From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction
- 1 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 3550-3565
Abstract
n 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 ( 4 x and 8 x ) 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.Keywords
All Related Versions
Funding Information
- ERC IMI (101005122)
- Horizon 2020 Framework Programme (952172)
- Musculoskeletal Research Center, Washington University in St. Louis (MC/PC/21013)
- Royal Society (IEC/NSFC/211235)
- NVIDIA Academic Hardware Grant Program
- SABER project supported by Boehringer Ingelheim Ltd.
- National Natural Science Foundation of China (RDA01)
- Wellcome Leap Dynamic Resilience program
- UKRI through the Horizon Europe MSCA Postdoctoral Fellowships (EP/Z002206/1)
- UKRI MRC Research
- TFS Research Grants (MR/U506710/1)
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (220785)
- UKRI Future Leaders Fellowship (MR/V023799/1)
- UKRI Future Leaders Fellowship (UKRI2738)
- Imperial College London Seeds for Success Fund
- CSC scholarship
This publication has 56 references indexed in Scilit:
- Beat Pilot Tone (BPT): Simultaneous MRI and RF motion sensing at arbitrary frequenciesMagnetic Resonance in Medicine, 2024
- SMRD: SURE-Based Robust MRI Reconstruction with Diffusion Models2023
- Single-subject Multi-contrast MRI Super-resolution via Implicit Neural Representations2023
- SVoRT: Iterative Transformer for Slice-to-Volume Registration in Fetal Brain MRI2022
- 3D Isotropic Super-resolution Prostate MRI Using Generative Adversarial Networks and Unpaired Multiplane SlicesJournal of Digital Imaging, 2021
- Anatomy-Guided Convolutional Neural Network for Motion Correction in Fetal Brain MRI2020
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- P‐LORAKS: Low‐rank modeling of local k‐space neighborhoods with parallel imaging dataMagnetic Resonance in Medicine, 2015
- Sparse MRI: The application of compressed sensing for rapid MR imagingMagnetic Resonance in Medicine, 2007
- Adaptive reconstruction of phased array MR imageryMagnetic Resonance in Medicine, 2000