Conditional Generative Adversarial Networks for Metal Artifact Reduction in CT Images of the Ear

We propose an approach based on a conditional generative adversarial network (cGAN) for the reduction of metal artifacts (RMA) in computed tomography (CT) ear images of cochlear implants (CIs) recipients. Our training set contains paired pre-implantation and post-implantation CTs of 90 ears. At the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Jg. 11070; S. 3
Hauptverfasser: Wang, Jianing, Zhao, Yiyuan, Noble, Jack H, Dawant, Benoit M
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Germany 01.01.2018
Schlagworte:
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract We propose an approach based on a conditional generative adversarial network (cGAN) for the reduction of metal artifacts (RMA) in computed tomography (CT) ear images of cochlear implants (CIs) recipients. Our training set contains paired pre-implantation and post-implantation CTs of 90 ears. At the training phase, the cGAN learns a mapping from the artifact-affected CTs to the artifact-free CTs. At the inference phase, given new metal-artifact-affected CTs, the cGAN produces CTs in which the artifacts are removed. As a pre-processing step, we also propose a band-wise normalization method, which splits a CT image into three channels according to the intensity value of each voxel and we show that this method improves the performance of the cGAN. We test our cGAN on post-implantation CTs of 74 ears and the quality of the artifact-corrected images is evaluated quantitatively by comparing the segmentations of intra-cochlear anatomical structures, which are obtained with a previously published method, in the real pre-implantation and the artifact-corrected CTs. We show that the proposed method leads to an average surface error of 0.18 mm which is about half of what could be achieved with a previously proposed technique.
AbstractList We propose an approach based on a conditional generative adversarial network (cGAN) for the reduction of metal artifacts (RMA) in computed tomography (CT) ear images of cochlear implants (CIs) recipients. Our training set contains paired pre-implantation and post-implantation CTs of 90 ears. At the training phase, the cGAN learns a mapping from the artifact-affected CTs to the artifact-free CTs. At the inference phase, given new metal-artifact-affected CTs, the cGAN produces CTs in which the artifacts are removed. As a pre-processing step, we also propose a band-wise normalization method, which splits a CT image into three channels according to the intensity value of each voxel and we show that this method improves the performance of the cGAN. We test our cGAN on post-implantation CTs of 74 ears and the quality of the artifact-corrected images is evaluated quantitatively by comparing the segmentations of intra-cochlear anatomical structures, which are obtained with a previously published method, in the real pre-implantation and the artifact-corrected CTs. We show that the proposed method leads to an average surface error of 0.18 mm which is about half of what could be achieved with a previously proposed technique.
We propose an approach based on a conditional generative adversarial network (cGAN) for the reduction of metal artifacts (RMA) in computed tomography (CT) ear images of cochlear implants (CIs) recipients. Our training set contains paired pre-implantation and post-implantation CTs of 90 ears. At the training phase, the cGAN learns a mapping from the artifact-affected CTs to the artifact-free CTs. At the inference phase, given new metal-artifact-affected CTs, the cGAN produces CTs in which the artifacts are removed. As a pre-processing step, we also propose a band-wise normalization method, which splits a CT image into three channels according to the intensity value of each voxel and we show that this method improves the performance of the cGAN. We test our cGAN on post-implantation CTs of 74 ears and the quality of the artifact-corrected images is evaluated quantitatively by comparing the segmentations of intra-cochlear anatomical structures, which are obtained with a previously published method, in the real pre-implantation and the artifact-corrected CTs. We show that the proposed method leads to an average surface error of 0.18 mm which is about half of what could be achieved with a previously proposed technique.We propose an approach based on a conditional generative adversarial network (cGAN) for the reduction of metal artifacts (RMA) in computed tomography (CT) ear images of cochlear implants (CIs) recipients. Our training set contains paired pre-implantation and post-implantation CTs of 90 ears. At the training phase, the cGAN learns a mapping from the artifact-affected CTs to the artifact-free CTs. At the inference phase, given new metal-artifact-affected CTs, the cGAN produces CTs in which the artifacts are removed. As a pre-processing step, we also propose a band-wise normalization method, which splits a CT image into three channels according to the intensity value of each voxel and we show that this method improves the performance of the cGAN. We test our cGAN on post-implantation CTs of 74 ears and the quality of the artifact-corrected images is evaluated quantitatively by comparing the segmentations of intra-cochlear anatomical structures, which are obtained with a previously published method, in the real pre-implantation and the artifact-corrected CTs. We show that the proposed method leads to an average surface error of 0.18 mm which is about half of what could be achieved with a previously proposed technique.
Author Wang, Jianing
Noble, Jack H
Dawant, Benoit M
Zhao, Yiyuan
Author_xml – sequence: 1
  givenname: Jianing
  surname: Wang
  fullname: Wang, Jianing
  organization: Dept. of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN 37235, USA
– sequence: 2
  givenname: Yiyuan
  surname: Zhao
  fullname: Zhao, Yiyuan
  organization: Dept. of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN 37235, USA
– sequence: 3
  givenname: Jack H
  surname: Noble
  fullname: Noble, Jack H
  organization: Dept. of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN 37235, USA
– sequence: 4
  givenname: Benoit M
  surname: Dawant
  fullname: Dawant, Benoit M
  organization: Dept. of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN 37235, USA
BackLink https://www.ncbi.nlm.nih.gov/pubmed/30693351$$D View this record in MEDLINE/PubMed
BookMark eNo1kL1OwzAYRT2A-Ck8ARLyyGKw4yS2xyoqpVIBCZU5OPEXMCR2sZ0i3p4gynSlo3PvcE_RgfMOELpg9JpRKm6UkIQTyimhVGWSsJodoWNOS8V5wU7QS-Wdscl6p3u8BAdBJ7sDPDc7CFEHO-EHSF8-fETc-YDvIU1oHpLtdJvwE5ix_a1j63C1watBv0LEvsPpDfBChzN02Ok-wvk-Z-j5drGp7sj6cbmq5mvynrMyEdkwkQtTSpBU0k6YXGnVtk1WdkzwoqQK8kZDyTnXRoGUjaDQQJ61TFFTmGyGrv52t8F_jhBTPdjYQt9rB36MdcaEyrlgXE3q5V4dmwFMvQ120OG7_n8l-wHbf1-j
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1007/978-3-030-00928-1_1
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle 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 no_fulltext_linktorsrc
ExternalDocumentID 30693351
Genre Journal Article
GrantInformation_xml – fundername: NIDCD NIH HHS
  grantid: R01 DC014037
– fundername: NIDCD NIH HHS
  grantid: R01 DC014462
GroupedDBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
ID FETCH-LOGICAL-j416t-8b1747d68e8080f7d49a9ccb26f1735609e4bae6333ad9e88b70ebe42c190d5d2
IEDL.DBID 7X8
ISICitedReferencesCount 103
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000477770600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Fri Jul 11 03:38:38 EDT 2025
Thu Apr 03 07:07:21 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Metal Artifact Reduction
Conditional Generative Adversarial Networks
Cochlear Implants
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-j416t-8b1747d68e8080f7d49a9ccb26f1735609e4bae6333ad9e88b70ebe42c190d5d2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 30693351
PQID 2179437139
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2179437139
pubmed_primary_30693351
PublicationCentury 2000
PublicationDate 2018-01-01
PublicationDateYYYYMMDD 2018-01-01
PublicationDate_xml – month: 01
  year: 2018
  text: 2018-01-01
  day: 01
PublicationDecade 2010
PublicationPlace Germany
PublicationPlace_xml – name: Germany
PublicationTitle Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
PublicationTitleAlternate Med Image Comput Comput Assist Interv
PublicationYear 2018
Score 2.572131
Snippet We propose an approach based on a conditional generative adversarial network (cGAN) for the reduction of metal artifacts (RMA) in computed tomography (CT) ear...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 3
SubjectTerms Algorithms
Cochlea - diagnostic imaging
Humans
Metals
Radiographic Image Enhancement
Radiographic Image Interpretation, Computer-Assisted
Reproducibility of Results
Sensitivity and Specificity
Tomography, X-Ray Computed
Title Conditional Generative Adversarial Networks for Metal Artifact Reduction in CT Images of the Ear
URI https://www.ncbi.nlm.nih.gov/pubmed/30693351
https://www.proquest.com/docview/2179437139
Volume 11070
WOSCitedRecordID wos000477770600001&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/eLvHCXMwpV1LS8QwEA7qevDiA1_riwheg23TbZKTyLKLHrYsssLeapqksILtuq3-fmearp4EwUsuIaXMTCffPPoNITd4R0G0Y5kNbMAAUgdM8jxhVimjAzCQKLTtsAmRpnI-V9Mu4VZ3bZVrn9g6alsZzJHfRi2VGYRU6m75znBqFFZXuxEam6THYQdbusRcfpMLef5YzsCQGZILQbyUhb9DyfZKGe_992X2yW4HJum91_4B2XDlIXkZVliGblN81LNKo0uj7ejlWqPB0dQ3f9cUICuduKZ7CP7lQJ-QzBWP00VJhzP6-AYup6ZVQQEr0pFeHZHn8Wg2fGDdHAX2CnCrYTKHsEPYRDokkSyEjZVWxuRRUoSCA-RRLs61Szjn2ionZS4C0G0cGUALdmCjY7JVVqU7JTQOQXeJxPKki02i80JqU3Adast5JKI-uV4LLAM7xeKDLl31UWc_IuuTEy_1bOkJNTIIWxTng_DsD6fPyQ5gFumzIBekV8BX6i7JtvlsFvXqqjUAWNPp5At2S7ya
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=Conditional+Generative+Adversarial+Networks+for+Metal+Artifact+Reduction+in+CT+Images+of+the+Ear&rft.jtitle=Medical+image+computing+and+computer-assisted+intervention+%3A+MICCAI+...+International+Conference+on+Medical+Image+Computing+and+Computer-Assisted+Intervention&rft.au=Wang%2C+Jianing&rft.au=Zhao%2C+Yiyuan&rft.au=Noble%2C+Jack+H&rft.au=Dawant%2C+Benoit+M&rft.date=2018-01-01&rft.volume=11070&rft.spage=3&rft_id=info:doi/10.1007%2F978-3-030-00928-1_1&rft.externalDBID=NO_FULL_TEXT