PMID- 34939246
OWN - NLM
STAT- MEDLINE
DCOM- 20220412
LR  - 20220603
IS  - 1099-1492 (Electronic)
IS  - 0952-3480 (Linking)
VI  - 35
IP  - 5
DP  - 2022 May
TI  - DEep learning-based rapid Spiral Image REconstruction (DESIRE) for 
      high-resolution spiral first-pass myocardial perfusion imaging.
PG  - e4661
LID - 10.1002/nbm.4661 [doi]
AB  - The objective of the current study was to develop and evaluate a DEep 
      learning-based rapid Spiral Image REconstruction (DESIRE) technique for 
      high-resolution spiral first-pass myocardial perfusion imaging with whole-heart 
      coverage, to provide fast and accurate image reconstruction for both single-slice 
      (SS) and simultaneous multislice (SMS) acquisitions. Three-dimensional 
      U-Net-based image enhancement architectures were evaluated for high-resolution 
      spiral perfusion imaging at 3 T. The SS and SMS MB = 2 networks were trained on 
      SS perfusion images from 156 slices from 20 subjects. Structural similarity index 
      (SSIM), peak signal-to-noise ratio (PSNR), and normalized root mean square error 
      (NRMSE) were assessed, and prospective images were blindly graded by two 
      experienced cardiologists (5: excellent; 1: poor). Excellent performance was 
      demonstrated for the proposed technique. For SS, SSIM, PSNR, and NRMSE were 0.977 
      [0.972, 0.982], 42.113 [40.174, 43.493] dB, and 0.102 [0.080, 0.125], 
      respectively, for the best network. For SMS MB = 2 retrospective data, SSIM, 
      PSNR, and NRMSE were 0.961 [0.950, 0.969], 40.834 [39.619, 42.004] dB, and 0.107 
      [0.086, 0.133], respectively, for the best network. The image quality scores were 
      4.5 [4.1, 4.8], 4.5 [4.3, 4.6], 3.5 [3.3, 4], and 3.5 [3.3, 3.8] for SS DESIRE, 
      SS L1-SPIRiT, MB = 2 DESIRE, and MB = 2 SMS-slice-L1-SPIRiT, respectively, 
      showing no statistically significant difference (p = 1 and p = 1 for SS and SMS, 
      respectively) between L1-SPIRiT and the proposed DESIRE technique. The network 
      inference time was ~100 ms per dynamic perfusion series with DESIRE, while the 
      reconstruction time of L1-SPIRiT with GPU acceleration was ~ 30 min. It was 
      concluded that DESIRE enabled fast and high-quality image reconstruction for both 
      SS and SMS MB = 2 whole-heart high-resolution spiral perfusion imaging.
CI  - (c) 2021 John Wiley & Sons, Ltd.
FAU - Wang, Junyu
AU  - Wang J
AUID- ORCID: 0000-0001-8314-4525
AD  - Department of Biomedical Engineering, University of Virginia, Charlottesville, 
      Virginia, USA.
FAU - Weller, Daniel S
AU  - Weller DS
AD  - Department of Electrical and Computer Engineering, University of Virginia, 
      Charlottesville, Virginia, USA.
FAU - Kramer, Christopher M
AU  - Kramer CM
AD  - Department of Medicine, Cardiovascular Division, University of Virginia Health 
      System, Charlottesville, Virginia, USA.
AD  - Radiology and Medical Imaging, University of Virginia Health System, 
      Charlottesville, Virginia, USA.
FAU - Salerno, Michael
AU  - Salerno M
AD  - Department of Biomedical Engineering, University of Virginia, Charlottesville, 
      Virginia, USA.
AD  - Department of Medicine, Cardiovascular Division, University of Virginia Health 
      System, Charlottesville, Virginia, USA.
AD  - Radiology and Medical Imaging, University of Virginia Health System, 
      Charlottesville, Virginia, USA.
AD  - Departments of Medicine and Radiology, Stanford University Medical Center, 
      Stanford, California, USA.
LA  - eng
GR  - R01 HL131919/HL/NHLBI NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
PT  - Research Support, Non-U.S. Gov't
DEP - 20211222
PL  - England
TA  - NMR Biomed
JT  - NMR in biomedicine
JID - 8915233
SB  - IM
MH  - *Deep Learning
MH  - Humans
MH  - Image Processing, Computer-Assisted
MH  - Magnetic Resonance Imaging
MH  - *Myocardial Perfusion Imaging/methods
MH  - Prospective Studies
MH  - Retrospective Studies
OTO - NOTNLM
OT  - deep learning
OT  - first-pass perfusion
OT  - image reconstruction
OT  - spiral
EDAT- 2021/12/24 06:00
MHDA- 2022/04/13 06:00
CRDT- 2021/12/23 06:08
PHST- 2021/11/01 00:00 [revised]
PHST- 2021/05/28 00:00 [received]
PHST- 2021/11/16 00:00 [accepted]
PHST- 2021/12/24 06:00 [pubmed]
PHST- 2022/04/13 06:00 [medline]
PHST- 2021/12/23 06:08 [entrez]
AID - 10.1002/nbm.4661 [doi]
PST - ppublish
SO  - NMR Biomed. 2022 May;35(5):e4661. doi: 10.1002/nbm.4661. Epub 2021 Dec 22.