Adaptive scatter kernel deconvolution modeling for cone‐beam CT scatter correction via deep reinforcement learning

Background Scattering photons can seriously contaminate cone‐beam CT (CBCT) image quality with severe artifacts and substantial degradation of CT value accuracy, which is a major concern limiting the widespread application of CBCT in the medical field. The scatter kernel deconvolution (SKD) method c...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Medical physics (Lancaster) Jg. 51; H. 2; S. 1163 - 1177
Hauptverfasser: Piao, Zun, Deng, Wenxin, Huang, Shuang, Lin, Guoqin, Qin, Peishan, Li, Xu, Wu, Wangjiang, Qi, Mengke, Zhou, Linghong, Li, Bin, Ma, Jianhui, Xu, Yuan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States 01.02.2024
Schlagworte:
ISSN:0094-2405, 2473-4209, 2473-4209
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Background Scattering photons can seriously contaminate cone‐beam CT (CBCT) image quality with severe artifacts and substantial degradation of CT value accuracy, which is a major concern limiting the widespread application of CBCT in the medical field. The scatter kernel deconvolution (SKD) method commonly used in clinic requires a Monte Carlo (MC) simulation to determine numerous quality‐related kernel parameters, and it cannot realize intelligent scatter kernel parameter optimization, causing limited accuracy of scatter estimation. Purpose Aiming at improving the scatter estimation accuracy of the SKD algorithm, an intelligent scatter correction framework integrating the SKD with deep reinforcement learning (DRL) scheme is proposed. Methods Our method firstly builds a scatter kernel model to iteratively convolve with raw projections, and then the deep Q‐network of the DRL scheme is introduced to intelligently interact with the scatter kernel to achieve a projection adaptive parameter optimization. The potential of the proposed framework is demonstrated on CBCT head and pelvis simulation data and experimental CBCT measurement data. Furthermore, we have implemented the U‐net based scatter estimation approach for comparison. Results The simulation study demonstrates that the mean absolute percentage error (MAPE) of the proposed method is less than 9.72% and the peak signal‐to‐noise ratio (PSNR) is higher than 23.90 dB, while for the conventional SKD algorithm, the minimum MAPE is 17.92% and the maximum PSNR is 19.32 dB. In the measurement study, we adopt a hardware‐based beam stop array algorithm to obtain the scatter‐free projections as a comparison baseline, and our method can achieve superior performance with MAPE < 17.79% and PSNR > 16.34 dB. Conclusions In this paper, we propose an intelligent scatter correction framework that integrates the physical scatter kernel model with DRL algorithm, which has the potential to improve the accuracy of the clinical scatter correction method to obtain better CBCT imaging quality.
AbstractList Background Scattering photons can seriously contaminate cone‐beam CT (CBCT) image quality with severe artifacts and substantial degradation of CT value accuracy, which is a major concern limiting the widespread application of CBCT in the medical field. The scatter kernel deconvolution (SKD) method commonly used in clinic requires a Monte Carlo (MC) simulation to determine numerous quality‐related kernel parameters, and it cannot realize intelligent scatter kernel parameter optimization, causing limited accuracy of scatter estimation. Purpose Aiming at improving the scatter estimation accuracy of the SKD algorithm, an intelligent scatter correction framework integrating the SKD with deep reinforcement learning (DRL) scheme is proposed. Methods Our method firstly builds a scatter kernel model to iteratively convolve with raw projections, and then the deep Q‐network of the DRL scheme is introduced to intelligently interact with the scatter kernel to achieve a projection adaptive parameter optimization. The potential of the proposed framework is demonstrated on CBCT head and pelvis simulation data and experimental CBCT measurement data. Furthermore, we have implemented the U‐net based scatter estimation approach for comparison. Results The simulation study demonstrates that the mean absolute percentage error (MAPE) of the proposed method is less than 9.72% and the peak signal‐to‐noise ratio (PSNR) is higher than 23.90 dB, while for the conventional SKD algorithm, the minimum MAPE is 17.92% and the maximum PSNR is 19.32 dB. In the measurement study, we adopt a hardware‐based beam stop array algorithm to obtain the scatter‐free projections as a comparison baseline, and our method can achieve superior performance with MAPE < 17.79% and PSNR > 16.34 dB. Conclusions In this paper, we propose an intelligent scatter correction framework that integrates the physical scatter kernel model with DRL algorithm, which has the potential to improve the accuracy of the clinical scatter correction method to obtain better CBCT imaging quality.
Scattering photons can seriously contaminate cone-beam CT (CBCT) image quality with severe artifacts and substantial degradation of CT value accuracy, which is a major concern limiting the widespread application of CBCT in the medical field. The scatter kernel deconvolution (SKD) method commonly used in clinic requires a Monte Carlo (MC) simulation to determine numerous quality-related kernel parameters, and it cannot realize intelligent scatter kernel parameter optimization, causing limited accuracy of scatter estimation. Aiming at improving the scatter estimation accuracy of the SKD algorithm, an intelligent scatter correction framework integrating the SKD with deep reinforcement learning (DRL) scheme is proposed. Our method firstly builds a scatter kernel model to iteratively convolve with raw projections, and then the deep Q-network of the DRL scheme is introduced to intelligently interact with the scatter kernel to achieve a projection adaptive parameter optimization. The potential of the proposed framework is demonstrated on CBCT head and pelvis simulation data and experimental CBCT measurement data. Furthermore, we have implemented the U-net based scatter estimation approach for comparison. The simulation study demonstrates that the mean absolute percentage error (MAPE) of the proposed method is less than 9.72% and the peak signal-to-noise ratio (PSNR) is higher than 23.90 dB, while for the conventional SKD algorithm, the minimum MAPE is 17.92% and the maximum PSNR is 19.32 dB. In the measurement study, we adopt a hardware-based beam stop array algorithm to obtain the scatter-free projections as a comparison baseline, and our method can achieve superior performance with MAPE < 17.79% and PSNR > 16.34 dB. In this paper, we propose an intelligent scatter correction framework that integrates the physical scatter kernel model with DRL algorithm, which has the potential to improve the accuracy of the clinical scatter correction method to obtain better CBCT imaging quality.
Scattering photons can seriously contaminate cone-beam CT (CBCT) image quality with severe artifacts and substantial degradation of CT value accuracy, which is a major concern limiting the widespread application of CBCT in the medical field. The scatter kernel deconvolution (SKD) method commonly used in clinic requires a Monte Carlo (MC) simulation to determine numerous quality-related kernel parameters, and it cannot realize intelligent scatter kernel parameter optimization, causing limited accuracy of scatter estimation.BACKGROUNDScattering photons can seriously contaminate cone-beam CT (CBCT) image quality with severe artifacts and substantial degradation of CT value accuracy, which is a major concern limiting the widespread application of CBCT in the medical field. The scatter kernel deconvolution (SKD) method commonly used in clinic requires a Monte Carlo (MC) simulation to determine numerous quality-related kernel parameters, and it cannot realize intelligent scatter kernel parameter optimization, causing limited accuracy of scatter estimation.Aiming at improving the scatter estimation accuracy of the SKD algorithm, an intelligent scatter correction framework integrating the SKD with deep reinforcement learning (DRL) scheme is proposed.PURPOSEAiming at improving the scatter estimation accuracy of the SKD algorithm, an intelligent scatter correction framework integrating the SKD with deep reinforcement learning (DRL) scheme is proposed.Our method firstly builds a scatter kernel model to iteratively convolve with raw projections, and then the deep Q-network of the DRL scheme is introduced to intelligently interact with the scatter kernel to achieve a projection adaptive parameter optimization. The potential of the proposed framework is demonstrated on CBCT head and pelvis simulation data and experimental CBCT measurement data. Furthermore, we have implemented the U-net based scatter estimation approach for comparison.METHODSOur method firstly builds a scatter kernel model to iteratively convolve with raw projections, and then the deep Q-network of the DRL scheme is introduced to intelligently interact with the scatter kernel to achieve a projection adaptive parameter optimization. The potential of the proposed framework is demonstrated on CBCT head and pelvis simulation data and experimental CBCT measurement data. Furthermore, we have implemented the U-net based scatter estimation approach for comparison.The simulation study demonstrates that the mean absolute percentage error (MAPE) of the proposed method is less than 9.72% and the peak signal-to-noise ratio (PSNR) is higher than 23.90 dB, while for the conventional SKD algorithm, the minimum MAPE is 17.92% and the maximum PSNR is 19.32 dB. In the measurement study, we adopt a hardware-based beam stop array algorithm to obtain the scatter-free projections as a comparison baseline, and our method can achieve superior performance with MAPE < 17.79% and PSNR > 16.34 dB.RESULTSThe simulation study demonstrates that the mean absolute percentage error (MAPE) of the proposed method is less than 9.72% and the peak signal-to-noise ratio (PSNR) is higher than 23.90 dB, while for the conventional SKD algorithm, the minimum MAPE is 17.92% and the maximum PSNR is 19.32 dB. In the measurement study, we adopt a hardware-based beam stop array algorithm to obtain the scatter-free projections as a comparison baseline, and our method can achieve superior performance with MAPE < 17.79% and PSNR > 16.34 dB.In this paper, we propose an intelligent scatter correction framework that integrates the physical scatter kernel model with DRL algorithm, which has the potential to improve the accuracy of the clinical scatter correction method to obtain better CBCT imaging quality.CONCLUSIONSIn this paper, we propose an intelligent scatter correction framework that integrates the physical scatter kernel model with DRL algorithm, which has the potential to improve the accuracy of the clinical scatter correction method to obtain better CBCT imaging quality.
Author Li, Xu
Ma, Jianhui
Li, Bin
Qi, Mengke
Piao, Zun
Zhou, Linghong
Xu, Yuan
Wu, Wangjiang
Huang, Shuang
Deng, Wenxin
Lin, Guoqin
Qin, Peishan
Author_xml – sequence: 1
  givenname: Zun
  surname: Piao
  fullname: Piao, Zun
  organization: Southern Medical University
– sequence: 2
  givenname: Wenxin
  surname: Deng
  fullname: Deng, Wenxin
  organization: Southern Medical University
– sequence: 3
  givenname: Shuang
  surname: Huang
  fullname: Huang, Shuang
  organization: Southern Medical University
– sequence: 4
  givenname: Guoqin
  surname: Lin
  fullname: Lin, Guoqin
  organization: Southern Medical University
– sequence: 5
  givenname: Peishan
  surname: Qin
  fullname: Qin, Peishan
  organization: Southern Medical University
– sequence: 6
  givenname: Xu
  surname: Li
  fullname: Li, Xu
  organization: Southern Medical University
– sequence: 7
  givenname: Wangjiang
  surname: Wu
  fullname: Wu, Wangjiang
  organization: Southern Medical University
– sequence: 8
  givenname: Mengke
  surname: Qi
  fullname: Qi, Mengke
  organization: Southern Medical University
– sequence: 9
  givenname: Linghong
  surname: Zhou
  fullname: Zhou, Linghong
  organization: Southern Medical University
– sequence: 10
  givenname: Bin
  surname: Li
  fullname: Li, Bin
  organization: Sun Yat‐sen University Cancer Center
– sequence: 11
  givenname: Jianhui
  surname: Ma
  fullname: Ma, Jianhui
  email: jianhuima37@163.com
  organization: Nanfang Hospital, Southern Medical University
– sequence: 12
  givenname: Yuan
  surname: Xu
  fullname: Xu, Yuan
  email: yuanxu@smu.edu.cn
  organization: Southern Medical University
BackLink https://www.ncbi.nlm.nih.gov/pubmed/37459053$$D View this record in MEDLINE/PubMed
BookMark eNp1kctOHDEQRa2ICIaHxBdEXmbTk7LdzyUaBYIEShawblW7qyMHt92xPYPY8Ql8I1-ShgEiRWFVizr3SFV3n-0474ixYwFLASC_jNNSlKWoP7CFzCuV5RKaHbYAaPJM5lDssf0YfwFAqQrYZXuqyosGCrVg6aTHKZkN8agxJQr8hoIjy3vS3m28XSfjHR99T9a4n3zwgc8Lerx_6AhHvrp6C2ofAulnfGNwFtDEAxk3RzSN5BK3hMHNlkP2cUAb6ehlHrDr069Xq2_Zxfez89XJRaaVFHVGSoBoyq5BQQIVKVl1FeoSQdXQCzmIjppe6kHQfBCWJDps6gKrAfohr0kdsM9b7xT87zXF1I4marIWHfl1bGWtGpmXlSxm9NMLuu5G6tspmBHDXfv6qb8uHXyMgYY3RED7VEI7Tu1zCTO6_AfVJuHTY1JAY_8XyLaBW2Pp7l1xe_ljy_8BHcmZkA
CitedBy_id crossref_primary_10_1038_s41598_024_54529_4
crossref_primary_10_1088_1361_6560_adaf06
crossref_primary_10_1002_mp_18024
crossref_primary_10_1002_mp_17435
crossref_primary_10_1016_j_prro_2023_10_014
crossref_primary_10_1088_1361_6560_adc86c
crossref_primary_10_3788_AOS241966
crossref_primary_10_1088_1361_6560_adebd7
Cites_doi 10.1259/bjr.20170266
10.1118/1.3589140
10.1088/0031-9155/55/1/007
10.1109/TMI.2021.3074712
10.1088/0031-9155/55/22/007
10.1002/mp.13878
10.1109/ACCESS.2018.2884704
10.1364/OE.27.001262
10.1609/aaai.v32i1.11796
10.3233/XST-160583
10.1002/mp.13274
10.1002/mp.12385
10.1609/aaai.v30i1.10295
10.1118/1.4943796
10.1088/1361-6560/ac55a5
10.1007/978-3-030-66843-3_18
10.1002/mp.12849
10.1109/TMI.2018.2823679
10.1002/mp.14624
10.1016/j.ndteint.2015.11.004
10.5152/TurkJOrthod.2016.15-00026R1
10.1088/1361-6560/ab18bf
10.1038/nature14236
10.1117/12.811578
10.1118/1.1339879
10.1118/1.2148916
10.1002/mp.12850
10.1016/j.media.2021.102193
10.1118/1.4734715
10.1002/mp.14712
10.1118/1.4801895
10.1002/mp.12625
10.1118/1.2924220
10.1117/12.2008181
10.1088/0031-9155/57/21/6849
10.1118/1.3599033
10.1002/mp.13175
10.1002/mp.12022
10.1007/s003300050710
10.1088/0031-9155/55/21/002
10.1002/mp.15656
10.1088/0031-9155/60/3/1339
10.1117/12.2646588
10.1016/j.media.2019.02.007
10.1088/0031-9155/60/9/3567
ContentType Journal Article
Copyright 2023 American Association of Physicists in Medicine.
Copyright_xml – notice: 2023 American Association of Physicists in Medicine.
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1002/mp.16618
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList
MEDLINE
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 1177
ExternalDocumentID 37459053
10_1002_mp_16618
MP16618
Genre article
Journal Article
GrantInformation_xml – fundername: National Key Research and Development Program of China
  funderid: 2022YFA1204203
– fundername: Guangdong Basic and Applied Basic Research Foundation
  funderid: 2020A1515110352; 2023A1515010537
– fundername: Guangzhou Science, and technology
  funderid: 202002030385
– fundername: National Natural Science Foundation of China
  funderid: 61971463; 82272131; 82202960
– fundername: National Natural Science Foundation of China
  grantid: 61971463
– fundername: Guangdong Basic and Applied Basic Research Foundation
  grantid: 2023A1515010537
– fundername: National Natural Science Foundation of China
  grantid: 82202960
– fundername: National Natural Science Foundation of China
  grantid: 82272131
– fundername: National Key Research and Development Program of China
  grantid: 2022YFA1204203
– fundername: Guangdong Basic and Applied Basic Research Foundation
  grantid: 2020A1515110352
– fundername: Guangzhou Science, and technology
  grantid: 202002030385
GroupedDBID ---
--Z
-DZ
.GJ
0R~
1OB
1OC
29M
2WC
33P
36B
3O-
4.4
53G
5GY
5RE
5VS
AAHQN
AAIPD
AAMMB
AAMNL
AANLZ
AAQQT
AASGY
AAXRX
AAYCA
AAZKR
ABCUV
ABDPE
ABEFU
ABFTF
ABJNI
ABLJU
ABQWH
ABXGK
ACAHQ
ACBEA
ACCZN
ACGFO
ACGFS
ACGOF
ACPOU
ACXBN
ACXQS
ADBBV
ADBTR
ADKYN
ADMLS
ADOZA
ADXAS
ADZMN
AEFGJ
AEGXH
AEIGN
AENEX
AEUYR
AEYWJ
AFBPY
AFFPM
AFWVQ
AGHNM
AGXDD
AGYGG
AHBTC
AIACR
AIAGR
AIDQK
AIDYY
AITYG
AIURR
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
AAYXX
ABUFD
AIQQE
CITATION
LH4
CGR
CUY
CVF
ECM
EIF
NPM
7X8
ID FETCH-LOGICAL-c3218-e310196b9a1e1a3e327b7ac6a0380d12f1be9d2cf1e374a6e1ba985a7f0df48e3
IEDL.DBID DRFUL
ISICitedReferencesCount 9
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001026650400001&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 Wed Oct 01 14:35:07 EDT 2025
Mon Jul 21 06:05:00 EDT 2025
Sat Nov 29 05:29:55 EST 2025
Tue Nov 18 22:21:10 EST 2025
Sun Jul 06 04:46:19 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords adaptive scatter kernel optimization
cone-beam CT scatter correction
deep reinforcement learning
scatter kernel deconvolution algorithm
Language English
License 2023 American Association of Physicists in Medicine.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3218-e310196b9a1e1a3e327b7ac6a0380d12f1be9d2cf1e374a6e1ba985a7f0df48e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 37459053
PQID 2839246725
PQPubID 23479
PageCount 15
ParticipantIDs proquest_miscellaneous_2839246725
pubmed_primary_37459053
crossref_primary_10_1002_mp_16618
crossref_citationtrail_10_1002_mp_16618
wiley_primary_10_1002_mp_16618_MP16618
PublicationCentury 2000
PublicationDate February 2024
2024-02-00
2024-Feb
20240201
PublicationDateYYYYMMDD 2024-02-01
PublicationDate_xml – month: 02
  year: 2024
  text: February 2024
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Medical physics (Lancaster)
PublicationTitleAlternate Med Phys
PublicationYear 2024
References 2021; 9
2010; 55
2021; 48
2019; 53
2006; 33
2013; 40
2017; 44
2022; 67
2009
2008; 35
2012; 39
2001; 28
2018; 45
2011; 38
2012; 57
2021; 73
2022; 49
2016; 78
1999; 9
2018; 6
2017; 90
2015; 60
2019; 64
2022
2020
2019; 46
2016; 43
2019; 27
2015; 518
2018
2020; 47
2016
2013
2016; 29
2021; 40
2016; 24
2018; 37
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_38_1
e_1_2_9_14_1
e_1_2_9_39_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_41_1
e_1_2_9_42_1
e_1_2_9_20_1
e_1_2_9_22_1
e_1_2_9_45_1
e_1_2_9_21_1
e_1_2_9_46_1
e_1_2_9_24_1
e_1_2_9_43_1
e_1_2_9_23_1
e_1_2_9_44_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
Ma J (e_1_2_9_40_1) 2021; 9
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
e_1_2_9_28_1
e_1_2_9_47_1
e_1_2_9_27_1
e_1_2_9_29_1
References_xml – volume: 29
  start-page: 16
  issue: 1
  year: 2016
  end-page: 21
  article-title: Cone beam computed tomography in orthodontics
  publication-title: Turk J Orthod
– volume: 45
  start-page: 4916
  issue: 11
  year: 2018
  end-page: 4926
  article-title: ScatterNet: a convolutional neural network for cone‐beam CT intensity correction
  publication-title: Med Phys
– volume: 55
  start-page: 99
  issue: 1
  year: 2010
  end-page: 120
  article-title: A fast and pragmatic approach for scatter correction in flat‐detector CT using elliptic modeling and iterative optimization
  publication-title: Phys Med Biol
– volume: 90
  issue: 1079
  year: 2017
  article-title: A robotic C‐arm cone beam CT system for image‐guided proton therapy: design and performance
  publication-title: Brit J Radiol
– volume: 40
  issue: 5
  year: 2013
  article-title: Monte Carlo study of the effects of system geometry and antiscatter grids on cone‐beam CT scatter distributions
  publication-title: Med Phys
– year: 2018
  article-title: Rainbow: combining improvements in deep reinforcement learning
– volume: 39
  start-page: 3624
  issue: 6Part4
  year: 2012
  end-page: 3625
  article-title: SU‐E‐l‐01: investigating the dependence of 2D and 3D scatter‐to‐primary ratios on breast density in clinical breast CT
  publication-title: Med Phys
– volume: 40
  start-page: 2272
  issue: 9
  year: 2021
  end-page: 2283
  article-title: X‐Ray scatter estimation using deep splines
  publication-title: Ieee T Med Imaging
– volume: 38
  start-page: 4296
  issue: 7
  year: 2011
  end-page: 4311
  article-title: A general framework and review of scatter correction methods in x‐ray cone‐beam computerized tomography. Part 1: scatter compensation approaches
  publication-title: Med Phys
– volume: 48
  start-page: 2816
  issue: 6
  year: 2021
  end-page: 2826
  article-title: Improving CBCT quality to CT level using deep learning with generative adversarial network
  publication-title: Med Phys
– volume: 45
  start-page: 1914
  issue: 5
  year: 2018
  end-page: 1925
  article-title: Acuros CTS: a fast, linear Boltzmann transport equation solver for computed tomography scatter – part II: system modeling, scatter correction, and optimization
  publication-title: Med Phys
– start-page: 177
  year: 2020
  end-page: 186
– volume: 46
  start-page: 238
  issue: 1
  year: 2019
  end-page: 249
  article-title: Real‐time scatter estimation for medical CT using the deep scatter estimation: method and robustness analysis with respect to different anatomies, dose levels, tube voltages, and data truncation
  publication-title: Med Phys
– year: 2016
  article-title: Deep reinforcement learning with double Q‐learning
– volume: 9
  start-page: 563
  issue: 3
  year: 1999
  end-page: 569
  article-title: Efficient object scatter correction algorithm for third and fourth generation CT scanners
  publication-title: Eur Radiol
– volume: 43
  start-page: 1736
  issue: 4
  year: 2016
  article-title: A model‐based scatter artifacts correction for cone beam CT
  publication-title: Med Phys
– start-page: 392
  year: 2013
  end-page: 399
  article-title: Scatter correction with kernel perturbation
– start-page: 644
  year: 2009
  end-page: 655
  article-title: Efficient scatter correction using asymmetric kernels
– volume: 73
  year: 2021
  article-title: Deep reinforcement learning in medical imaging: a literature review
  publication-title: Med Image Anal
– volume: 67
  issue: 5
  year: 2022
  article-title: A deep unsupervised learning framework for the 4D CBCT artifact correction
  publication-title: Phys Med Biol
– volume: 57
  start-page: 6849
  issue: 21
  year: 2012
  end-page: 6867
  article-title: Hybrid scatter correction for CT imaging
  publication-title: Phys Med Biol
– volume: 55
  start-page: 6695
  issue: 22
  year: 2010
  end-page: 6720
  article-title: Improved scatter correction using adaptive scatter kernel superposition
  publication-title: Phys Med Biol
– volume: 37
  start-page: 1430
  issue: 6
  year: 2018
  end-page: 1439
  article-title: Intelligent parameter tuning in optimization‐based iterative CT reconstruction via deep reinforcement learning
  publication-title: Ieee T Med Imaging
– volume: 44
  start-page: 71
  issue: 1
  year: 2017
  end-page: 83
  article-title: X‐ray scatter correction for multi‐source interior computed tomography
  publication-title: Med Phys
– volume: 28
  start-page: 220
  issue: 2
  year: 2001
  end-page: 231
  article-title: Cone‐beam computed tomography with a flat‐panel imager: magnitude and effects of x‐ray scatter
  publication-title: Med Phys
– volume: 44
  start-page: 4437
  issue: 9
  year: 2017
  end-page: 4451
  article-title: Optimal combination of anti‐scatter grids and software correction for CBCT imaging
  publication-title: Med Phys
– volume: 45
  start-page: 1899
  issue: 5
  year: 2018
  end-page: 1913
  article-title: Acuros CTS: a fast, linear Boltzmann transport equation solver for computed tomography scatter – part I: core algorithms and validation
  publication-title: Med Phys
– volume: 78
  start-page: 52
  year: 2016
  end-page: 60
  article-title: Scattering correction using continuously thickness‐adapted kernels
  publication-title: Ndt&E Int
– volume: 44
  start-page: 6690
  issue: 12
  year: 2017
  end-page: 6705
  article-title: Deep reinforcement learning for automated radiation adaptation in lung cancer
  publication-title: Med Phys
– volume: 27
  start-page: 1262
  issue: 2
  year: 2019
  article-title: Metropolis Monte Carlo simulation scheme for fast scattered X‐ray photon calculation in CT
  publication-title: Opt Express
– volume: 49
  start-page: 4566
  issue: 7
  year: 2022
  end-page: 4584
  article-title: Empirical scatter correction: cBCT scatter artifact reduction without prior information
  publication-title: Med Phys
– volume: 53
  start-page: 156
  year: 2019
  end-page: 164
  article-title: Evaluating reinforcement learning agents for anatomical landmark detection
  publication-title: Med Image Anal
– volume: 24
  start-page: 723
  issue: 5
  year: 2016
  end-page: 732
  article-title: Separable scatter model of the detector and object contributions using continuously thickness‐adapted kernels in CBCT
  publication-title: J X‐Ray Sci Technol
– volume: 35
  start-page: 2452
  issue: 6
  year: 2008
  end-page: 2462
  article-title: Focused beam‐stop array for the measurement of scatter in megavoltage portal and cone beam CT imaging
  publication-title: Med Phys
– volume: 38
  start-page: 5186
  issue: 9
  year: 2011
  end-page: 5199
  article-title: A general framework and review of scatter correction methods in cone beam CT. Part 2: scatter estimation approaches
  publication-title: Med Phys
– volume: 60
  start-page: 3567
  issue: 9
  year: 2015
  end-page: 3587
  article-title: A practical cone‐beam CT scatter correction method with optimized Monte Carlo simulations for image‐guided radiation therapy
  publication-title: Phys Med Biol
– volume: 6
  start-page: 78031
  year: 2018
  end-page: 78037
  article-title: Scatter artifacts removal using learning‐based method for CBCT in IGRT system
  publication-title: Ieee Access
– volume: 518
  start-page: 529
  issue: 7540
  year: 2015
  end-page: 533
  article-title: Human‐level control through deep reinforcement learning
  publication-title: Nature
– start-page: 675
  year: 2022
  end-page: 679
  article-title: Learning CT scatter estimation without labeled data: a feasibility study
– volume: 64
  issue: 11
  year: 2019
  article-title: Intelligent inverse treatment planning via deep reinforcement learning, a proof‐of‐principle study in high dose‐rate brachytherapy for cervical cancer
  publication-title: Phys Med Biol
– volume: 60
  start-page: 1339
  issue: 3
  year: 2015
  end-page: 1365
  article-title: Patient‐specific scatter correction for flat‐panel detector‐based cone‐beam CT imaging
  publication-title: Phys Med Biol
– volume: 9
  start-page: B45
  issue: 3
  year: 2021
  article-title: Monte Carlo simulation fused with target distribution modeling via deep reinforcement learning for automatic high‐efficiency photon distribution estimation
  publication-title: Photon Res (Washington, DC)
– volume: 33
  start-page: 187
  issue: 1
  year: 2006
  end-page: 197
  article-title: A simple, direct method for x‐ray scatter estimation and correction in digital radiography and cone‐beam CT
  publication-title: Med Phys
– volume: 48
  start-page: 1909
  issue: 4
  year: 2021
  end-page: 1920
  article-title: Improving efficiency of training a virtual treatment planner network via knowledge‐guided deep reinforcement learning for intelligent automatic treatment planning of radiotherapy
  publication-title: Med Phys
– volume: 47
  start-page: 190
  issue: 1
  year: 2020
  end-page: 200
  article-title: Modified fast adaptive scatter kernel superposition (mfASKS) correction and its dosimetric impact on CBCT‐based proton therapy dose calculation
  publication-title: Med Phys
– volume: 55
  start-page: 6353
  issue: 21
  year: 2010
  end-page: 6375
  article-title: Projection correlation based view interpolation for cone beam CT: primary fluence restoration in scatter measurement with a moving beam stop array
  publication-title: Phys Med Biol
– ident: e_1_2_9_2_1
  doi: 10.1259/bjr.20170266
– ident: e_1_2_9_5_1
  doi: 10.1118/1.3589140
– ident: e_1_2_9_7_1
  doi: 10.1088/0031-9155/55/1/007
– ident: e_1_2_9_30_1
  doi: 10.1109/TMI.2021.3074712
– ident: e_1_2_9_20_1
  doi: 10.1088/0031-9155/55/22/007
– ident: e_1_2_9_17_1
  doi: 10.1002/mp.13878
– ident: e_1_2_9_28_1
  doi: 10.1109/ACCESS.2018.2884704
– ident: e_1_2_9_14_1
  doi: 10.1364/OE.27.001262
– ident: e_1_2_9_42_1
  doi: 10.1609/aaai.v32i1.11796
– ident: e_1_2_9_19_1
  doi: 10.3233/XST-160583
– ident: e_1_2_9_27_1
  doi: 10.1002/mp.13274
– ident: e_1_2_9_24_1
  doi: 10.1002/mp.12385
– ident: e_1_2_9_43_1
  doi: 10.1609/aaai.v30i1.10295
– ident: e_1_2_9_10_1
  doi: 10.1118/1.4943796
– ident: e_1_2_9_25_1
  doi: 10.1088/1361-6560/ac55a5
– ident: e_1_2_9_33_1
  doi: 10.1007/978-3-030-66843-3_18
– volume: 9
  start-page: B45
  issue: 3
  year: 2021
  ident: e_1_2_9_40_1
  article-title: Monte Carlo simulation fused with target distribution modeling via deep reinforcement learning for automatic high‐efficiency photon distribution estimation
  publication-title: Photon Res (Washington, DC)
– ident: e_1_2_9_12_1
  doi: 10.1002/mp.12849
– ident: e_1_2_9_36_1
  doi: 10.1109/TMI.2018.2823679
– ident: e_1_2_9_26_1
  doi: 10.1002/mp.14624
– ident: e_1_2_9_18_1
  doi: 10.1016/j.ndteint.2015.11.004
– ident: e_1_2_9_3_1
  doi: 10.5152/TurkJOrthod.2016.15-00026R1
– ident: e_1_2_9_39_1
  doi: 10.1088/1361-6560/ab18bf
– ident: e_1_2_9_32_1
  doi: 10.1038/nature14236
– ident: e_1_2_9_41_1
  doi: 10.1117/12.811578
– ident: e_1_2_9_4_1
  doi: 10.1118/1.1339879
– ident: e_1_2_9_8_1
  doi: 10.1118/1.2148916
– ident: e_1_2_9_11_1
  doi: 10.1002/mp.12850
– ident: e_1_2_9_34_1
  doi: 10.1016/j.media.2021.102193
– ident: e_1_2_9_9_1
  doi: 10.1118/1.4734715
– ident: e_1_2_9_38_1
  doi: 10.1002/mp.14712
– ident: e_1_2_9_15_1
  doi: 10.1118/1.4801895
– ident: e_1_2_9_37_1
  doi: 10.1002/mp.12625
– ident: e_1_2_9_45_1
  doi: 10.1118/1.2924220
– ident: e_1_2_9_21_1
  doi: 10.1117/12.2008181
– ident: e_1_2_9_16_1
  doi: 10.1088/0031-9155/57/21/6849
– ident: e_1_2_9_6_1
  doi: 10.1118/1.3599033
– ident: e_1_2_9_29_1
  doi: 10.1002/mp.13175
– ident: e_1_2_9_47_1
  doi: 10.1002/mp.12022
– ident: e_1_2_9_13_1
  doi: 10.1007/s003300050710
– ident: e_1_2_9_46_1
  doi: 10.1088/0031-9155/55/21/002
– ident: e_1_2_9_23_1
  doi: 10.1002/mp.15656
– ident: e_1_2_9_22_1
  doi: 10.1088/0031-9155/60/3/1339
– ident: e_1_2_9_31_1
  doi: 10.1117/12.2646588
– ident: e_1_2_9_35_1
  doi: 10.1016/j.media.2019.02.007
– ident: e_1_2_9_44_1
  doi: 10.1088/0031-9155/60/9/3567
SSID ssj0006350
Score 2.4780643
Snippet Background Scattering photons can seriously contaminate cone‐beam CT (CBCT) image quality with severe artifacts and substantial degradation of CT value...
Scattering photons can seriously contaminate cone-beam CT (CBCT) image quality with severe artifacts and substantial degradation of CT value accuracy, which is...
SourceID proquest
pubmed
crossref
wiley
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1163
SubjectTerms adaptive scatter kernel optimization
cone‐beam CT scatter correction
deep reinforcement learning
scatter kernel deconvolution algorithm
Title Adaptive scatter kernel deconvolution modeling for cone‐beam CT scatter correction via deep reinforcement learning
URI https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmp.16618
https://www.ncbi.nlm.nih.gov/pubmed/37459053
https://www.proquest.com/docview/2839246725
Volume 51
WOSCitedRecordID wos001026650400001&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 Full Collection 2020
  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/eLvHCXMwpV1LS8QwEB5848X3Y30RQfRUt02abXsUdfGgIqKyt5KmUxHdtWzXPfsT_I3-EidptyIqCJ56aJImnczMl8d8A7BHKFe2Mq2dMEXt-BkalUpSR0Q-uWPlSW0JTO_Og8vLsNOJrqpblSYWpuSHqDfcjGZYe20UXCVF85M0tJsfeuRcwnGYNDFVtPCaPLlu357XdphcaRmAEvnmDEGOqGdd3hzV_eqMviHMr4DVepz2_H_6ugBzFc5kR-XEWIQx7C3BzEV1kr4E0_bqpy6WYXCUqtwYPVZoS7bJHrFPH2SpWSsPq6nJbMoc8nOMUC6jF_j--pag6rLjm7qiNqk-bKAEGz4oagBz1kfLzartNiSrklTcr8Bt-_Tm-MypcjE4WhAKcJBgIClrQuJDTwkUPEgCpVvKFaGbejzzEoxSrjMPReCrFnqJikKpgsxNMz9EsQoTPerbOjDfpMGSLR-1Un7GXRWY_NcicaVMQyGCBhyMhBLriqjc5Mt4ikuKZR5389j-zgbs1iXzkpzjpzIjucakOeY4RPXw-aWIucGG5Ce4bMBaKfC6FRqDjMg-NWDfyvXX5uOLK_vc-GvBTZjlhIvKi99bMDHov-A2TOnh4KHo78B40Al3qpn8AWri9kg
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3JbtRAEC1NJiFwISFsAwlpJJScTOxevIhTFDIKyswoQhOUm9Vul1EUZrBmO_MJfCNfQnV7QRFEQsrJB3e3266ues-9vAJ4RyxXhYUxXpyj8WSB1qWy3BOJJDjWgTJOwPTLIBqN4qur5KIDH5qzMJU-RDvhZj3DxWvr4HZC-uiPauikfB8QusRrsC5DEcVdWP_4uX85aAMxYWl1AiWRdhFBNdqzPj9q6t5Go78o5m3G6iCnv3Wvzm7D45ppsuNqaDyBDk53YHNYr6XvwAO3-dPMn8LiONelDXtsbpzcJrvBGT2R5fZveVUPTuaS5hDSMeK5jG7grx8_M9QTdjJuKxqb7MMdlWCra00NYMlm6NRZjZuIZHWaiq_P4LJ_Oj458-psDJ4RxAM8JCJI7pqRATHQAgWPskibUPsi9vOAF0GGSc5NEaCIpA4xyHQSKx0Vfl7IGMVz6E6pby-BSZsIS4USjday4L6ObAZskflK5bEQUQ8OG6ukppYqtxkzvqWVyDJPJ2XqPmcP3rYly0qe419lGsOm5Dt2QURP8ftynnLLDgkpuOrBi8ribSv0DiqhCNWDA2fYO5tPhxfu-up_C-7Dw7PxcJAOPo3OX8MjTiyp2ga-C93FbIl7sGFWi-v57E09oH8DV2f5UA
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT9wwEB7BUlAvtIU-trTgSqicAokfm0ScEHRFxbJaVVBxixx7UqF2t9Husuf-hP7G_pKOnQdCFAmppxxiO07GM98XP74B2CWWq3qFMUFi0QSyQOdSuQ1EKgmOdaSMFzD9OoiHw-TqKh0twWFzFqbSh2gn3Jxn-HjtHBxLWxzcqoaOy_2I0CVZhhWpUiU7sHLypX85aAMxYWl1AiWVbhFBNdqzIT9o6t5Fo3sU8y5j9ZDTf_ZfnX0O6zXTZEfV0HgBSzjZgLXzei19A1b95k8z24T5kdWlC3tsZrzcJvuOU3ois-5veVEPTuaT5hDSMeK5jG7gn1-_c9RjdnzRVjQu2Yc_KsEW15oawJJN0auzGj8Ryeo0Fd9ewmX_08XxaVBnYwiMIB4QIBFBctecDIiRFih4nMfa9HQoktBGvIhyTC03RYQilrqHUa7TROm4CG0hExSvoDOhvr0BJl0iLNWTaLSWBQ917DJgizxUyiZCxF3Ya6ySmVqq3GXM-JFVIss8G5eZ_5xd-NCWLCt5jn-VaQybke-4BRE9wZ83s4w7dkhIwVUXXlcWb1uhd1ApRagufPSGfbD57Hzkr28fW3AH1kYn_WzweXi2BU85kaRqF_g76MynN_genpjF_Ho23a7H81_tC_jL
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=Adaptive+scatter+kernel+deconvolution+modeling+for+cone%E2%80%90beam+CT+scatter+correction+via+deep+reinforcement+learning&rft.jtitle=Medical+physics+%28Lancaster%29&rft.au=Piao%2C+Zun&rft.au=Deng%2C+Wenxin&rft.au=Huang%2C+Shuang&rft.au=Lin%2C+Guoqin&rft.date=2024-02-01&rft.issn=0094-2405&rft.eissn=2473-4209&rft.volume=51&rft.issue=2&rft.spage=1163&rft.epage=1177&rft_id=info:doi/10.1002%2Fmp.16618&rft.externalDBID=10.1002%252Fmp.16618&rft.externalDocID=MP16618
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