Format

Send to

Choose Destination
Magn Reson Med. 2018 Nov;80(5):1765-1775. doi: 10.1002/mrm.27166. Epub 2018 Mar 9.

A convolutional neural network to filter artifacts in spectroscopic MRI.

Author information

1
Department of Radiation Oncology, Emory University, Atlanta, Georgia.
2
Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, Georgia.
3
Winship Cancer Institute of Emory University, Atlanta, Georgia.
4
Department of Radiology, University of Miami Miller School of Medicine, Miami, Florida.
5
Department of Radiology, Duke University School of Medicine, Durham, North Carolina.
6
Institute of Translational Medicine, University of Liverpool, Liverpool, United Kingdom.
7
Department of Radiology, Icahn School of Medicine at Mt. Sinai, New York, New York.
8
Department of Radiology and Radiological Science, The Johns Hopkins University, Baltimore, Maryland.
9
Department of Radiology and Imaging Sciences, Emory University, Atlanta, Georgia.
10
Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, Georgia.

Abstract

PURPOSE:

Proton MRSI is a noninvasive modality capable of generating volumetric maps of in vivo tissue metabolism without the need for ionizing radiation or injected contrast agent. Magnetic resonance spectroscopic imaging has been shown to be a viable imaging modality for studying several neuropathologies. However, a key hurdle in the routine clinical adoption of MRSI is the presence of spectral artifacts that can arise from a number of sources, possibly leading to false information.

METHODS:

A deep learning model was developed that was capable of identifying and filtering out poor quality spectra. The core of the model used a tiled convolutional neural network that analyzed frequency-domain spectra to detect artifacts.

RESULTS:

When compared with a panel of MRS experts, our convolutional neural network achieved high sensitivity and specificity with an area under the curve of 0.95. A visualization scheme was implemented to better understand how the convolutional neural network made its judgement on single-voxel or multivoxel MRSI, and the convolutional neural network was embedded into a pipeline capable of producing whole-brain spectroscopic MRI volumes in real time.

CONCLUSION:

The fully automated method for assessment of spectral quality provides a valuable tool to support clinical MRSI or spectroscopic MRI studies for use in fields such as adaptive radiation therapy planning.

KEYWORDS:

MR spectroscopic imaging; deep learning; machine learning; spectroscopic MRI

PMID:
29520831
PMCID:
PMC6107370
[Available on 2019-11-01]
DOI:
10.1002/mrm.27166

Supplemental Content

Full text links

Icon for Wiley
Loading ...
Support Center