Texture‐aware dual domain mapping model for low‐dose CT reconstruction

Background Remarkable progress has been made for low‐dose computed tomography (CT) reconstruction tasks by applying deep learning techniques. However, establishing an intrinsic link between deep learning techniques and CT texture preservation is still one of the significant challenges for researcher...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Medical physics (Lancaster) Jg. 49; H. 6; S. 3860 - 3873
Hauptverfasser: Wang, Huafeng, Zhao, Xuemei, Liu, Wanquan, Li, Lihong C., Ma, Jianhua, Guo, Lei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States 01.06.2022
Schlagworte:
ISSN:0094-2405, 2473-4209, 2473-4209
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Background Remarkable progress has been made for low‐dose computed tomography (CT) reconstruction tasks by applying deep learning techniques. However, establishing an intrinsic link between deep learning techniques and CT texture preservation is still one of the significant challenges for researchers to further improve the effect of low‐dose CT (LDCT) reconstruction. Purpose Most of the existing deep learning‐based LDCT reconstruction methods are derived from popular frameworks, and most models focus on the image domain. Even few existing methods start with dual domains (sinogram and image) by considering the processing of the data itself, the final performances are limited due to the lack of perception of textures. With this in mind, we propose a method for texture perception on dual domains, so that the reconstruction process can be uniformly driven by visual effects. Methods The proposed method involves the processing of two domains: the sinogram domain and the image domain. For the sinogram domain, we have designed a novel dilated residual network (S‐DRN) which aims to increase the receptive field to obtain multiscale information. For the image domain, we propose a self‐attention (SA) residual encoder & decoder network (SRED‐Net) as the denoising network for obtaining much acceptable edges and textures. In addition, the composite loss function composed of the feature loss constructed by the proposed boundary and texture feature‐aware network (BTFAN) and the mean square error (MSE) can obtain a higher image quality while retaining more details and fewer artifacts, thereby obtaining better visual image quality. Results The proposed method was validated using both the American association of physicists in medicine (AAPM)‐Mayo clinic LDCT data sets and a real clinic data. Experimental results demonstrated that the new method has achieved the state‐of‐the‐art performance on objective indicators and visual metrics in terms of denoising and texture restoration. Conclusions Compared with single‐domain or existing dual‐domain processing strategies, the proposed texture‐aware dual domain mapping network (TADDM‐Net) can much better improve the visual effect of reconstructed CT images. Meantime, we also provide much intuitive evidence in terms of model interpretability.
AbstractList Remarkable progress has been made for low-dose computed tomography (CT) reconstruction tasks by applying deep learning techniques. However, establishing an intrinsic link between deep learning techniques and CT texture preservation is still one of the significant challenges for researchers to further improve the effect of low-dose CT (LDCT) reconstruction. Most of the existing deep learning-based LDCT reconstruction methods are derived from popular frameworks, and most models focus on the image domain. Even few existing methods start with dual domains (sinogram and image) by considering the processing of the data itself, the final performances are limited due to the lack of perception of textures. With this in mind, we propose a method for texture perception on dual domains, so that the reconstruction process can be uniformly driven by visual effects. The proposed method involves the processing of two domains: the sinogram domain and the image domain. For the sinogram domain, we have designed a novel dilated residual network (S-DRN) which aims to increase the receptive field to obtain multiscale information. For the image domain, we propose a self-attention (SA) residual encoder & decoder network (SRED-Net) as the denoising network for obtaining much acceptable edges and textures. In addition, the composite loss function composed of the feature loss constructed by the proposed boundary and texture feature-aware network (BTFAN) and the mean square error (MSE) can obtain a higher image quality while retaining more details and fewer artifacts, thereby obtaining better visual image quality. The proposed method was validated using both the American association of physicists in medicine (AAPM)-Mayo clinic LDCT data sets and a real clinic data. Experimental results demonstrated that the new method has achieved the state-of-the-art performance on objective indicators and visual metrics in terms of denoising and texture restoration. Compared with single-domain or existing dual-domain processing strategies, the proposed texture-aware dual domain mapping network (TADDM-Net) can much better improve the visual effect of reconstructed CT images. Meantime, we also provide much intuitive evidence in terms of model interpretability.
Remarkable progress has been made for low-dose computed tomography (CT) reconstruction tasks by applying deep learning techniques. However, establishing an intrinsic link between deep learning techniques and CT texture preservation is still one of the significant challenges for researchers to further improve the effect of low-dose CT (LDCT) reconstruction.BACKGROUNDRemarkable progress has been made for low-dose computed tomography (CT) reconstruction tasks by applying deep learning techniques. However, establishing an intrinsic link between deep learning techniques and CT texture preservation is still one of the significant challenges for researchers to further improve the effect of low-dose CT (LDCT) reconstruction.Most of the existing deep learning-based LDCT reconstruction methods are derived from popular frameworks, and most models focus on the image domain. Even few existing methods start with dual domains (sinogram and image) by considering the processing of the data itself, the final performances are limited due to the lack of perception of textures. With this in mind, we propose a method for texture perception on dual domains, so that the reconstruction process can be uniformly driven by visual effects.PURPOSEMost of the existing deep learning-based LDCT reconstruction methods are derived from popular frameworks, and most models focus on the image domain. Even few existing methods start with dual domains (sinogram and image) by considering the processing of the data itself, the final performances are limited due to the lack of perception of textures. With this in mind, we propose a method for texture perception on dual domains, so that the reconstruction process can be uniformly driven by visual effects.The proposed method involves the processing of two domains: the sinogram domain and the image domain. For the sinogram domain, we have designed a novel dilated residual network (S-DRN) which aims to increase the receptive field to obtain multiscale information. For the image domain, we propose a self-attention (SA) residual encoder & decoder network (SRED-Net) as the denoising network for obtaining much acceptable edges and textures. In addition, the composite loss function composed of the feature loss constructed by the proposed boundary and texture feature-aware network (BTFAN) and the mean square error (MSE) can obtain a higher image quality while retaining more details and fewer artifacts, thereby obtaining better visual image quality.METHODSThe proposed method involves the processing of two domains: the sinogram domain and the image domain. For the sinogram domain, we have designed a novel dilated residual network (S-DRN) which aims to increase the receptive field to obtain multiscale information. For the image domain, we propose a self-attention (SA) residual encoder & decoder network (SRED-Net) as the denoising network for obtaining much acceptable edges and textures. In addition, the composite loss function composed of the feature loss constructed by the proposed boundary and texture feature-aware network (BTFAN) and the mean square error (MSE) can obtain a higher image quality while retaining more details and fewer artifacts, thereby obtaining better visual image quality.The proposed method was validated using both the American association of physicists in medicine (AAPM)-Mayo clinic LDCT data sets and a real clinic data. Experimental results demonstrated that the new method has achieved the state-of-the-art performance on objective indicators and visual metrics in terms of denoising and texture restoration.RESULTSThe proposed method was validated using both the American association of physicists in medicine (AAPM)-Mayo clinic LDCT data sets and a real clinic data. Experimental results demonstrated that the new method has achieved the state-of-the-art performance on objective indicators and visual metrics in terms of denoising and texture restoration.Compared with single-domain or existing dual-domain processing strategies, the proposed texture-aware dual domain mapping network (TADDM-Net) can much better improve the visual effect of reconstructed CT images. Meantime, we also provide much intuitive evidence in terms of model interpretability.CONCLUSIONSCompared with single-domain or existing dual-domain processing strategies, the proposed texture-aware dual domain mapping network (TADDM-Net) can much better improve the visual effect of reconstructed CT images. Meantime, we also provide much intuitive evidence in terms of model interpretability.
Background Remarkable progress has been made for low‐dose computed tomography (CT) reconstruction tasks by applying deep learning techniques. However, establishing an intrinsic link between deep learning techniques and CT texture preservation is still one of the significant challenges for researchers to further improve the effect of low‐dose CT (LDCT) reconstruction. Purpose Most of the existing deep learning‐based LDCT reconstruction methods are derived from popular frameworks, and most models focus on the image domain. Even few existing methods start with dual domains (sinogram and image) by considering the processing of the data itself, the final performances are limited due to the lack of perception of textures. With this in mind, we propose a method for texture perception on dual domains, so that the reconstruction process can be uniformly driven by visual effects. Methods The proposed method involves the processing of two domains: the sinogram domain and the image domain. For the sinogram domain, we have designed a novel dilated residual network (S‐DRN) which aims to increase the receptive field to obtain multiscale information. For the image domain, we propose a self‐attention (SA) residual encoder & decoder network (SRED‐Net) as the denoising network for obtaining much acceptable edges and textures. In addition, the composite loss function composed of the feature loss constructed by the proposed boundary and texture feature‐aware network (BTFAN) and the mean square error (MSE) can obtain a higher image quality while retaining more details and fewer artifacts, thereby obtaining better visual image quality. Results The proposed method was validated using both the American association of physicists in medicine (AAPM)‐Mayo clinic LDCT data sets and a real clinic data. Experimental results demonstrated that the new method has achieved the state‐of‐the‐art performance on objective indicators and visual metrics in terms of denoising and texture restoration. Conclusions Compared with single‐domain or existing dual‐domain processing strategies, the proposed texture‐aware dual domain mapping network (TADDM‐Net) can much better improve the visual effect of reconstructed CT images. Meantime, we also provide much intuitive evidence in terms of model interpretability.
Author Guo, Lei
Liu, Wanquan
Wang, Huafeng
Ma, Jianhua
Zhao, Xuemei
Li, Lihong C.
Author_xml – sequence: 1
  givenname: Huafeng
  surname: Wang
  fullname: Wang, Huafeng
  organization: North China University of Technology
– sequence: 2
  givenname: Xuemei
  surname: Zhao
  fullname: Zhao, Xuemei
  organization: North China University of Technology
– sequence: 3
  givenname: Wanquan
  surname: Liu
  fullname: Liu, Wanquan
  email: liuwq63@mail.sysu.edu.cn
  organization: Sun Yat‐sen University
– sequence: 4
  givenname: Lihong C.
  surname: Li
  fullname: Li, Lihong C.
  organization: Department of Engineering and Environmental Science, City University of New York at College of Staten Island
– sequence: 5
  givenname: Jianhua
  surname: Ma
  fullname: Ma, Jianhua
  organization: Department of Biomedical Engineering, Southern Medical University
– sequence: 6
  givenname: Lei
  surname: Guo
  fullname: Guo, Lei
  organization: Beihang University
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35297051$$D View this record in MEDLINE/PubMed
BookMark eNp1kMtOwzAQRS0Eog-Q-AKUJZuUsWPHyRJVPFUEi7KOHGeCguI42IlKd3wC38iX0NICEoLVbM49o3tHZLexDRJyRGFCAdipaSdUxCB3yJBxGYWcQbpLhgApDxkHMSAj758AII4E7JNBJFgqQdAhuZnjS9c7fH99UwvlMCh6VQeFNapqAqPatmoeA2MLrIPSuqC2ixVZWI_BdB441Lbxnet1V9nmgOyVqvZ4uL1j8nBxPp9ehbO7y-vp2SzUEaMyxJwjTTRLhdBMxolCSjnVqSgxApVQqXNWRpLmWHLNhY6TokwVhSSXvFCJiMbkZONtnX3u0XeZqbzGulYN2t5nLOaw_kTX6PEW7XODRda6yii3zL76_7i0s947LL8RCtl62sy02ee0K3TyC9VVp9bFO6eq-q9AuAksqhqX_4qz2_sN_wGDQong
CitedBy_id crossref_primary_10_1109_ACCESS_2025_3585001
crossref_primary_10_1007_s10278_023_00934_6
crossref_primary_10_1016_j_media_2024_103420
crossref_primary_10_3390_bioengineering11090874
crossref_primary_10_1007_s44163_025_00419_1
crossref_primary_10_1109_JBHI_2023_3348436
crossref_primary_10_1016_j_eswa_2023_120001
crossref_primary_10_1016_j_knosys_2022_109295
crossref_primary_10_1002_acm2_14270
Cites_doi 10.1038/s42256-019-0057-9
10.1109/TMI.2012.2187213
10.1109/CVPR.2016.90
10.1109/TMI.2017.2715284
10.1109/TMI.2006.875429
10.1002/mp.12344
10.1109/TMI.2020.2968472
10.1109/ICAIBD49809.2020.9137456
10.1109/TMI.2019.2917258
10.1007/s11263-007-0110-8
10.1109/TMI.2018.2827462
10.1364/BOE.8.000679
10.1021/acs.jpca.8b08584
10.1109/CVPR.2019.01076
10.1088/0031-9155/53/17/021
10.1109/TIP.2005.859389
10.1056/NEJMoa1301851
10.1109/TMI.2019.2959609
10.1109/BIA50171.2020.9244282
10.1118/1.4851635
10.1109/TMI.2018.2823756
10.1007/s00330-018-5829-9
10.1109/42.993128
10.1088/0031-9155/55/18/009
10.1088/1361-6560/ab8fc1
10.1109/TNS.2016.2611624
10.1118/1.2836950
10.1109/TNS.2015.2467219
10.1056/NEJMra072149
10.2214/AJR.09.2989
10.1109/ICCV.2019.00280
ContentType Journal Article
Copyright 2022 American Association of Physicists in Medicine.
Copyright_xml – notice: 2022 American Association of Physicists in Medicine.
DBID AAYXX
CITATION
NPM
7X8
DOI 10.1002/mp.15607
DatabaseName CrossRef
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList PubMed
MEDLINE - Academic

Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Physics
EISSN 2473-4209
EndPage 3873
ExternalDocumentID 35297051
10_1002_mp_15607
MP15607
Genre article
Journal Article
GrantInformation_xml – fundername: Beijing Municipal Education Commission Scientific Research Program
  funderid: KM202110009001
– fundername: Hebei Provincial Science and Technology Plan Project
  funderid: 203777116D
– fundername: Beijing Municipal Education Commission Scientific Research Program
  grantid: KM202110009001
– fundername: Hebei Provincial Science and Technology Plan Project
  grantid: 203777116D
GroupedDBID ---
--Z
-DZ
.GJ
0R~
1OB
1OC
29M
2WC
33P
36B
3O-
4.4
53G
5GY
5RE
5VS
AAHHS
AAHQN
AAIPD
AAMNL
AANLZ
AAQQT
AASGY
AAXRX
AAYCA
AAZKR
ABCUV
ABDPE
ABEFU
ABFTF
ABJNI
ABLJU
ABQWH
ABTAH
ABXGK
ACAHQ
ACBEA
ACCFJ
ACCZN
ACGFO
ACGFS
ACGOF
ACPOU
ACXBN
ACXQS
ADBBV
ADBTR
ADKYN
ADOZA
ADXAS
ADZMN
AEEZP
AEGXH
AEIGN
AENEX
AEQDE
AEUYR
AFBPY
AFFPM
AFWVQ
AHBTC
AIACR
AIAGR
AITYG
AIURR
AIWBW
AJBDE
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMYDB
ASPBG
BFHJK
C45
CS3
DCZOG
DRFUL
DRMAN
DRSTM
DU5
EBD
EBS
EJD
EMB
EMOBN
F5P
HDBZQ
HGLYW
I-F
KBYEO
LATKE
LEEKS
LOXES
LUTES
LYRES
MEWTI
O9-
OVD
P2P
P2W
PALCI
PHY
RJQFR
RNS
ROL
SAMSI
SUPJJ
SV3
TEORI
TN5
TWZ
USG
WOHZO
WXSBR
XJT
ZGI
ZVN
ZXP
ZY4
ZZTAW
AAMMB
AAYXX
ABUFD
ADMLS
AEFGJ
AEYWJ
AGHNM
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
LH4
NPM
7X8
ID FETCH-LOGICAL-c3217-eb4e18c2955c2768ae1141c95fe30a817cb2f371bef4c45c68df9a108b74da853
IEDL.DBID DRFUL
ISICitedReferencesCount 8
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000776351900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0094-2405
2473-4209
IngestDate Sun Nov 09 14:20:42 EST 2025
Wed Feb 19 02:26:47 EST 2025
Sat Nov 29 06:02:50 EST 2025
Tue Nov 18 21:41:32 EST 2025
Wed Jan 22 16:24:10 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 6
Keywords denoising
dual domain
texture preservation
CT reconstruction
Language English
License 2022 American Association of Physicists in Medicine.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3217-eb4e18c2955c2768ae1141c95fe30a817cb2f371bef4c45c68df9a108b74da853
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 35297051
PQID 2640321715
PQPubID 23479
PageCount 14
ParticipantIDs proquest_miscellaneous_2640321715
pubmed_primary_35297051
crossref_primary_10_1002_mp_15607
crossref_citationtrail_10_1002_mp_15607
wiley_primary_10_1002_mp_15607_MP15607
PublicationCentury 2000
PublicationDate June 2022
PublicationDateYYYYMMDD 2022-06-01
PublicationDate_xml – month: 06
  year: 2022
  text: June 2022
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Medical physics (Lancaster)
PublicationTitleAlternate Med Phys
PublicationYear 2022
References 2010; 55
2017; 8
2017; 1
2009; 81
2017; 2017
2019; 1
2013; 369
2017; 44
2020; 39
2019; 38
2008; 35
2016; 2016
2008; 53
2014; 41
2019; 123
2012; 31
2007; 357
2017; 36
2015; 62
2020
2002; 21
2006; 25
2019
2019; 29
2017
2016
2015
2010; 195
2014
2020; 65
2018; 37
2005; 14
e_1_2_9_30_1
e_1_2_9_31_1
e_1_2_9_11_1
e_1_2_9_34_1
e_1_2_9_10_1
e_1_2_9_35_1
e_1_2_9_13_1
e_1_2_9_32_1
e_1_2_9_12_1
e_1_2_9_33_1
e_1_2_9_15_1
e_1_2_9_14_1
e_1_2_9_17_1
e_1_2_9_36_1
e_1_2_9_16_1
e_1_2_9_37_1
e_1_2_9_19_1
e_1_2_9_18_1
e_1_2_9_20_1
e_1_2_9_22_1
e_1_2_9_21_1
e_1_2_9_24_1
e_1_2_9_23_1
e_1_2_9_8_1
e_1_2_9_7_1
e_1_2_9_6_1
e_1_2_9_5_1
e_1_2_9_4_1
e_1_2_9_3_1
e_1_2_9_2_1
e_1_2_9_9_1
e_1_2_9_26_1
e_1_2_9_25_1
Vaswani A (e_1_2_9_27_1) 2017; 2017
e_1_2_9_28_1
e_1_2_9_29_1
References_xml – volume: 37
  start-page: 1348
  issue: 6
  year: 2018
  end-page: 1357
  article-title: Low‐dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss
  publication-title: IEEE Trans Med Imaging
– year: 2015
  article-title: Very deep convolutional networks for large‐scale image recognition
– volume: 8
  start-page: 679
  issue: 2
  year: 2017
  end-page: 694
  article-title: Low‐dose CT via convolutional neural network
  publication-title: Biomed Opt Express
– volume: 1
  start-page: 269
  issue: 6
  year: 2019
  end-page: 276
  article-title: Competitive performance of a modularized deep neural network compared to commercial algorithms for low‐dose CT image reconstruction
  publication-title: Nat Mach Intell
– volume: 357
  start-page: 2277
  issue: 22
  year: 2007
  end-page: 2284
  article-title: Computed tomography—an increasing source of radiation exposure
  publication-title: N Engl J Med
– volume: 44
  start-page: e360
  issue: 10
  year: 2017
  end-page: e375
  article-title: A deep convolutional neural network using directional wavelets for low‐dose X‐ray CT reconstruction
  publication-title: Med Phys
– volume: 195
  start-page: 713
  issue: 3
  year: 2010
  end-page: 719
  article-title: Abdominal CT: comparison of low‐dose CT with adaptive statistical iterative reconstruction and routine‐dose CT with filtered back projection in 53 patients
  publication-title: AJR Am J Roentgenol
– volume: 123
  start-page: 943
  issue: 4
  year: 2019
  end-page: 950
  article-title: Algebraic reconstruction technique for diffusion NMR experiments. Application to the molecular weight prediction of polymers
  publication-title: J Phys Chem A
– volume: 35
  start-page: 1051
  issue: 3
  year: 2008
  end-page: 1064
  article-title: An outlook on x‐ray CT research and development
  publication-title: Med Phys
– year: 2016
  article-title: Multi‐scale context aggregation by dilated convolutions
– start-page: 2710
  year: 2019
  end-page: 2719
  article-title: SROBB: targeted perceptual loss for single image super‐resolution
– volume: 37
  start-page: 1358
  issue: 6
  year: 2018
  end-page: 1369
  article-title: Deep convolutional framelet denosing for low‐dose CT via wavelet residual network
  publication-title: IEEE Trans Med Imaging
– volume: 38
  start-page: 2903
  issue: 12
  year: 2019
  end-page: 2913
  article-title: Domain progressive 3D residual convolution network to improve low‐dose CT imaging
  publication-title: IEEE Trans Med Imaging
– volume: 31
  start-page: 1228
  issue: 6
  year: 2012
  end-page: 1239
  article-title: Ray contribution masks for structure adaptive sinogram filtering
  publication-title: IEEE Trans Med Imaging
– volume: 62
  start-page: 2226
  issue: 5
  year: 2015
  end-page: 2233
  article-title: A simple low‐dose X‐ray CT simulation from high‐dose scan
  publication-title: IEEE Trans Nucl Sci
– year: 2014
– volume: 2017
  start-page: 5999
  year: 2017
  end-page: 6009
  article-title: Attention is all you need
  publication-title: Adv Neural Inf Process Syst
– volume: 55
  start-page: 5401
  issue: 18
  year: 2010
  end-page: 5415
  article-title: Block matching 3D random noise filtering for absorption optical projection tomography
  publication-title: Phys Med Biol
– volume: 81
  start-page: 24
  issue: 1
  year: 2009
  end-page: 52
  article-title: A fast approximation of the bilateral filter using a signal processing approach
  publication-title: Int J Comput Vis
– volume: 29
  start-page: 4008
  issue: 8
  year: 2019
  end-page: 4015
  article-title: CT reconstruction algorithms affect histogram and texture analysis: evidence for liver parenchyma, focal solid liver lesions, and renal cysts
  publication-title: Eur. Radiol.
– volume: 39
  start-page: 2289
  issue: 7
  year: 2020
  end-page: 2301
  article-title: SACNN: self‐attention convolutional neural network for low‐dose CT denoising with self‐supervised perceptual loss network
  publication-title: IEEE Trans Med Imaging
– volume: 36
  start-page: 2524
  issue: 12
  year: 2017
  end-page: 2535
  article-title: Low‐dose CT with a residual encoder‐decoder convolutional neural network
  publication-title: IEEE Trans Med Imaging
– volume: 65
  issue: 24
  year: 2020
  article-title: A dual‐domain deep learning‐based reconstruction method for fully 3D sparse data helical CT
  publication-title: Phys Med Biol
– volume: 21
  start-page: 89
  issue: 2
  year: 2002
  end-page: 99
  article-title: Statistical image reconstruction for polyenergetic X‐ray computed tomography
  publication-title: IEEE Trans Med Imaging
– volume: 2016
  start-page: 770
  year: 2016
  end-page: 778
  article-title: Deep residual learning for image recognition
– start-page: 223
  year: 2020
  end-page: 226
  article-title: A preliminary study on projection denoising for low‐dose CT imaging using modified dual‐domain U‐net
– volume: 369
  start-page: 245
  issue: 3
  year: 2013
  end-page: 254
  article-title: Targeting of low‐dose CT screening according to the risk of lung‐cancer death
  publication-title: N Engl J Med
– volume: 25
  start-page: 1022
  issue: 8
  year: 2006
  end-page: 1036
  article-title: Penalized‐likelihood sinogram restoration for computed tomography
  publication-title: IEEE Trans Med Imaging
– volume: 39
  start-page: 1856
  issue: 6
  year: 2020
  end-page: 1867
  article-title: UNet++: redesigning skip connections to exploit multiscale features in image segmentation
  publication-title: IEEE Trans Med Imaging
– year: 2017
– volume: 41
  issue: 1
  year: 2014
  article-title: Adaptive nonlocal means filtering based on local noise level for CT denoising
  publication-title: Med Phys
– year: 2019
  article-title: DuDoNet: dual domain network for CT metal artifact reduction
– volume: 53
  start-page: 4777
  issue: 17
  year: 2008
  end-page: 4807
  article-title: Image reconstruction in circular cone‐beam computed tomography by constrained, total‐variation minimization
  publication-title: Phys Med Biol
– volume: 1
  start-page: 46
  issue: 1
  year: 2017
  end-page: 55
  article-title: Super‐resolution reconstruction of 3D PET images using two respiratory‐phase low‐dose CT images
  publication-title: IEEE Trans Radiat Plasma Med Sci
– volume: 14
  start-page: 2117
  issue: 12
  year: 2005
  end-page: 2128
  article-title: An information fidelity criterion for image quality assessment using natural scene statistics
  publication-title: IEEE Trans Image Process
– ident: e_1_2_9_22_1
  doi: 10.1038/s42256-019-0057-9
– ident: e_1_2_9_8_1
  doi: 10.1109/TMI.2012.2187213
– ident: e_1_2_9_31_1
  doi: 10.1109/CVPR.2016.90
– ident: e_1_2_9_28_1
– ident: e_1_2_9_13_1
  doi: 10.1109/TMI.2017.2715284
– ident: e_1_2_9_15_1
  doi: 10.1109/TMI.2006.875429
– ident: e_1_2_9_16_1
  doi: 10.1002/mp.12344
– ident: e_1_2_9_23_1
  doi: 10.1109/TMI.2020.2968472
– ident: e_1_2_9_20_1
  doi: 10.1109/ICAIBD49809.2020.9137456
– volume: 2017
  start-page: 5999
  year: 2017
  ident: e_1_2_9_27_1
  article-title: Attention is all you need
  publication-title: Adv Neural Inf Process Syst
– ident: e_1_2_9_19_1
  doi: 10.1109/TMI.2019.2917258
– ident: e_1_2_9_7_1
  doi: 10.1007/s11263-007-0110-8
– ident: e_1_2_9_14_1
  doi: 10.1109/TMI.2018.2827462
– ident: e_1_2_9_34_1
  doi: 10.1364/BOE.8.000679
– ident: e_1_2_9_5_1
  doi: 10.1021/acs.jpca.8b08584
– ident: e_1_2_9_18_1
  doi: 10.1109/CVPR.2019.01076
– ident: e_1_2_9_6_1
  doi: 10.1088/0031-9155/53/17/021
– ident: e_1_2_9_36_1
  doi: 10.1109/TIP.2005.859389
– ident: e_1_2_9_3_1
  doi: 10.1056/NEJMoa1301851
– ident: e_1_2_9_25_1
  doi: 10.1109/TMI.2019.2959609
– ident: e_1_2_9_35_1
  doi: 10.1109/BIA50171.2020.9244282
– ident: e_1_2_9_10_1
  doi: 10.1118/1.4851635
– ident: e_1_2_9_17_1
  doi: 10.1109/TMI.2018.2823756
– ident: e_1_2_9_21_1
  doi: 10.1007/s00330-018-5829-9
– ident: e_1_2_9_9_1
  doi: 10.1109/42.993128
– ident: e_1_2_9_30_1
– ident: e_1_2_9_11_1
  doi: 10.1088/0031-9155/55/18/009
– ident: e_1_2_9_24_1
  doi: 10.1088/1361-6560/ab8fc1
– ident: e_1_2_9_26_1
– ident: e_1_2_9_12_1
  doi: 10.1109/TNS.2016.2611624
– ident: e_1_2_9_4_1
  doi: 10.1118/1.2836950
– ident: e_1_2_9_37_1
  doi: 10.1109/TNS.2015.2467219
– ident: e_1_2_9_2_1
  doi: 10.1056/NEJMra072149
– ident: e_1_2_9_33_1
  doi: 10.2214/AJR.09.2989
– ident: e_1_2_9_29_1
– ident: e_1_2_9_32_1
  doi: 10.1109/ICCV.2019.00280
SSID ssj0006350
Score 2.4246173
Snippet Background Remarkable progress has been made for low‐dose computed tomography (CT) reconstruction tasks by applying deep learning techniques. However,...
Remarkable progress has been made for low-dose computed tomography (CT) reconstruction tasks by applying deep learning techniques. However, establishing an...
SourceID proquest
pubmed
crossref
wiley
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 3860
SubjectTerms CT reconstruction
denoising
dual domain
texture preservation
Title Texture‐aware dual domain mapping model for low‐dose CT reconstruction
URI https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmp.15607
https://www.ncbi.nlm.nih.gov/pubmed/35297051
https://www.proquest.com/docview/2640321715
Volume 49
WOSCitedRecordID wos000776351900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library - Journals
  customDbUrl:
  eissn: 2473-4209
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0006350
  issn: 0094-2405
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEB50feDF92N9EUH0VG3TpmmPoi4iKiIr7K2kaSKC2y5bH1d_gr_RX-Ik7VZEBcFTL9PQJvP4JpP5ArDrc50yV5tNdx06QcgyR-g4c1zGaKhD1DDPNgpf8KurqNeLr-tTlaYXpuKHaDbcjGVYf20MXKTl4SdpaH9wYLqA-ThMUFTboAUTJzed24vGD2MorRpQ4sDUENiIetalh6N3vwajbwjzK2C1Eacz959vnYfZGmeSo0oxFmBM5YswfVlX0hdhyh79lOUSnHfRPz8N1fvrm3gRQ0VMdxbJir64z0lfGP6GO2IvzCEIcMlD8YKSWVEqctwlNp9uOGiX4bZz2j0-c-obFhzpYy7iqDRQXiRpzJikmHgIhemRJ2Omle-KyOMypdrnXqp0IAMmwyjTsfDcKOVBJjDSr0ArL3K1BgRxEto_6oPhPONhjBJ-phn64YjKNKNt2B9NdSJr-nFzC8ZDUhEn06Q_SOwktWGnkRxUlBs_yYxWK0F7MEUOkaviqUwQ4Lnm3zzWhtVqGZtREGzGHLWvDXt2tX4dPrm8ts_1vwpuwAw1fRF2e2YTWjjvagsm5fPjfTnchnHei7Zr_fwA62fmWA
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1fb9MwED-Vlm28bFDYKGPDSIg9hSZOnD_iaRpUHbRVhVqpb5Hj2KhSm1Qtpa98BD4jn4Sz82eqAGkST3m5WInvfPe7s-9ngDduoBJmK110V77l-Sy1uIpSy2aM-spHC3NMo_AgGI3C2SwaN-B91QtT8EPUBTe9Moy_1gtcF6S7d6yhy9U73QYcPICWh1bEmtD68KU3HdSOGGNp0YESeXoTgVXcszbtVu_uR6M_IOY-YjUhp3fyXx_7GI5LpEmuC9N4Ag2ZteFwWO6lt-HAHP4Um6fwaYIeeruWv3785Du-lkT3Z5E0X_J5RpZcMzh8JebKHIIQlyzyHUqm-UaSmwkxGXXNQvsMpr2Pk5u-Vd6xYAkXsxFLJp50QkEjxgTF1INLTJAcETElXZuHTiASqtzASaTyhMeEH6Yq4o4dJoGXcoz1p9DM8kw-B4JICT0AWoRmPQv8CCXcVDH0xCEVSUo7cFXNdSxKAnJ9D8YiLqiTabxcxWaSOvC6llwVpBt_k6nUFeOK0NscPJP5dhMjxLP1vzmsA2eFHutREG5GAdpfB94adf1z-Hg4Ns8X9xV8BUf9yXAQD25Hn8_hEdVdEqZY8xKaqAN5AQ_F92_zzfqyNNPfTF7pYA
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT9wwEB7xKIhLofTBFkpdqWpPYRMnTmJxQtAVtMtqVS0St8jxo0Jik9Uuy175CfxGfglj54FQW6lST7lMrMTz-sb2fAb4HCYmZ76xi-4m9qKYKU8YrjyfMRqbGC0scI3C_WQwSC8v-XAJDptemIofol1ws57h4rV1cD1RpvvEGjqeHNg24GQZViPGY_TK1ZOfvYt-G4gxl1YdKDyymwis4Z71abd593k2-g1iPkesLuX0Nv_rY7fgZY00yVFlGq9gSRfbsH5e76Vvw5o7_Clnr-H7CCP0fKof7u7FQkw1sf1ZRJVjcVWQsbAMDr-IuzKHIMQl1-UCJVU50-R4RFxF3bLQvoGL3rfR8alX37HgyRCrEU_nkQ5SSTljkmLpITQWSIHkzOjQF2mQyJyaMAlybSIZMRmnynAR-GmeREpgrn8LK0VZ6B0giJQwAqBFWNazJOYoESrDMBKnVOaKduBrM9eZrAnI7T0Y11lFnUyz8SRzk9SBT63kpCLd-JNMo64MPcJuc4hCl_NZhhDPt_8WsA68q_TYjoJwkydofx344tT11-Gz86F7vv9XwY-wPjzpZf2zwY9d2KC2ScKt1ezBCqpAf4AX8vbmajbdr630Efiu6Ns
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Texture-aware+dual+domain+mapping+model+for+low-dose+CT+reconstruction&rft.jtitle=Medical+physics+%28Lancaster%29&rft.au=Wang%2C+Huafeng&rft.au=Zhao%2C+Xuemei&rft.au=Liu%2C+Wanquan&rft.au=Li%2C+Lihong+C&rft.date=2022-06-01&rft.eissn=2473-4209&rft_id=info:doi/10.1002%2Fmp.15607&rft_id=info%3Apmid%2F35297051&rft.externalDocID=35297051
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0094-2405&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0094-2405&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0094-2405&client=summon