Multiatlas Fusion with a Hybrid CT Number Correction Technique for Subject-Specific Pseudo-CT Estimation in the Context of MRI-Only Radiation Therapy

To propose a hybrid multiatlas fusion and correction approach to estimate a pseudo-computed tomography (pCT) image from T2-weighted brain magnetic resonance (MR) images in the context of MRI-only radiotherapy. A set of eleven pairs of T2-weighted MR and CT brain images was included. Using leave-one-...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of medical imaging and radiation sciences Jg. 50; H. 3; S. 425
Hauptverfasser: Boukellouz, Wafa, Moussaoui, Abdelouahab, Taleb-Ahmed, Abdelmalik, Boydev, Christine
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States 01.09.2019
Schlagworte:
ISSN:1876-7982, 1876-7982
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract To propose a hybrid multiatlas fusion and correction approach to estimate a pseudo-computed tomography (pCT) image from T2-weighted brain magnetic resonance (MR) images in the context of MRI-only radiotherapy. A set of eleven pairs of T2-weighted MR and CT brain images was included. Using leave-one-out cross-validation, atlas MR images were registered to the target MRI with multimetric, multiresolution deformable registration. The subsequent deformations were applied to the atlas CT images, producing uncorrected pCT images. Afterward, a three-dimensional hybrid CT number correction technique was used. This technique uses information about MR intensity, spatial location, and tissue label from segmented MR images with the fuzzy c-means algorithm and combines them in a weighted fashion to correct Hounsfield unit values of the uncorrected pCT images. The corrected pCT images were then fused into a final pCT image. The proposed hybrid approach proved to be performant in correcting Hounsfield unit values in terms of qualitative and quantitative measures. Average correlation was 0.92 and 0.91 for the proposed approach by taking the mean and the median, respectively, compared with 0.86 for the uncorrected unfused version. Average values of dice similarity coefficient for bone were 0.68 and 0.72 for the fused corrected pCT images by taking the mean and the median, respectively, compared with 0.65 for the uncorrected unfused version indicating a significant bone estimation improvement. A hybrid fusion and correction method is presented to estimate a pCT image from T2-weighted brain MR images.
AbstractList To propose a hybrid multiatlas fusion and correction approach to estimate a pseudo-computed tomography (pCT) image from T2-weighted brain magnetic resonance (MR) images in the context of MRI-only radiotherapy.OBJECTIVETo propose a hybrid multiatlas fusion and correction approach to estimate a pseudo-computed tomography (pCT) image from T2-weighted brain magnetic resonance (MR) images in the context of MRI-only radiotherapy.A set of eleven pairs of T2-weighted MR and CT brain images was included. Using leave-one-out cross-validation, atlas MR images were registered to the target MRI with multimetric, multiresolution deformable registration. The subsequent deformations were applied to the atlas CT images, producing uncorrected pCT images. Afterward, a three-dimensional hybrid CT number correction technique was used. This technique uses information about MR intensity, spatial location, and tissue label from segmented MR images with the fuzzy c-means algorithm and combines them in a weighted fashion to correct Hounsfield unit values of the uncorrected pCT images. The corrected pCT images were then fused into a final pCT image.MATERIALS AND METHODSA set of eleven pairs of T2-weighted MR and CT brain images was included. Using leave-one-out cross-validation, atlas MR images were registered to the target MRI with multimetric, multiresolution deformable registration. The subsequent deformations were applied to the atlas CT images, producing uncorrected pCT images. Afterward, a three-dimensional hybrid CT number correction technique was used. This technique uses information about MR intensity, spatial location, and tissue label from segmented MR images with the fuzzy c-means algorithm and combines them in a weighted fashion to correct Hounsfield unit values of the uncorrected pCT images. The corrected pCT images were then fused into a final pCT image.The proposed hybrid approach proved to be performant in correcting Hounsfield unit values in terms of qualitative and quantitative measures. Average correlation was 0.92 and 0.91 for the proposed approach by taking the mean and the median, respectively, compared with 0.86 for the uncorrected unfused version. Average values of dice similarity coefficient for bone were 0.68 and 0.72 for the fused corrected pCT images by taking the mean and the median, respectively, compared with 0.65 for the uncorrected unfused version indicating a significant bone estimation improvement.RESULTSThe proposed hybrid approach proved to be performant in correcting Hounsfield unit values in terms of qualitative and quantitative measures. Average correlation was 0.92 and 0.91 for the proposed approach by taking the mean and the median, respectively, compared with 0.86 for the uncorrected unfused version. Average values of dice similarity coefficient for bone were 0.68 and 0.72 for the fused corrected pCT images by taking the mean and the median, respectively, compared with 0.65 for the uncorrected unfused version indicating a significant bone estimation improvement.A hybrid fusion and correction method is presented to estimate a pCT image from T2-weighted brain MR images.CONCLUSIONA hybrid fusion and correction method is presented to estimate a pCT image from T2-weighted brain MR images.
To propose a hybrid multiatlas fusion and correction approach to estimate a pseudo-computed tomography (pCT) image from T2-weighted brain magnetic resonance (MR) images in the context of MRI-only radiotherapy. A set of eleven pairs of T2-weighted MR and CT brain images was included. Using leave-one-out cross-validation, atlas MR images were registered to the target MRI with multimetric, multiresolution deformable registration. The subsequent deformations were applied to the atlas CT images, producing uncorrected pCT images. Afterward, a three-dimensional hybrid CT number correction technique was used. This technique uses information about MR intensity, spatial location, and tissue label from segmented MR images with the fuzzy c-means algorithm and combines them in a weighted fashion to correct Hounsfield unit values of the uncorrected pCT images. The corrected pCT images were then fused into a final pCT image. The proposed hybrid approach proved to be performant in correcting Hounsfield unit values in terms of qualitative and quantitative measures. Average correlation was 0.92 and 0.91 for the proposed approach by taking the mean and the median, respectively, compared with 0.86 for the uncorrected unfused version. Average values of dice similarity coefficient for bone were 0.68 and 0.72 for the fused corrected pCT images by taking the mean and the median, respectively, compared with 0.65 for the uncorrected unfused version indicating a significant bone estimation improvement. A hybrid fusion and correction method is presented to estimate a pCT image from T2-weighted brain MR images.
Author Boukellouz, Wafa
Boydev, Christine
Taleb-Ahmed, Abdelmalik
Moussaoui, Abdelouahab
Author_xml – sequence: 1
  givenname: Wafa
  surname: Boukellouz
  fullname: Boukellouz, Wafa
  email: w_boukellouz@outlook.fr
  organization: Department of Informatics, Ferhat Abbas University, Sétif, Algeria. Electronic address: w_boukellouz@outlook.fr
– sequence: 2
  givenname: Abdelouahab
  surname: Moussaoui
  fullname: Moussaoui, Abdelouahab
  organization: Department of Informatics, Ferhat Abbas University, Sétif, Algeria
– sequence: 3
  givenname: Abdelmalik
  surname: Taleb-Ahmed
  fullname: Taleb-Ahmed, Abdelmalik
  organization: IEMN, UMR CNRS 8520, Department OAE, University of Valenciennes and Hainaut-Cambresis, UVHC, Valenciennes, France
– sequence: 4
  givenname: Christine
  surname: Boydev
  fullname: Boydev, Christine
  organization: Department of Radiotherapy, Institut Curie - Hôpital René Huguenin Saint-Cloud, France
BackLink https://www.ncbi.nlm.nih.gov/pubmed/31128942$$D View this record in MEDLINE/PubMed
BookMark eNpNkMtKBDEURIMovn_AhWTpptvkTrqTXsrgqOALHddDOrlhMvRjTNLofIj_a_sCV3WhThXUPSDbXd8hISec5Zzx8nyVr1ofcmC8ytkk50pskX2uZJnJSsH2v3uPHMS4YqwEKatdsjfhHFQlYJ983A1N8jo1OtLZEH3f0TefllTT600dvKXTOb0f2hoDnfYhoElfyBzNsvOvA1LXB_o81KvRyJ7XaLzzhj5GHGyfjdHLmHyrvzO-o2mJY0uX8D3R3tG7p5vsoWs29Elb_wPNlxj0enNEdpxuIh7_6iF5mV3Op9fZ7cPVzfTiNjNC8JRZJpRgykHtAIvCOVEYW6jagnRG2kqXWOlCAmPKKnQguZO8nrDClNIVSsAhOfvpXYd-XBPTovXRYNPoDvshLgAmwAFExUb09Bcd6hbtYh3GYWGz-HslfAIBLHoa
CitedBy_id crossref_primary_10_1177_15330338231199286
ContentType Journal Article
Copyright Copyright © 2019. Published by Elsevier Inc.
Copyright_xml – notice: Copyright © 2019. Published by Elsevier Inc.
DBID NPM
7X8
DOI 10.1016/j.jmir.2019.03.184
DatabaseName PubMed
MEDLINE - Academic
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
PubMed
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 no_fulltext_linktorsrc
Discipline Medicine
EISSN 1876-7982
ExternalDocumentID 31128942
Genre Journal Article
GroupedDBID ---
--K
.1-
.FO
0R~
1B1
1P~
4.4
457
5GY
AAEDT
AAEDW
AALRI
AAXUO
ABJNI
ACGFS
ADBBV
ADPAM
ADVLN
AEVXI
AFJKZ
AFRHN
AFTJW
AITUG
AJUYK
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
BELOY
CS3
EBS
EFJIC
EJD
FDB
HZ~
KOM
M41
NPM
O9-
OI~
OU0
RIG
ROL
SEL
SES
XH2
Z5R
7X8
EFKBS
ID FETCH-LOGICAL-c441t-d048408f2bf2e55ff45cd58bd27fc7d9a6e9a572008d8ef271f71b305c67f5842
IEDL.DBID 7X8
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000485809400010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1876-7982
IngestDate Wed Oct 01 14:50:37 EDT 2025
Thu Jan 02 23:00:05 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 3
Keywords Pseudo-CT
hybrid CT number correction
multiatlas fusion
brain
MR-only radiotherapy
Language English
License Copyright © 2019. Published by Elsevier Inc.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c441t-d048408f2bf2e55ff45cd58bd27fc7d9a6e9a572008d8ef271f71b305c67f5842
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 31128942
PQID 2232122490
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2232122490
pubmed_primary_31128942
PublicationCentury 2000
PublicationDate 2019-Sep
20190901
PublicationDateYYYYMMDD 2019-09-01
PublicationDate_xml – month: 09
  year: 2019
  text: 2019-Sep
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Journal of medical imaging and radiation sciences
PublicationTitleAlternate J Med Imaging Radiat Sci
PublicationYear 2019
SSID ssj0062779
Score 2.1009963
Snippet To propose a hybrid multiatlas fusion and correction approach to estimate a pseudo-computed tomography (pCT) image from T2-weighted brain magnetic resonance...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 425
Title Multiatlas Fusion with a Hybrid CT Number Correction Technique for Subject-Specific Pseudo-CT Estimation in the Context of MRI-Only Radiation Therapy
URI https://www.ncbi.nlm.nih.gov/pubmed/31128942
https://www.proquest.com/docview/2232122490
Volume 50
WOSCitedRecordID wos000485809400010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Li9swEBbtppS9tN0-tumLKfQq1lZkyzotJWxID3FDyEJuQbIkcNna2U1Smh_S_9sZ2emeCoVefJMR8szo8zy-j7FPVlulXVZxrUaWS28kL4yW3BlH5OGJx2VRbEKVZbFa6XmfcNv2bZXHmBgDtWsrypFf4DUmqAqkk8vNLSfVKKqu9hIaD9lghFCGrFqt_lQRcqEi116KHs-VLkQ_NNP1d337XhMfaBpJTlNiN_0bxIxXzeTp_27yGXvSg0z43FnFGXvgm-fs8awvo79gv-LYrdkhcobJnvJlQPlYMDA90AQXjJdQRqkQGJN6R5x9gOWR7hUQ6AJGHErh8ChgH-oK5lu_dy3HpVcYNrqJSKgbQIQJkQPr5w7aALPFF_61uTnAglgRuhd3zAYv2fXkajme8l6fgVcIonbcoffLpAjCBuGzLASZVS4rrBMqVMppk3ttMkUdFq7wQag0qNRigKlyFRD4iFfspGkb_5qBDBaBUbAyCSNpZG6F9QL_Rq3zXlmXDtnH44Gv0f6pqGEa3-636_sjH7Lz7qutNx1Rx3qEYLLQUrz5h9Vv2SkZQ9c-9o4NAnq_f88eVT929fbuQzQsfJbz2W-r9doa
linkProvider ProQuest
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=Multiatlas+Fusion+with+a+Hybrid+CT+Number+Correction+Technique+for+Subject-Specific+Pseudo-CT+Estimation+in+the+Context+of+MRI-Only+Radiation+Therapy&rft.jtitle=Journal+of+medical+imaging+and+radiation+sciences&rft.au=Boukellouz%2C+Wafa&rft.au=Moussaoui%2C+Abdelouahab&rft.au=Taleb-Ahmed%2C+Abdelmalik&rft.au=Boydev%2C+Christine&rft.date=2019-09-01&rft.issn=1876-7982&rft.eissn=1876-7982&rft.volume=50&rft.issue=3&rft.spage=425&rft_id=info:doi/10.1016%2Fj.jmir.2019.03.184&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1876-7982&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1876-7982&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1876-7982&client=summon