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 language | English (US) |
|---|---|
| Journal | Magnetic Resonance in Medicine |
| DOIs | |
| State | Accepted/In press - Jan 1 2019 |
Fingerprint
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 journal › Article
}
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 -