Constrained Magnetic Resonance Spectroscopic Imaging by Learning Nonlinear Low-Dimensional Models

Fan Lam, Yahang Li, Xi Peng

Research output: Contribution to journalArticlepeer-review

Abstract

Magnetic resonance spectroscopic imaging (MRSI) is a powerful molecular imaging modality but has very limited speed, resolution, and SNR tradeoffs. Construction of a low-dimensional model to effectively reduce the dimensionality of the imaging problem has recently shown great promise in improving these tradeoffs. This paper presents a new approach to model and reconstruct the spectroscopic signals by learning a nonlinear low-dimensional representation of the general MR spectra. Specifically, we trained a deep neural network to capture the low-dimensional manifold, where the high-dimensional spectroscopic signals reside. A regularization formulation is proposed to effectively integrate the learned model and physics-based data acquisition model for MRSI reconstruction with the capability to incorporate additional spatiospectral constraints. An efficient numerical algorithm was developed to solve the associated optimization problem involving back-propagating the trained network. Simulation and experimental results were obtained to demonstrate the representation power of the learned model and the ability of the proposed formulation in producing SNR-enhancing reconstruction from the practical MRSI data.

Original languageEnglish (US)
Article number8770102
Pages (from-to)545-555
Number of pages11
JournalIEEE transactions on medical imaging
Volume39
Issue number3
DOIs
StatePublished - Mar 2020

Keywords

  • MR spectroscopic imaging
  • low-dimensionalmodels
  • manifold learning
  • neural network
  • spatiospectral constraint
  • spectroscopy

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Constrained Magnetic Resonance Spectroscopic Imaging by Learning Nonlinear Low-Dimensional Models'. Together they form a unique fingerprint.

Cite this