task remains challenging due to hierarchical structural disruptions. It includes local detail loss from k-space undersampling, global structural aliasing caused by motion, and volumetric anisotropy. Therefore, we propose a progressive refinement implicit neural representation (PR-INR) framework. Our PR-INR unifies motion correction, structural refinement, and volumetric synthesis within a geometry-aware coordinate space. Specifically, a motion-aware diffusion module is first employed to generate coarse volumetric reconstructions that suppress motion artifacts and preserve global anatomical structures. Then, we introduce an implicit detail restoration module that performs residual refinement by aligning spatial coordinates with visual features. It corrects local structures and enhances boundary precision. Further, a voxel continuous-aware representation module represents the image as a continuous function over 3D coordinates. It enables accurate inter-slice completion and high-frequency detail recovery. We evaluate PR-INR on five public MRI datasets under various motion conditions (3% and 5% displacement), undersampling rates (4x and 8x) and slice resolutions (scale = 5). Experimental results demonstrate that PR-INR outperforms state-of-the-art methods in both quantitative reconstruction metrics and visual quality. It further shows generalization and robustness across diverse unseen domains.

Problem

• Recovering 3D brain volumes from 2D MRI slices under motion
• Addressing local detail loss and global aliasing in MRI reconstruction
• Enhancing volumetric synthesis with implicit neural representation

Innovation

• Progressive refinement implicit neural representation framework
• Motion-aware diffusion for coarse volumetric reconstructions
• Voxel continuous-aware representation for inter-slice completion