Augmenting Colonoscopy Using Extended and Directional CycleGAN for Lossy Image Translation

Colorectal cancer screening modalities, such as optical colonoscopy (OC) and virtual colonoscopy (VC), are critical for diagnosing and ultimately removing polyps (precursors for colon cancer). The non-invasive VC is normally used to inspect a 3D reconstructed colon (from computed tomography scans) f...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) Ročník 2020; s. 4695 - 4704
Hlavní autoři: Mathew, Shawn, Nadeem, Saad, Kumari, Sruti, Kaufman, Arie
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.06.2020
Témata:
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Colorectal cancer screening modalities, such as optical colonoscopy (OC) and virtual colonoscopy (VC), are critical for diagnosing and ultimately removing polyps (precursors for colon cancer). The non-invasive VC is normally used to inspect a 3D reconstructed colon (from computed tomography scans) for polyps and if found, the OC procedure is performed to physically traverse the colon via endoscope and remove these polyps. In this paper, we present a deep learning framework, Extended and Directional CycleGAN, for lossy unpaired image-to-image translation between OC and VC to augment OC video sequences with scale-consistent depth information from VC and VC with patient-specific textures, color and specular highlights from OC (e.g. for realistic polyp synthesis). Both OC and VC contain structural information, but it is obscured in OC by additional patient-specific texture and specular highlights, hence making the translation from OC to VC lossy. The existing CycleGAN approaches do not handle lossy transformations. To address this shortcoming, we introduce an extended cycle consistency loss, which compares the geometric structures from OC in the VC domain. This loss removes the need for the CycleGAN to embed OC information in the VC domain. To handle a stronger removal of the textures and lighting, a Directional Discriminator is introduced to differentiate the direction of translation (by creating paired information for the discriminator), as opposed to the standard CycleGAN which is direction-agnostic. Combining the extended cycle consistency loss and the Directional Discriminator, we show state-of-the-art results on scale-consistent depth inference for phantom, textured VC and for real polyp and normal colon video sequences. We also present results for realistic pendunculated and flat polyp synthesis from bumps introduced in 3D VC models.
AbstractList Colorectal cancer screening modalities, such as optical colonoscopy (OC) and virtual colonoscopy (VC), are critical for diagnosing and ultimately removing polyps (precursors of colon cancer). The non-invasive VC is normally used to inspect a 3D reconstructed colon (from CT scans) for polyps and if found, the OC procedure is performed to physically traverse the colon via endoscope and remove these polyps. In this paper, we present a deep learning framework, Extended and Directional CycleGAN, for lossy unpaired image-to-image translation between OC and VC to augment OC video sequences with scale-consistent depth information from VC, and augment VC with patient-specific textures, color and specular highlights from OC (e.g, for realistic polyp synthesis). Both OC and VC contain structural information, but it is obscured in OC by additional patient-specific texture and specular highlights, hence making the translation from OC to VC lossy. The existing CycleGAN approaches do not handle lossy transformations. To address this shortcoming, we introduce an extended cycle consistency loss, which compares the geometric structures from OC in the VC domain. This loss removes the need for the CycleGAN to embed OC information in the VC domain. To handle a stronger removal of the textures and lighting, a Directional Discriminator is introduced to differentiate the direction of translation (by creating paired information for the discriminator), as opposed to the standard CycleGAN which is direction-agnostic. Combining the extended cycle consistency loss and the Directional Discriminator, we show state-of-the-art results on scale-consistent depth inference for phantom, textured VC and for real polyp and normal colon video sequences. We also present results for realistic pendunculated and flat polyp synthesis from bumps introduced in 3D VC models.
Colorectal cancer screening modalities, such as optical colonoscopy (OC) and virtual colonoscopy (VC), are critical for diagnosing and ultimately removing polyps (precursors for colon cancer). The non-invasive VC is normally used to inspect a 3D reconstructed colon (from computed tomography scans) for polyps and if found, the OC procedure is performed to physically traverse the colon via endoscope and remove these polyps. In this paper, we present a deep learning framework, Extended and Directional CycleGAN, for lossy unpaired image-to-image translation between OC and VC to augment OC video sequences with scale-consistent depth information from VC and VC with patient-specific textures, color and specular highlights from OC (e.g. for realistic polyp synthesis). Both OC and VC contain structural information, but it is obscured in OC by additional patient-specific texture and specular highlights, hence making the translation from OC to VC lossy. The existing CycleGAN approaches do not handle lossy transformations. To address this shortcoming, we introduce an extended cycle consistency loss, which compares the geometric structures from OC in the VC domain. This loss removes the need for the CycleGAN to embed OC information in the VC domain. To handle a stronger removal of the textures and lighting, a Directional Discriminator is introduced to differentiate the direction of translation (by creating paired information for the discriminator), as opposed to the standard CycleGAN which is direction-agnostic. Combining the extended cycle consistency loss and the Directional Discriminator, we show state-of-the-art results on scale-consistent depth inference for phantom, textured VC and for real polyp and normal colon video sequences. We also present results for realistic pendunculated and flat polyp synthesis from bumps introduced in 3D VC models.
Colorectal cancer screening modalities, such as optical colonoscopy (OC) and virtual colonoscopy (VC), are critical for diagnosing and ultimately removing polyps (precursors of colon cancer). The non-invasive VC is normally used to inspect a 3D reconstructed colon (from CT scans) for polyps and if found, the OC procedure is performed to physically traverse the colon via endoscope and remove these polyps. In this paper, we present a deep learning framework, Extended and Directional CycleGAN, for lossy unpaired image-to-image translation between OC and VC to augment OC video sequences with scale-consistent depth information from VC, and augment VC with patient-specific textures, color and specular highlights from OC (e.g, for realistic polyp synthesis). Both OC and VC contain structural information, but it is obscured in OC by additional patient-specific texture and specular highlights, hence making the translation from OC to VC lossy. The existing CycleGAN approaches do not handle lossy transformations. To address this shortcoming, we introduce an extended cycle consistency loss, which compares the geometric structures from OC in the VC domain. This loss removes the need for the CycleGAN to embed OC information in the VC domain. To handle a stronger removal of the textures and lighting, a Directional Discriminator is introduced to differentiate the direction of translation (by creating paired information for the discriminator), as opposed to the standard CycleGAN which is direction-agnostic. Combining the extended cycle consistency loss and the Directional Discriminator, we show state-of-the-art results on scale-consistent depth inference for phantom, textured VC and for real polyp and normal colon video sequences. We also present results for realistic pendunculated and flat polyp synthesis from bumps introduced in 3D VC models.Colorectal cancer screening modalities, such as optical colonoscopy (OC) and virtual colonoscopy (VC), are critical for diagnosing and ultimately removing polyps (precursors of colon cancer). The non-invasive VC is normally used to inspect a 3D reconstructed colon (from CT scans) for polyps and if found, the OC procedure is performed to physically traverse the colon via endoscope and remove these polyps. In this paper, we present a deep learning framework, Extended and Directional CycleGAN, for lossy unpaired image-to-image translation between OC and VC to augment OC video sequences with scale-consistent depth information from VC, and augment VC with patient-specific textures, color and specular highlights from OC (e.g, for realistic polyp synthesis). Both OC and VC contain structural information, but it is obscured in OC by additional patient-specific texture and specular highlights, hence making the translation from OC to VC lossy. The existing CycleGAN approaches do not handle lossy transformations. To address this shortcoming, we introduce an extended cycle consistency loss, which compares the geometric structures from OC in the VC domain. This loss removes the need for the CycleGAN to embed OC information in the VC domain. To handle a stronger removal of the textures and lighting, a Directional Discriminator is introduced to differentiate the direction of translation (by creating paired information for the discriminator), as opposed to the standard CycleGAN which is direction-agnostic. Combining the extended cycle consistency loss and the Directional Discriminator, we show state-of-the-art results on scale-consistent depth inference for phantom, textured VC and for real polyp and normal colon video sequences. We also present results for realistic pendunculated and flat polyp synthesis from bumps introduced in 3D VC models.
Author Kaufman, Arie
Kumari, Sruti
Nadeem, Saad
Mathew, Shawn
AuthorAffiliation 2 Memorial Sloan Kettering Cancer Center
1 Stony Brook University
AuthorAffiliation_xml – name: 2 Memorial Sloan Kettering Cancer Center
– name: 1 Stony Brook University
Author_xml – sequence: 1
  givenname: Shawn
  surname: Mathew
  fullname: Mathew, Shawn
  organization: Stony Brook University
– sequence: 2
  givenname: Saad
  surname: Nadeem
  fullname: Nadeem, Saad
  organization: Memorial Sloan Kettering Cancer Center
– sequence: 3
  givenname: Sruti
  surname: Kumari
  fullname: Kumari, Sruti
  organization: Stony Brook University
– sequence: 4
  givenname: Arie
  surname: Kaufman
  fullname: Kaufman, Arie
  organization: Stony Brook University
BackLink https://www.ncbi.nlm.nih.gov/pubmed/33456298$$D View this record in MEDLINE/PubMed
BookMark eNpVUMtO6zAQNQh0gdIvuFfISzYtHju2482VqvCUKkAIWLCJXGdajBK7xCmif08QD8FiHppzdM7M7JGtEAMS8g_YGICZo-L--ibjirExZ5yNGcu03CBDo3PQvA9Qudwku8CUGCkDZutHv0OGKT0xxgQHUCb_Q3aEyKTiJt8lD5PVosHQ-bCgRaxjiMnF5ZrepffJyWuHocKK2lDRY9-i63wMtqbF2tV4Nrmk89jSaUxpTS8au0B629qQavtO2yfbc1snHH7WAbk7PbktzkfTq7OLYjIdeQFZNwKuNUflEESluewz5HN0xs0M4xwhk4y7mbRCzfhco2KIGpg0BhVwC0IMyP8P3eVq1mDl-mtaW5fL1je2XZfR-vI3EvxjuYgvZf88AC17gcNPgTY-rzB1ZeOTw7q2AeMqlTzTudYm63cbkIOfXt8mXw_tCX8_CB4Rv2EDUkkD4g1RxYfL
CODEN IEEPAD
ContentType Conference Proceeding
Journal Article
DBID 6IE
6IH
CBEJK
RIE
RIO
NPM
7X8
5PM
DOI 10.1109/CVPR42600.2020.00475
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle 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: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Computer Science
EISBN 9781728171685
1728171687
EISSN 1063-6919
EndPage 4704
ExternalDocumentID PMC7811175
33456298
9156591
Genre orig-research
Journal Article
GrantInformation_xml – fundername: NHLBI NIH HHS
  grantid: U01 HL127522
– fundername: NCI NIH HHS
  grantid: P30 CA008748
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
23M
29F
29O
6IK
ABDPE
ACGFS
IPLJI
M43
NPM
RIG
RNS
7X8
5PM
ID FETCH-LOGICAL-i314t-12772e6ce13d72513d18fec9cb9022e14502cb5a36b2f7e60ee710599e612a133
IEDL.DBID RIE
ISICitedReferencesCount 51
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000620679504097&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1063-6919
IngestDate Thu Aug 21 18:24:17 EDT 2025
Fri Sep 05 10:39:28 EDT 2025
Wed Feb 19 02:04:13 EST 2025
Wed Aug 27 02:30:35 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i314t-12772e6ce13d72513d18fec9cb9022e14502cb5a36b2f7e60ee710599e612a133
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Equal Contribution
PMID 33456298
PQID 2478779451
PQPubID 23479
PageCount 10
ParticipantIDs pubmed_primary_33456298
pubmedcentral_primary_oai_pubmedcentral_nih_gov_7811175
proquest_miscellaneous_2478779451
ieee_primary_9156591
PublicationCentury 2000
PublicationDate 20200601
PublicationDateYYYYMMDD 2020-06-01
PublicationDate_xml – month: 6
  year: 2020
  text: 20200601
  day: 1
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationTitleAlternate Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit
PublicationYear 2020
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
ssj0023720
Score 2.570898
Snippet Colorectal cancer screening modalities, such as optical colonoscopy (OC) and virtual colonoscopy (VC), are critical for diagnosing and ultimately removing...
SourceID pubmedcentral
proquest
pubmed
ieee
SourceType Open Access Repository
Aggregation Database
Index Database
Publisher
StartPage 4695
SubjectTerms Cancer
Colon
Endoscopes
Gallium nitride
Image reconstruction
Machine learning
Three-dimensional displays
Title Augmenting Colonoscopy Using Extended and Directional CycleGAN for Lossy Image Translation
URI https://ieeexplore.ieee.org/document/9156591
https://www.ncbi.nlm.nih.gov/pubmed/33456298
https://www.proquest.com/docview/2478779451
https://pubmed.ncbi.nlm.nih.gov/PMC7811175
Volume 2020
WOSCitedRecordID wos000620679504097&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JTsMwELUK4sCJHcpSGYkjoY0dx_GxisoioapCUFVcIieeQA-kqAtS_56xE8KiXrhFiiNZ9mTmPfvNDCEXWmVB2NHM87WRSFCM8KI8zT1jWCpMYCS4dkDDe9nvR6ORGjTIZZ0LAwBOfAZX9tHd5ZtJtrBHZW2FZEPYVPU1KWWZq1Wfp3BkMqGKquw4v6Pa8XDw4OqvIwtkVsAVWDGh66GyCk7-VUX-CDPXW_-b4DbZ_87Xo4M6Eu2QBhS7ZKsCmLT6fWd75Lm7eHHyoOKFxuj1iolNSllSpxugveo8nOrC0MoVWpxO4yXa1k23TxHg0nuMqkt694Z-iLpAV4rp9snTde8xvvWq5gremPvB3PMZ4moIM_C5kQhyuPGjHDKVpQrDOviB6LAsFZqHKcslhB0AabGYAsREGpntAVkvJgUcEZrpgOU8yJG6IB7TUstIMKFNxA1XQSiaZM8uVfJe1s9IqlVqkvOvTUjQpu1FhS5gspglzFYMQkchcMxhuSn1x5xbzqaiJpG_tqseYOtl_35TjF9d3WybVIto6Xj1dE7IprWTUgZ2Stbn0wWckY3sYz6eTVtocqOo5UzuE8x-19c
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fT9swED5VMIk9AYNtZWN4Eo9kNP4Rx4-oglFRqmoChHiJnPjC-kCKaIvU_35nJws_xAtvkeJIln25-z77uzuAfWsKmfQsj2LrNBEUp6K0zMvIOZ4rJ53G0A7oaqhHo_T62ow7cNDmwiBiEJ_hL_8Y7vLdtFj4o7JDQ2RD-VT1VSUlj-tsrfZERRCXSUza5MfFPXPYvxr_CRXYiQdyL-GSXk4Yuqi8BShf6yKfBZqT9fdNcQO2nzL22LiNRZvQweoTrDcQkzU_8GwLbo4Wt0EgVN2yPvm9aurTUpYsKAfYcXMizmzlWOMMPVJn_SVZ1--jESOIy4YUV5dscEeeiIVQV8vptuHy5Piifxo17RWiiYjlPIo5IWtMCoyF0wRzhIvTEgtT5IYCO8ZS9XiRKyuSnJcakx6i9mjMIKEiS9z2M6xU0wq_Aius5KWQJZEXQmRWW50qrqxLhRNGJqoLW36psvu6gkbWrFIXfv7fhIys2l9V2Aqni1nGfc0gchWKxnypN6X9WAjP2kzaBf1iu9oBvmL2yzfV5G-onO3Tagkv7bw9nT1YO704H2bDwejsG3z0NlOLwr7DyvxhgbvwoXicT2YPP4Lh_QMR4do2
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%3Abook&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=Augmenting+Colonoscopy+Using+Extended+and+Directional+CycleGAN+for+Lossy+Image+Translation&rft.au=Mathew%2C+Shawn&rft.au=Nadeem%2C+Saad&rft.au=Kumari%2C+Sruti&rft.au=Kaufman%2C+Arie&rft.date=2020-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=4695&rft.epage=4704&rft_id=info:doi/10.1109%2FCVPR42600.2020.00475&rft.externalDocID=9156591
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6919&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6919&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6919&client=summon