Robust multi‐coil MRI reconstruction via self‐supervised denoising
Magnetic Resonance in Medicine · 2025
DOI: 10.1002/mrm.30591 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2025. Verfasst von Asad Aali und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Stanford University, Stanford, California. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Google Research Scholar Program, NIH HHS, National Science Foundation.
Abstract (Originalsprache)
Purpose
To examine the effect of incorporating self‐supervised denoising as a pre‐processing step for training deep learning (DL) based reconstruction methods on data corrupted by Gaussian noise. K‐space data employed for training are typically multi‐coil and inherently noisy. Although DL‐based reconstruction methods trained on fully sampled data can enable high reconstruction quality, obtaining large, noise‐free datasets is impractical.
Methods
We leverage Generalized Stein's Unbiased Risk Estimate (GSURE) for denoising. We evaluate two DL‐based reconstruction methods: Diffusion Probabilistic Models (DPMs) and Model‐Based Deep Learning (MoDL). We evaluate the impact of denoising on the performance of these DL‐based methods in solving accelerated multi‐coil magnetic resonance imaging (MRI) reconstruction. The experiments were carried out on T2‐weighted brain and fat‐suppressed proton‐density knee scans.
Results
We observed that self‐supervised denoising enhances the quality and efficiency of MRI reconstructions across various scenarios. Specifically, employing denoised images rather than noisy counterparts when training DL networks results in lower normalized root mean squared error (NRMSE), higher structural similarity index measure (SSIM) and peak signal‐to‐noise ratio (PSNR) across different SNR levels, including 32, 22, and 12 dB for T2‐weighted brain data, and 24, 14, and 4 dB for fat‐suppressed knee data.
Conclusion
We showed that denoising is an essential pre‐processing technique capable of improving the efficacy of DL‐based MRI reconstruction methods under diverse conditions. By refining the quality of input data, denoising enables training more effective DL networks, potentially bypassing the need for noise‐free reference MRI scans.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Stanford University, Stanford, California.
- Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas.
- Intel Corporation, Hillsboro, Oregon.
- MD Anderson Cancer Center, Houston, Texas.
- Dell Medical School Department of Diagnostic Medicine, The University of Texas at Austin, Austin, Texas.
- Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, Texas.
ORCID-Profile: Asad Aali, Yamin I Arefeen
Förderung
- Google Research Scholar Program
- NIH HHS
- National Science Foundation
- Oracle for Research Fellowship
- NIBIB NIH HHS
- National Institutes of Health
- Oracle
Zitieren
APA
Aali, A., Arvinte, M., Kumar, S., Arefeen, Y. I., & Tamir, J. I. (2025). Robust multi‐coil MRI reconstruction via self‐supervised denoising. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.30591
Vancouver
Aali A, Arvinte M, Kumar S, Arefeen YI, Tamir JI. Robust multi‐coil MRI reconstruction via self‐supervised denoising. Magnetic Resonance in Medicine. 2025. doi:10.1002/mrm.30591
BibTeX
@article{Aali2025,
author = {Aali, Asad and Arvinte, Marius and Kumar, Sidharth and Arefeen, Yamin I and Tamir, Jonathan I},
title = {Robust multi‐coil MRI reconstruction via self‐supervised denoising},
journal = {Magnetic Resonance in Medicine},
year = {2025},
doi = {10.1002/mrm.30591}
}
EUVIMED