Joint learning of nonlinear representation and projection for fast constrained MRSI reconstruction
Magnetic Resonance in Medicine · 2025
DOI: 10.1002/mrm.30276 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2025. Verfasst von Yahang Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bioengineering, University of Illinois Urbana-Champaign, Urbana, Illinois, USA. Hauptthemen laut MEDLINE: Algorithms, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Brain. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Cancer Prevention and Research Institute of Texas, NIGMS NIH HHS, NIBIB NIH HHS.
Abstract (Originalsprache)
Purpose
To develop and evaluate a novel method for computationally efficient reconstruction from noisy MR spectroscopic imaging (MRSI) data.
Methods
The proposed method features (a) a novel strategy that jointly learns a nonlinear low‐dimensional representation of high‐dimensional spectroscopic signals and a neural‐network‐based projector to recover the low‐dimensional embeddings from noisy/limited data; (b) a formulation that integrates the forward encoding model, a regularizer exploiting the learned representation, and a complementary spatial constraint; and (c) a highly efficient algorithm enabled by the learned projector within an alternating direction method of multipliers (ADMM) framework, circumventing the computationally expensive network inversion subproblem.
Results
The proposed method has been evaluated using simulations as well as in vivo H and P MRSI data, demonstrating improved performance over state‐of‐the‐art methods, with about 6 fewer averages needed than standard Fourier reconstruction for similar metabolite estimation variances and up to 100 reduction in processing time compared to a prior neural network constrained reconstruction method. Computational and theoretical analyses were performed to offer further insights into the effectiveness of the proposed method.
Conclusion
A novel method was developed for fast, high‐SNR spatiospectral reconstruction from noisy MRSI data. We expect our method to be useful for enhancing the quality of MRSI or other high‐dimensional spatiospectral imaging data.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Bioengineering, University of Illinois Urbana-Champaign, Urbana, Illinois, USA.
- Beckman Institute for Advanced Science and Technology, University of Illinois Urbana-Champaign, Urbana, Illinois, USA.
- Advanced Imaging Research Center, University of Texas Southwestern Medical Center, Dallas, Texas, USA.
- High-Field Magnetic Resonance Center, Max Planck Institute for Biological Cybernetics, Tübingen, Germany.
- Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, Illinois, USA.
- Carle Neuroscience Institute, Carle Foundation Hospital, Urbana, Illinois, USA.
ORCID-Profile: Yahang Li, Zepeng Wang, Aaron Anderson, Fan Lam
Förderung
- Cancer Prevention and Research Institute of Texas
- NIGMS NIH HHS
- NIBIB NIH HHS
- European Research Council Starting Grant
- National Science Foundation, Division of Chemical, Bioengineering, Environmental, and Transport Systems
- National Institute of General Medical Sciences
- National Institute of Biomedical Imaging and Bioengineering
- National Science Foundation
Zitieren
APA
Li, Y., Ruhm, L., Wang, Z., Zhao, R., Anderson, A., Arnold, P., Huesmann, G., Henning, A., & Lam, F. (2025). Joint learning of nonlinear representation and projection for fast constrained MRSI reconstruction. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.30276
Vancouver
Li Y, Ruhm L, Wang Z, Zhao R, Anderson A, Arnold P, et al. Joint learning of nonlinear representation and projection for fast constrained MRSI reconstruction. Magnetic Resonance in Medicine. 2025. doi:10.1002/mrm.30276
BibTeX
@article{Li2025,
author = {Li, Yahang and Ruhm, Loreen and Wang, Zepeng and Zhao, Ruiyang and Anderson, Aaron and Arnold, Paul and Huesmann, Graham and Henning, Anke and Lam, Fan},
title = {Joint learning of nonlinear representation and projection for fast constrained MRSI reconstruction},
journal = {Magnetic Resonance in Medicine},
year = {2025},
doi = {10.1002/mrm.30276}
}
EUVIMED