PMID- 32352197
OWN - NLM
STAT- MEDLINE
DCOM- 20210729
LR  - 20210729
IS  - 1099-1492 (Electronic)
IS  - 0952-3480 (Linking)
VI  - 33
IP  - 7
DP  - 2020 Jul
TI  - Deep complex convolutional network for fast reconstruction of 3D late gadolinium 
      enhancement cardiac MRI.
PG  - e4312
LID - 10.1002/nbm.4312 [doi]
AB  - Several deep-learning models have been proposed to shorten MRI scan time. Prior 
      deep-learning models that utilize real-valued kernels have limited capability to 
      learn rich representations of complex MRI data. In this work, we utilize a 
      complex-valued convolutional network (CNet) for fast reconstruction of highly 
      under-sampled MRI data and evaluate its ability to rapidly reconstruct 3D late 
      gadolinium enhancement (LGE) data. CNet preserves the complex nature and optimal 
      combination of real and imaginary components of MRI data throughout the 
      reconstruction process by utilizing complex-valued convolution, novel radial 
      batch normalization, and complex activation function layers in a U-Net 
      architecture. A prospectively under-sampled 3D LGE cardiac MRI dataset of 219 
      patients (17 003 images) at acceleration rates R = 3 through R = 5 was used to 
      evaluate CNet. The dataset was further retrospectively under-sampled to a maximum 
      of R = 8 to simulate higher acceleration rates. We created three reconstructions 
      of the 3D LGE dataset using (1) CNet, (2) a compressed-sensing-based 
      low-dimensional-structure self-learning and thresholding algorithm (LOST), and 
      (3) a real-valued U-Net (realNet) with the same number of parameters as CNet. 
      LOST-reconstructed data were considered the reference for training and evaluation 
      of all models. The reconstructed images were quantitatively evaluated using 
      mean-squared error (MSE) and the structural similarity index measure (SSIM), and 
      subjectively evaluated by three independent readers. Quantitatively, 
      CNet-reconstructed images had significantly improved MSE and SSIM values compared 
      with realNet (MSE, 0.077 versus 0.091; SSIM, 0.876 versus 0.733, respectively; p 
      < 0.01). Subjective quality assessment showed that CNet-reconstructed image 
      quality was similar to that of compressed sensing and significantly better than 
      that of realNet. CNet reconstruction was also more than 300 times faster than 
      compressed sensing. Retrospective under-sampled images demonstrate the potential 
      of CNet at higher acceleration rates. CNet enables fast reconstruction of highly 
      accelerated 3D MRI with superior performance to real-valued networks, and 
      achieves faster reconstruction than compressed sensing.
CI  - (c) 2020 John Wiley & Sons, Ltd.
FAU - El-Rewaidy, Hossam
AU  - El-Rewaidy H
AUID- ORCID: 0000-0002-5266-8702
AD  - Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical 
      Center and Harvard Medical School, Boston, Massachusetts.
AD  - Department of Computer Science, Technical University of Munich, Munich, Germany.
FAU - Neisius, Ulf
AU  - Neisius U
AD  - Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical 
      Center and Harvard Medical School, Boston, Massachusetts.
FAU - Mancio, Jennifer
AU  - Mancio J
AD  - Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical 
      Center and Harvard Medical School, Boston, Massachusetts.
FAU - Kucukseymen, Selcuk
AU  - Kucukseymen S
AD  - Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical 
      Center and Harvard Medical School, Boston, Massachusetts.
FAU - Rodriguez, Jennifer
AU  - Rodriguez J
AD  - Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical 
      Center and Harvard Medical School, Boston, Massachusetts.
FAU - Paskavitz, Amanda
AU  - Paskavitz A
AD  - Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical 
      Center and Harvard Medical School, Boston, Massachusetts.
FAU - Menze, Bjoern
AU  - Menze B
AD  - Department of Computer Science, Technical University of Munich, Munich, Germany.
FAU - Nezafat, Reza
AU  - Nezafat R
AD  - Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical 
      Center and Harvard Medical School, Boston, Massachusetts.
LA  - eng
GR  - R01 HL129185/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 - 20200430
PL  - England
TA  - NMR Biomed
JT  - NMR in biomedicine
JID - 8915233
RN  - AU0V1LM3JT (Gadolinium)
SB  - IM
MH  - Female
MH  - Gadolinium/*chemistry
MH  - Heart/*diagnostic imaging
MH  - Humans
MH  - Image Processing, Computer-Assisted
MH  - *Imaging, Three-Dimensional
MH  - *Magnetic Resonance Imaging
MH  - Male
MH  - Middle Aged
MH  - *Neural Networks, Computer
MH  - Numerical Analysis, Computer-Assisted
OTO - NOTNLM
OT  - MRI
OT  - complex convolutional network
OT  - deep learning
OT  - image reconstruction
OT  - late gadolinium enhancement
EDAT- 2020/05/01 06:00
MHDA- 2021/07/30 06:00
CRDT- 2020/05/01 06:00
PHST- 2019/09/05 00:00 [received]
PHST- 2020/03/19 00:00 [revised]
PHST- 2020/03/24 00:00 [accepted]
PHST- 2020/05/01 06:00 [pubmed]
PHST- 2021/07/30 06:00 [medline]
PHST- 2020/05/01 06:00 [entrez]
AID - 10.1002/nbm.4312 [doi]
PST - ppublish
SO  - NMR Biomed. 2020 Jul;33(7):e4312. doi: 10.1002/nbm.4312. Epub 2020 Apr 30.