MRI denoising with a non‐blind deep complex‐valued convolutional neural network
NMR in Biomedicine · 2025-01 · 38 (1)
DOI: 10.1002/nbm.5291 ↗Kurz gefasst
Fachartikel in der Zeitschrift NMR in Biomedicine, online erschienen am 11.11.2024. Verfasst von Quan Dou und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, University of Virginia, Charlottesville, Virginia, USA. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Signal-To-Noise Ratio, Neural Networks, Computer. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIBIB NIH HHS, National Heart, Lung, and Blood Institute's Division of Intramural Research, Siemens Medical Solutions.
Abstract (Originalsprache)
MR images with high signal‐to‐noise ratio (SNR) provide more diagnostic information. Various methods for MRI denoising have been developed, but the majority of them operate on the magnitude image and neglect the phase information. Therefore, the goal of this work is to design and implement a complex‐valued convolutional neural network (CNN) for MRI denoising. A complex‐valued CNN incorporating the noise level map (non‐blind DnCNN) was trained with ground truth and simulated noise‐corrupted image pairs. The proposed method was validated using both simulated and in vivo data collected from low‐field scanners. Its denoising performance was quantitively and qualitatively evaluated, and it was compared with the real‐valued CNN and several other algorithms. For the simulated noise‐corrupted testing dataset, the complex‐valued models had superior normalized root‐mean‐square error, peak SNR, structural similarity index, and phase ABSD. By incorporating the noise level map, the non‐blind DnCNN showed better performance in dealing with spatially varying parallel imaging noise. For in vivo low‐field data, the non‐blind DnCNN significantly improved the SNR and visual quality of the image. The proposed non‐blind DnCNN provides an efficient and effective approach for MRI denoising. This is the first application of non‐blind DnCNN to medical imaging. The method holds the potential to enable improved low‐field MRI, facilitating enhanced diagnostic imaging in under‐resourced areas.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Engineering, University of Virginia, Charlottesville, Virginia, USA.
- Cardiovascular Branch, Division of Intramural Research, National Heart, Lung, and Blood Institute, National Institutes of Health, Bethesda, Maryland, USA.
- Department of Radiology and Medical Imaging, University of Virginia, Charlottesville, Virginia, USA.
ORCID-Profile: Quan Dou, Zhixing Wang, Adrienne E Campbell-Washburn
Förderung
- NIBIB NIH HHS
- National Heart, Lung, and Blood Institute's Division of Intramural Research
- Siemens Medical Solutions
- National Institute of Biomedical Imaging and Bioengineering
Zitieren
APA
Dou, Q., Wang, Z., Feng, X., Campbell-Washburn, A. E., Mugler, J. P., & Meyer, C. H. (2025). MRI denoising with a non‐blind deep complex‐valued convolutional neural network. NMR in Biomedicine, 38(1). https://doi.org/10.1002/nbm.5291
Vancouver
Dou Q, Wang Z, Feng X, Campbell-Washburn AE, Mugler JP, Meyer CH. MRI denoising with a non‐blind deep complex‐valued convolutional neural network. NMR in Biomedicine. 2025;38(1). doi:10.1002/nbm.5291
BibTeX
@article{Dou2025,
author = {Dou, Quan and Wang, Zhixing and Feng, Xue and Campbell-Washburn, Adrienne E and Mugler, John P and Meyer, Craig H},
title = {MRI denoising with a non‐blind deep complex‐valued convolutional neural network},
journal = {NMR in Biomedicine},
year = {2025},
volume = {38},
number = {1},
doi = {10.1002/nbm.5291}
}
EUVIMED