loading page

LeaRning nonlineAr representatIon and projectIon for faSt constrained MRSI rEconstruction (RAIISE)
  • +6
  • Yahang Li ,
  • Loreen Ruhm ,
  • Zepeng Wang ,
  • Ruiyang Zhao ,
  • Aaron Anderson ,
  • Paul Arnold ,
  • Graham Huesmann ,
  • Anke Henning ,
  • Fan Lam
Yahang Li
Department of Bioengineering, Department of Bioengineering

Corresponding Author:[email protected]

Author Profile
Loreen Ruhm
Author Profile
Zepeng Wang
Author Profile
Ruiyang Zhao
Author Profile
Aaron Anderson
Author Profile
Paul Arnold
Author Profile
Graham Huesmann
Author Profile
Anke Henning
Author Profile


Learning and utilizing low-dimensional models for high-dimensional spatiospectral imaging problems is an active research area. We present here a novel method for computationally efficient reconstruction from noisy high-dimensional MR spectroscopic imaging (MRSI) data. 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 joint formulation that integrates the forward spatiospectral encoding model, a constraint exploiting the learned representation, and a complementary spatial constraint; and (c) a highly efficient algorithm enabled by a learned projector within an alternating direction method of multipliers (ADMM) framework, circumventing the computationally expensive network inversion subproblem. The proposed method has been evaluated using simulations and in vivo 31P-MRSI and 1H-MRSI data, demonstrating improved performance over state-of-the-art methods. Computational complexity and algorithm convergence analysis have been performed to offer further insights into the effectiveness of the proposed method.