High-dimensional Embedding Prior for Noisy K-space Domain MRIReconstruction
2026-07-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors focus on improving MRI image reconstruction when the data is noisy or incomplete, which is a common problem in real scans. They propose a new method that changes how the data is represented, making it easier for advanced models called diffusion-based solvers to do their job better without altering their core steps. Their experiments show this new approach consistently produces clearer images, especially when noise levels are high. This work offers a new way to make MRI reconstructions more reliable under tough conditions.
MRI reconstructionk-spacediffusion modelsinverse problemsnoise corruptionhigh-dimensional representationundersamplinggenerative priordata embedding
Authors
Yu Guan, Tianjia Huang, Qinrong Cai, Qiuyun Fan, Dong Liang, Qiegen Liu
Abstract
Magnetic resonance imaging (MRI) reconstruction under realistic acquisition conditions can be fundamentally viewed as estimating the underlying k-space distribution from incomplete and noise-corrupted measurements. While diffusion models have recently shown strong potential as generative prior for inverse problems,existingapproachesstruggletohandlenoisyreconstruction settings, especially when operating directly in k-space domain. In this work, we propose a unified high-dimensional k-space reconstruction framework tailored for noisy inverse problems, whichenhancesdiffusion-based solversthroughrepresentation lifting.Ratherthanmodifyingthe underlying optimization procedures, the proposed framework augments the data representation space, enabling existing diffusion-based solvers to operate on enriched k-space embeddings with improved expressiveness. Extensive experiments on both in-house and public datasets across varying noise levels and undersampled factors demonstrate that the proposed frame work consistently improves reconstruction quality for multiple diffusion-based inverse solvers. Notably, the largest gains are observed in high-noise regimes, which is consistent with our theoretical analysis of error propagation under high-dimensional representation. These results suggest that high-dimensional representation provides a general and model-agnostic mechanism for improving diffusion-based MRI reconstruction in noisy settings, offering a new perspective on robust k-space generative modeling for practical inverse problems. The code will be available at https://github.com/yqx7150/HEP-MRIRec.