PMID- 34438372
OWN - NLM
STAT- MEDLINE
DCOM- 20220127
LR  - 20220127
IS  - 2057-1976 (Electronic)
IS  - 2057-1976 (Linking)
VI  - 7
IP  - 6
DP  - 2021 Sep 6
TI  - Generation of attenuation correction factors from time-of-flight PET emission 
      data using high-resolution residual U-net.
LID - 10.1088/2057-1976/ac21aa [doi]
AB  - Attenuation correction of annihilation photons is essential in PET image 
      reconstruction for providing accurate quantitative activity maps. In the absence 
      of an aligned CT device to obtain attenuation information, we propose the 
      high-resolution residual U-net (HRU-Net) to extract attenuation correction 
      factors (ACF) directly from time-of-flight (TOF) PET emission data. HRU-Net is 
      built upon the U-Net encoding-decoding architecture and it utilizes four blocks 
      of modified residual connections in each stage. In each residual block, 
      concatenation is performed to incorporate input and output feature vectors. In 
      addition, flexible and efficient elements of convolutional neural network (CNN) 
      such as dilated convolutions, pre-activation order of a batch normalization (BN) 
      layer, a rectified linear unit (ReLU) layer and a convolution layer, and residual 
      connections are utilized to extract high resolution features. To illustrate the 
      effectiveness of the proposed method, HRU-Net estimated ACF, attenuation maps and 
      activity maps are compared with maximum likelihood ACF (MLACF) algorithm, U-Net, 
      and HC-Net. An ablation study is conducted using non-TOF and TOF sinograms as 
      inputs of networks. The experimental results show that HRU-Net with TOF 
      projections as inputs leads to normalized root mean square error (NRMSE) of 
      4.84% +/- 1.58%, outperforming MLACF, U-Net and HC-Net with NRMSE of 
      47.82% +/- 13.62%, 6.92% +/- 1.94%, and 7.99% +/- 2.49%, respectively.
CI  - (c) 2021 IOP Publishing Ltd.
FAU - Yin, Tuo
AU  - Yin T
AUID- ORCID: 0000-0002-8778-480X
AD  - Department of Information and Communications Engineering, Tokyo Institute of 
      Technology, Yokohama 226-8503, Japan.
FAU - Obi, Takashi
AU  - Obi T
AUID- ORCID: 0000-0001-9430-2728
AD  - Institute of Innovative Research, Tokyo Institute of Technology, Yokohama 
      226-8503, Japan.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20210906
PL  - England
TA  - Biomed Phys Eng Express
JT  - Biomedical physics & engineering express
JID - 101675002
SB  - IM
MH  - Algorithms
MH  - Neural Networks, Computer
MH  - *Positron-Emission Tomography
OTO - NOTNLM
OT  - attenuation correction
OT  - convolutional neural network (CNN)
OT  - deep learning
OT  - positron emission tomography (PET)
EDAT- 2021/08/27 06:00
MHDA- 2022/01/28 06:00
CRDT- 2021/08/26 20:30
PHST- 2021/03/30 00:00 [received]
PHST- 2021/08/26 00:00 [accepted]
PHST- 2021/08/27 06:00 [pubmed]
PHST- 2022/01/28 06:00 [medline]
PHST- 2021/08/26 20:30 [entrez]
AID - 10.1088/2057-1976/ac21aa [doi]
PST - epublish
SO  - Biomed Phys Eng Express. 2021 Sep 6;7(6). doi: 10.1088/2057-1976/ac21aa.