Machine Learning-Enabled High-Resolution Dynamic Deuterium MR Spectroscopic Imaging

Yudu Li, Yibo Zhao, Rong Guo, Tao Wang, Yi Zhang, Matthew Chrostek, Walter C. Low, Xiao Hong Zhu, Zhi Pei Liang, Wei Chen

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


Deuterium magnetic resonance spectroscopic imaging (DMRSI) has recently been recognized as a potentially powerful tool for noninvasive imaging of brain energy metabolism and tumor. However, the low sensitivity of DMRSI has significantly limited its utility for both research and clinical applications. This work presents a novel machine learning-based method to address this limitation. The proposed method synergistically integrates physics-based subspace modeling and data-driven deep learning for effective denoising, making high-resolution dynamic DMRSI possible. Specifically, a novel subspace model was used to represent the dynamic DMRSI signals; deep neural networks were trained to capture the low-dimensional manifolds of the spectral and temporal distributions of practical dynamic DMRSI data. The learned subspace and manifold structures were integrated via a regularization formulation to remove measurement noise. Theoretical analysis, computer simulations, and in vivo experiments have been conducted to demonstrate the denoising efficacy of the proposed method which enabled high-resolution imaging capability. The translational potential was demonstrated in tumor-bearing rats, where the Warburg effect associated with cancer metabolism and tumor heterogeneity were successfully captured. The new method may not only provide an effective tool to enhance the sensitivity of DMRSI for basic research and clinical applications but also provide a framework for denoising other spatiospectral data.

Original languageEnglish (US)
Pages (from-to)3879-3890
Number of pages12
JournalIEEE Transactions on Medical Imaging
Issue number12
Early online dateJul 28 2021
StatePublished - Dec 1 2021

Bibliographical note

Funding Information:
Manuscript received April 5, 2021; revised June 18, 2021; accepted July 25, 2021. Date of publication July 28, 2021; date of current version November 30, 2021. This work was supported in part by the NIH under Grant R01-CA240953, Grant U01-EB026978, Grant R01MH111413, Grant P30NS076408, Grant P41EB027061, and Grant R01EB023704. (Corresponding authors: Wei Chen; Zhi-Pei Liang.) This work involved human subjects or animals in its research. All the procedures and experiments involved in the animal study followed the National Research Council’s Guide for the Care and Use of Laboratory Animals and were in accordance with the protocol approved by the Institutional Animal Care and Use Committee of the University of Minnesota.

Publisher Copyright:
© 1982-2012 IEEE.


  • Biochemistry
  • Image resolution
  • Imaging
  • In vivo deuterium MRS imaging (DMRSI)
  • Manifolds
  • Sensitivity
  • Spatial resolution
  • Tumors
  • high spatiotemporal resolution
  • machine learning
  • subspace modelling

PubMed: MeSH publication types

  • Journal Article
  • Research Support, N.I.H., Extramural


Dive into the research topics of 'Machine Learning-Enabled High-Resolution Dynamic Deuterium MR Spectroscopic Imaging'. Together they form a unique fingerprint.

Cite this