Incorporation of a spectral model in a convolutional neural network for accelerated spectral fitting

Saumya S. Gurbani, Sulaiman Sheriff, Andrew A. Maudsley, Hyunsuk Shim, Lee A.D. Cooper

Research output: Contribution to journalArticlepeer-review

13 Scopus citations


Purpose: MRSI has shown great promise in the detection and monitoring of neurologic pathologies such as tumor. A necessary component of data processing includes the quantitation of each metabolite, typically done through fitting a model of the spectrum to the data. For high-resolution volumetric MRSI of the brain, which may have ~10,000 spectra, significant processing time is required for spectral analysis and generation of metabolite maps. Methods: A novel unsupervised deep learning architecture that combines a convolutional neural network with a priori models of the spectrum is presented. This architecture, a convolutional encoder–model decoder (CEMD), combines the strengths of adaptive and unbiased convolutional networks with models of magnetic resonance and is readily interpretable. Results: The CEMD architecture performs accurate spectral fitting for volumetric MRSI in patients with glioblastoma, provides whole-brain fitting in 1 min on a standard computer, and handles a variety of spectral artifacts. Conclusion: A new architecture combining physics domain knowledge with convolutional neural networks has been developed and is able to perform rapid spectral fitting of whole-brain data. Rapid processing is a critical step toward routine clinical practice.

Original languageEnglish (US)
Pages (from-to)3346-3357
Number of pages12
JournalMagnetic Resonance in Medicine
Issue number5
StatePublished - May 2019


  • MR spectroscopy
  • MRSI
  • brain
  • deep learning
  • machine learning
  • spectral analysis
  • spectroscopic imaging

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'Incorporation of a spectral model in a convolutional neural network for accelerated spectral fitting'. Together they form a unique fingerprint.

Cite this