BibTex format
@article{Zhang:2026:10.1109/TIP.2026.3678052,
author = {Zhang, Z and Zhang, L and Cheng, Y and Wang, Z and Wang, F and Zhang, H and Yang, Y and Wu, Y and Huang, J and Aviles-Rivero, AI and Gao, Z and Yang, G and Lally, PJ},
doi = {10.1109/TIP.2026.3678052},
journal = {IEEE Trans Image Process},
pages = {3550--3565},
title = {From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction.},
url = {http://dx.doi.org/10.1109/TIP.2026.3678052},
volume = {35},
year = {2026}
}
RIS format (EndNote, RefMan)
TY - JOUR
AB - 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.
AU - Zhang,Z
AU - Zhang,L
AU - Cheng,Y
AU - Wang,Z
AU - Wang,F
AU - Zhang,H
AU - Yang,Y
AU - Wu,Y
AU - Huang,J
AU - Aviles-Rivero,AI
AU - Gao,Z
AU - Yang,G
AU - Lally,PJ
DO - 10.1109/TIP.2026.3678052
EP - 3565
PY - 2026///
SP - 3550
TI - From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction.
T2 - IEEE Trans Image Process
UR - http://dx.doi.org/10.1109/TIP.2026.3678052
UR - https://www.ncbi.nlm.nih.gov/pubmed/41921146
VL - 35
ER -