PMID- 33584973
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20210217
IS  - 1945-7928 (Print)
IS  - 1945-8452 (Electronic)
IS  - 1945-7928 (Linking)
VI  - 2018
DP  - 2018 Apr
TI  - MODEL BASED IMAGE RECONSTRUCTION USING DEEP LEARNED PRIORS (MODL).
PG  - 671-674
LID - 10.1109/isbi.2018.8363663 [doi]
AB  - We introduce a model-based image reconstruction framework, where we use a deep 
      convolution neural network (CNN) based regularization prior. We rely on a 
      recursive algorithm, which alternates between a CNN based denoising step and 
      enforcement of data consistency. Unrolling the recursive algorithm yields a deep 
      network that is trained using backpropagation. The unique aspect of this method 
      is the use of the same CNN weights at each iteration, which makes the resulting 
      structure consistent with the model-based formulation. Also, this approach 
      reduces the number of trainable parameters, which hence lower the amount of 
      training data needed. The use of a forward model also reduces the size of the 
      network and enables the exploitation additional prior information available from 
      calibration data. The use of the framework for multichannel MRI reconstruction 
      provides improved reconstructions, compared to other state-of-the-art methods.
FAU - Aggarwal, Hemant Kumar
AU  - Aggarwal HK
AD  - University of Iowa, Iowa, USA.
FAU - Mani, Merry P
AU  - Mani MP
AD  - University of Iowa, Iowa, USA.
FAU - Jacob, Mathews
AU  - Jacob M
AD  - University of Iowa, Iowa, USA.
LA  - eng
GR  - R01 EB019961/EB/NIBIB NIH HHS/United States
PT  - Journal Article
DEP - 20180524
PL  - United States
TA  - Proc IEEE Int Symp Biomed Imaging
JT  - Proceedings. IEEE International Symposium on Biomedical Imaging
JID - 101492570
PMC - PMC7876898
MID - NIHMS1667933
OTO - NOTNLM
OT  - Deep learning
OT  - convolutional neural network
OT  - parallel imaging
EDAT- 2018/04/01 00:00
MHDA- 2018/04/01 00:01
PMCR- 2021/02/11
CRDT- 2021/02/15 06:09
PHST- 2021/02/15 06:09 [entrez]
PHST- 2018/04/01 00:00 [pubmed]
PHST- 2018/04/01 00:01 [medline]
PHST- 2021/02/11 00:00 [pmc-release]
AID - 10.1109/isbi.2018.8363663 [doi]
PST - ppublish
SO  - Proc IEEE Int Symp Biomed Imaging. 2018 Apr;2018:671-674. doi: 
      10.1109/isbi.2018.8363663. Epub 2018 May 24.