PMID- 30166355
OWN - NLM
STAT- MEDLINE
DCOM- 20200319
LR  - 20200319
IS  - 1535-5667 (Electronic)
IS  - 0161-5505 (Linking)
VI  - 60
IP  - 4
DP  - 2019 Apr
TI  - Synthesis of Patient-Specific Transmission Data for PET Attenuation Correction 
      for PET/MRI Neuroimaging Using a Convolutional Neural Network.
PG  - 555-560
LID - 10.2967/jnumed.118.214320 [doi]
AB  - Attenuation correction is a notable challenge associated with simultaneous 
      PET/MRI, particularly in neuroimaging, where sharp boundaries between air and 
      bone volumes exist. This challenge leads to concerns about the visual and, more 
      specifically, quantitative accuracy of PET reconstructions for data obtained with 
      PET/MRI. Recently developed techniques can synthesize attenuation maps using only 
      MRI data and are likely adequate for clinical use; however, little work has been 
      conducted to assess their suitability for the dynamic PET studies frequently used 
      in research to derive physiologic information such as the binding potential of 
      neuroreceptors in a region. At the same time, existing PET/MRI attenuation 
      correction methods are predicated on synthesizing CT data, which is not ideal, as 
      CT data are acquired with much lower-energy photons than PET data and thus do not 
      optimally reflect the PET attenuation map. Methods: We trained a convolutional 
      neural network to generate patient-specific transmission data from T1-weighted 
      MRI. Using the trained network, we generated transmission data for a testing set 
      comprising 11 subjects scanned with (11)C-labeled 
      N-[2-]4-(2-methoxyphenyl)-1-piperazinyl]ethyl]-N-(2-pyridinyl)cyclohexanecarboxamide) 
      ((11)C-WAY-100635) and 10 subjects scanned with (11)C-labeled 
      3-amino-4-(2-dimethylaminomethyl-phenylsulfanyl)benzonitrile ((11)C-DASB). We 
      assessed both static and dynamic reconstructions. For dynamic PET data, we report 
      differences in both the nondisplaceable and the free binding potential for 
      (11)C-WAY-100635 and distribution volume for (11)C-DASB. Results: The mean bias 
      for generated transmission data was -1.06% +/- 0.81%. Global biases in static PET 
      uptake were -0.49% +/- 1.7%, and -1.52% +/- 0.73% for (11)C-WAY-100635 and 
      (11)C-DASB, respectively. Conclusion: Our neural network approach is capable of 
      synthesizing patient-specific transmission data with sufficient accuracy for both 
      static and dynamic PET studies.
CI  - (c) 2019 by the Society of Nuclear Medicine and Molecular Imaging.
FAU - Spuhler, Karl D
AU  - Spuhler KD
AD  - Department of Biomedical Engineering, Stony Brook University, Stony Brook, New 
      York.
FAU - Gardus, John 3rd
AU  - Gardus J 3rd
AD  - Department of Psychiatry, Stony Brook University Medical Center, Stony Brook, New 
      York.
FAU - Gao, Yi
AU  - Gao Y
AD  - Health Science Center, Shenzhen University, Guangdong, China; and.
FAU - DeLorenzo, Christine
AU  - DeLorenzo C
AD  - Department of Psychiatry, Stony Brook University Medical Center, Stony Brook, New 
      York.
FAU - Parsey, Ramin
AU  - Parsey R
AD  - Department of Psychiatry, Stony Brook University Medical Center, Stony Brook, New 
      York.
FAU - Huang, Chuan
AU  - Huang C
AD  - Department of Biomedical Engineering, Stony Brook University, Stony Brook, New 
      York chuan.huang@stonybrookmedicine.edu.
AD  - Department of Psychiatry, Stony Brook University Medical Center, Stony Brook, New 
      York.
AD  - Department of Radiology, Stony Brook University Medical Center, Stony Brook, New 
      York.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20180830
PL  - United States
TA  - J Nucl Med
JT  - Journal of nuclear medicine : official publication, Society of Nuclear Medicine
JID - 0217410
RN  - 0 (3-amino-4-(2-dimethylaminomethylphenylsulfanyl)benzonitrile)
RN  - 0 (Aniline Compounds)
RN  - 0 (Piperazines)
RN  - 0 (Pyridines)
RN  - 0 (Radioactive Tracers)
RN  - 0 (Sulfides)
RN  - 71IH826FEG 
      (N-(2-(4-(2-methoxyphenyl)-1-piperazinyl)ethyl)-N-(2-pyridinyl)cyclohexanecarboxamide)
SB  - IM
MH  - Aniline Compounds
MH  - Humans
MH  - Image Processing, Computer-Assisted/*methods
MH  - *Magnetic Resonance Imaging
MH  - Multimodal Imaging
MH  - *Neural Networks, Computer
MH  - *Neuroimaging
MH  - Piperazines
MH  - *Positron-Emission Tomography
MH  - Pyridines
MH  - Radioactive Tracers
MH  - Retrospective Studies
MH  - Sulfides
OTO - NOTNLM
OT  - PET/MRI
OT  - attenuation correction
OT  - deep learning
OT  - image processing
OT  - image reconstruction
OT  - kinetic modeling
EDAT- 2018/09/01 06:00
MHDA- 2020/03/20 06:00
CRDT- 2018/09/01 06:00
PHST- 2018/05/10 00:00 [received]
PHST- 2018/08/23 00:00 [accepted]
PHST- 2018/09/01 06:00 [pubmed]
PHST- 2020/03/20 06:00 [medline]
PHST- 2018/09/01 06:00 [entrez]
AID - jnumed.118.214320 [pii]
AID - 10.2967/jnumed.118.214320 [doi]
PST - ppublish
SO  - J Nucl Med. 2019 Apr;60(4):555-560. doi: 10.2967/jnumed.118.214320. Epub 2018 Aug 
      30.