Data-driven self-calibration and reconstruction for non-cartesian wave-encoded single-shot fast spin echo using deep learning.
data-driven
deep learning
parallel imaging and compressed sensing
single-shot fast spin echo
wave encoding
Journal
Journal of magnetic resonance imaging : JMRI
ISSN: 1522-2586
Titre abrégé: J Magn Reson Imaging
Pays: United States
ID NLM: 9105850
Informations de publication
Date de publication:
03 2020
03 2020
Historique:
received:
17
04
2019
accepted:
03
07
2019
pubmed:
20
7
2019
medline:
15
5
2021
entrez:
20
7
2019
Statut:
ppublish
Résumé
Current self-calibration and reconstruction methods for wave-encoded single-shot fast spin echo imaging (SSFSE) requires long computational time, especially when high accuracy is needed. To develop and investigate the clinical feasibility of data-driven self-calibration and reconstruction of wave-encoded SSFSE imaging for computation time reduction and quality improvement. Prospective controlled clinical trial. With Institutional Review Board approval, the proposed method was assessed on 29 consecutive adult patients (18 males, 11 females, range, 24-77 years). A wave-encoded variable-density SSFSE sequence was developed for clinical 3.0T abdominal scans to enable 3.5× acceleration with full-Fourier acquisitions. Data-driven calibration of wave-encoding point-spread function (PSF) was developed using a trained deep neural network. Data-driven reconstruction was developed with another set of neural networks based on the calibrated wave-encoding PSF. Training of the calibration and reconstruction networks was performed on 15,783 2D wave-encoded SSFSE abdominal images. Image quality of the proposed data-driven approach was compared independently and blindly with a conventional approach using iterative self-calibration and reconstruction with parallel imaging and compressed sensing by three radiologists on a scale from -2 to 2 for noise, contrast, sharpness, artifacts, and confidence. Computation time of these two approaches was also compared. Wilcoxon signed-rank tests were used to compare image quality and two-tailed t-tests were used to compare computation time with P values of under 0.05 considered statistically significant. An average 2.1-fold speedup in computation was achieved using the proposed method. The proposed data-driven self-calibration and reconstruction approach significantly reduced the perceived noise level (mean scores 0.82, P < 0.0001). The proposed data-driven calibration and reconstruction achieved twice faster computation with reduced perceived noise, providing a fast and robust self-calibration and reconstruction for clinical abdominal SSFSE imaging. 1 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2020;51:841-853.
Sections du résumé
BACKGROUND
Current self-calibration and reconstruction methods for wave-encoded single-shot fast spin echo imaging (SSFSE) requires long computational time, especially when high accuracy is needed.
PURPOSE
To develop and investigate the clinical feasibility of data-driven self-calibration and reconstruction of wave-encoded SSFSE imaging for computation time reduction and quality improvement.
STUDY TYPE
Prospective controlled clinical trial.
SUBJECTS
With Institutional Review Board approval, the proposed method was assessed on 29 consecutive adult patients (18 males, 11 females, range, 24-77 years).
FIELD STRENGTH/SEQUENCE
A wave-encoded variable-density SSFSE sequence was developed for clinical 3.0T abdominal scans to enable 3.5× acceleration with full-Fourier acquisitions. Data-driven calibration of wave-encoding point-spread function (PSF) was developed using a trained deep neural network. Data-driven reconstruction was developed with another set of neural networks based on the calibrated wave-encoding PSF. Training of the calibration and reconstruction networks was performed on 15,783 2D wave-encoded SSFSE abdominal images.
ASSESSMENT
Image quality of the proposed data-driven approach was compared independently and blindly with a conventional approach using iterative self-calibration and reconstruction with parallel imaging and compressed sensing by three radiologists on a scale from -2 to 2 for noise, contrast, sharpness, artifacts, and confidence. Computation time of these two approaches was also compared.
STATISTICAL TESTS
Wilcoxon signed-rank tests were used to compare image quality and two-tailed t-tests were used to compare computation time with P values of under 0.05 considered statistically significant.
RESULTS
An average 2.1-fold speedup in computation was achieved using the proposed method. The proposed data-driven self-calibration and reconstruction approach significantly reduced the perceived noise level (mean scores 0.82, P < 0.0001).
DATA CONCLUSION
The proposed data-driven calibration and reconstruction achieved twice faster computation with reduced perceived noise, providing a fast and robust self-calibration and reconstruction for clinical abdominal SSFSE imaging.
LEVEL OF EVIDENCE
1 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2020;51:841-853.
Identifiants
pubmed: 31322799
doi: 10.1002/jmri.26871
pmc: PMC8018814
mid: NIHMS1681001
doi:
Types de publication
Controlled Clinical Trial
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
841-853Subventions
Organisme : NIBIB NIH HHS
ID : R01 EB009690
Pays : United States
Organisme : NIBIB NIH HHS
ID : R01 EB019241
Pays : United States
Organisme : NHLBI NIH HHS
ID : R01 HL136965
Pays : United States
Informations de copyright
© 2019 International Society for Magnetic Resonance in Medicine.
Références
Magn Reson Med. 2007 Dec;58(6):1182-95
pubmed: 17969013
Magn Reson Med. 2008 Sep;60(3):640-9
pubmed: 18727082
Magn Reson Med. 2017 Nov;78(5):1757-1766
pubmed: 27943402
J Magn Reson Imaging. 2008 Nov;28(5):1219-25
pubmed: 18972330
Magn Reson Med. 2017 Sep;78(3):1093-1099
pubmed: 27770457
Radiology. 2018 Nov;289(2):366-373
pubmed: 30040039
J Magn Reson Imaging. 1996 Jul-Aug;6(4):698-9
pubmed: 8835965
IEEE Trans Med Imaging. 2018 Jun;37(6):1322-1332
pubmed: 29870362
IEEE Signal Process Mag. 2020 Jan;37(1):111-127
pubmed: 33192036
Magn Reson Med. 2018 Jun;79(6):3055-3071
pubmed: 29115689
J Magn Reson Imaging. 2014 Apr;39(4):745-67
pubmed: 24399498
J Magn Reson Imaging. 2018 Apr;47(4):954-966
pubmed: 28906567
Magn Reson Imaging. 2015 Feb;33(2):240-5
pubmed: 25447416
Magn Reson Med. 2015 Jun;73(6):2152-62
pubmed: 24986223
Magn Reson Med. 2014 Mar;71(3):990-1001
pubmed: 23649942
Magn Reson Med. 2019 Feb;81(2):1181-1190
pubmed: 30346058
Magn Reson Med. 2015 May;73(5):1775-85
pubmed: 24824404
Radiology. 2017 Feb;282(2):561-568
pubmed: 27564132
Magn Reson Med. 2015 Mar;73(3):929-938
pubmed: 25640187
J Magn Reson Imaging. 2015 Dec;42(6):1747-58
pubmed: 26094580
Radiology. 1986 Nov;161(2):527-31
pubmed: 3763926