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 journalArticle

Abstract

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)
JournalMagnetic Resonance in Medicine
DOIs
StateAccepted/In press - Jan 1 2019

Fingerprint

Brain
Physics
Glioblastoma
Artifacts
Nervous System
Magnetic Resonance Spectroscopy
Learning
Pathology
Neoplasms

Keywords

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

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Incorporation of a spectral model in a convolutional neural network for accelerated spectral fitting. / Gurbani, Saumya S.; Sheriff, Sulaiman; Maudsley, Andrew A; Shim, Hyunsuk; Cooper, Lee A.D.

In: Magnetic Resonance in Medicine, 01.01.2019.

Research output: Contribution to journalArticle

@article{9b4c2054610347b8b8198df19791dfed,
title = "Incorporation of a spectral model in a convolutional neural network for accelerated spectral fitting",
abstract = "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.",
keywords = "brain, deep learning, machine learning, MR spectroscopy, MRSI, spectral analysis, spectroscopic imaging",
author = "Gurbani, {Saumya S.} and Sulaiman Sheriff and Maudsley, {Andrew A} and Hyunsuk Shim and Cooper, {Lee A.D.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1002/mrm.27641",
language = "English (US)",
journal = "Magnetic Resonance in Medicine",
issn = "0740-3194",
publisher = "John Wiley and Sons Inc.",

}

TY - JOUR

T1 - Incorporation of a spectral model in a convolutional neural network for accelerated spectral fitting

AU - Gurbani, Saumya S.

AU - Sheriff, Sulaiman

AU - Maudsley, Andrew A

AU - Shim, Hyunsuk

AU - Cooper, Lee A.D.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - 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.

AB - 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.

KW - brain

KW - deep learning

KW - machine learning

KW - MR spectroscopy

KW - MRSI

KW - spectral analysis

KW - spectroscopic imaging

UR - http://www.scopus.com/inward/record.url?scp=85060353356&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060353356&partnerID=8YFLogxK

U2 - 10.1002/mrm.27641

DO - 10.1002/mrm.27641

M3 - Article

C2 - 30666698

AN - SCOPUS:85060353356

JO - Magnetic Resonance in Medicine

JF - Magnetic Resonance in Medicine

SN - 0740-3194

ER -