Separation of color channels from conventional colonoscopy images improves deep neural network detection of polyps

Significance: Colorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on polyp detection and discrimination. Aim: To advance detection and discrimination using currently available commercial colonoscopy systems, we de...

Full description

Saved in:
Bibliographic Details
Published inJournal of biomedical optics Vol. 26; no. 1; p. 015001
Main Authors Lai, Lily L, Blakely, Andrew, Invernizzi, Marta, Lin, James, Kidambi, Trilokesh, Melstrom, Kurt A, Yu, Kevin, Lu, Thomas
Format Journal Article
LanguageEnglish
Published United States Society of Photo-Optical Instrumentation Engineers 01.01.2021
S P I E - International Society for
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Significance: Colorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on polyp detection and discrimination. Aim: To advance detection and discrimination using currently available commercial colonoscopy systems, we developed a deep neural network (DNN) separating the color channels from images acquired under narrow-band imaging (NBI) and white-light endoscopy (WLE). Approach: Images of normal colon mucosa and polyps from colonoscopies were studied. Each color image was extracted based on the color channel: red/green/blue. A multilayer DNN was trained using one-channel, two-channel, and full-color images. The trained DNN was then tested for performance in detection of polyps. Results: The DNN performed better using full-colored NBI over WLE images in the detection of polyps. Furthermore, the DNN performed better using the two-channel red + green images when compared to full-color WLE images. Conclusions: The separation of color channels from full-color NBI and WLE images taken from commercially available colonoscopes may improve the ability of the DNN to detect and discriminate polyps. Further studies are needed to better determine the color channels and combination of channels to include and exclude in DNN development for clinical use.
AbstractList SIGNIFICANCEColorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on polyp detection and discrimination. AIMTo advance detection and discrimination using currently available commercial colonoscopy systems, we developed a deep neural network (DNN) separating the color channels from images acquired under narrow-band imaging (NBI) and white-light endoscopy (WLE). APPROACHImages of normal colon mucosa and polyps from colonoscopies were studied. Each color image was extracted based on the color channel: red/green/blue. A multilayer DNN was trained using one-channel, two-channel, and full-color images. The trained DNN was then tested for performance in detection of polyps. RESULTSThe DNN performed better using full-colored NBI over WLE images in the detection of polyps. Furthermore, the DNN performed better using the two-channel red + green images when compared to full-color WLE images. CONCLUSIONSThe separation of color channels from full-color NBI and WLE images taken from commercially available colonoscopes may improve the ability of the DNN to detect and discriminate polyps. Further studies are needed to better determine the color channels and combination of channels to include and exclude in DNN development for clinical use.
Significance: Colorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on polyp detection and discrimination.Aim: To advance detection and discrimination using currently available commercial colonoscopy systems, we developed a deep neural network (DNN) separating the color channels from images acquired under narrow-band imaging (NBI) and white-light endoscopy (WLE).Approach: Images of normal colon mucosa and polyps from colonoscopies were studied. Each color image was extracted based on the color channel: red/green/blue. A multilayer DNN was trained using one-channel, two-channel, and full-color images. The trained DNN was then tested for performance in detection of polyps.Results: The DNN performed better using full-colored NBI over WLE images in the detection of polyps. Furthermore, the DNN performed better using the two-channel red + green images when compared to full-color WLE images.Conclusions: The separation of color channels from full-color NBI and WLE images taken from commercially available colonoscopes may improve the ability of the DNN to detect and discriminate polyps. Further studies are needed to better determine the color channels and combination of channels to include and exclude in DNN development for clinical use.
Colorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on polyp detection and discrimination. To advance detection and discrimination using currently available commercial colonoscopy systems, we developed a deep neural network (DNN) separating the color channels from images acquired under narrow-band imaging (NBI) and white-light endoscopy (WLE). Images of normal colon mucosa and polyps from colonoscopies were studied. Each color image was extracted based on the color channel: red/green/blue. A multilayer DNN was trained using one-channel, two-channel, and full-color images. The trained DNN was then tested for performance in detection of polyps. The DNN performed better using full-colored NBI over WLE images in the detection of polyps. Furthermore, the DNN performed better using the two-channel red + green images when compared to full-color WLE images. The separation of color channels from full-color NBI and WLE images taken from commercially available colonoscopes may improve the ability of the DNN to detect and discriminate polyps. Further studies are needed to better determine the color channels and combination of channels to include and exclude in DNN development for clinical use.
Significance : Colorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on polyp detection and discrimination. Aim : To advance detection and discrimination using currently available commercial colonoscopy systems, we developed a deep neural network (DNN) separating the color channels from images acquired under narrow-band imaging (NBI) and white-light endoscopy (WLE). Approach : Images of normal colon mucosa and polyps from colonoscopies were studied. Each color image was extracted based on the color channel: red/green/blue. A multilayer DNN was trained using one-channel, two-channel, and full-color images. The trained DNN was then tested for performance in detection of polyps. Results : The DNN performed better using full-colored NBI over WLE images in the detection of polyps. Furthermore, the DNN performed better using the two-channel red + green images when compared to full-color WLE images. Conclusions : The separation of color channels from full-color NBI and WLE images taken from commercially available colonoscopes may improve the ability of the DNN to detect and discriminate polyps. Further studies are needed to better determine the color channels and combination of channels to include and exclude in DNN development for clinical use.
Significance: Colorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on polyp detection and discrimination. Aim: To advance detection and discrimination using currently available commercial colonoscopy systems, we developed a deep neural network (DNN) separating the color channels from images acquired under narrow-band imaging (NBI) and white-light endoscopy (WLE). Approach: Images of normal colon mucosa and polyps from colonoscopies were studied. Each color image was extracted based on the color channel: red/green/blue. A multilayer DNN was trained using one-channel, two-channel, and full-color images. The trained DNN was then tested for performance in detection of polyps. Results: The DNN performed better using full-colored NBI over WLE images in the detection of polyps. Furthermore, the DNN performed better using the two-channel red + green images when compared to full-color WLE images. Conclusions: The separation of color channels from full-color NBI and WLE images taken from commercially available colonoscopes may improve the ability of the DNN to detect and discriminate polyps. Further studies are needed to better determine the color channels and combination of channels to include and exclude in DNN development for clinical use.
Author Melstrom, Kurt A
Yu, Kevin
Lin, James
Blakely, Andrew
Lu, Thomas
Kidambi, Trilokesh
Invernizzi, Marta
Lai, Lily L
Author_xml – sequence: 1
  givenname: Lily L
  orcidid: 0000-0001-6639-4485
  surname: Lai
  fullname: Lai, Lily L
  email: llai@coh.org
  organization: City of Hope, Department of Surgery, Duarte, California, United States
– sequence: 2
  givenname: Andrew
  surname: Blakely
  fullname: Blakely, Andrew
  email: andrew.blakely@nih.gov
  organization: National Cancer Institute, National Institutes of Health Campus, Department of Surgery, Bethesda, Maryland, United States
– sequence: 3
  givenname: Marta
  surname: Invernizzi
  fullname: Invernizzi, Marta
  email: minvernizzi@coh.org
  organization: City of Hope, Department of Surgery, Duarte, California, United States
– sequence: 4
  givenname: James
  surname: Lin
  fullname: Lin, James
  email: jalin@coh.org
  organization: City of Hope, Division of Gastroenterology, Duarte, California, United States
– sequence: 5
  givenname: Trilokesh
  orcidid: 0000-0002-1138-2492
  surname: Kidambi
  fullname: Kidambi, Trilokesh
  email: trkidambi@coh.org
  organization: City of Hope, Division of Gastroenterology, Duarte, California, United States
– sequence: 6
  givenname: Kurt A
  orcidid: 0000-0001-8085-998X
  surname: Melstrom
  fullname: Melstrom, Kurt A
  email: kmelstrom@coh.org
  organization: City of Hope, Department of Surgery, Duarte, California, United States
– sequence: 7
  givenname: Kevin
  surname: Yu
  fullname: Yu, Kevin
  email: kyu@caltech.edu
  organization: Jet Propulsion Labarotory, Pasadena, California, United States
– sequence: 8
  givenname: Thomas
  surname: Lu
  fullname: Lu, Thomas
  email: Thomas.t.lu@jpl.nasa.gov
  organization: Jet Propulsion Labarotory, Pasadena, California, United States
BackLink https://www.ncbi.nlm.nih.gov/pubmed/33442965$$D View this record in MEDLINE/PubMed
BookMark eNp1kUtv1DAQxy1URB_wAbigSFy4JHic-JELEq14qlIPwNnyeidtStY2drJovz3TblseEqcZjX_znxn_j9lBiAEZew68AQD9GprPpxeNUA00HCTn8IgdgVS8FsLAAeXctHWrlDlkx6Vcc86N6tUTdti2XSd6JY9Y_oLJZTePMVRxqHycYq78lQsBp1INOW6oFrYYbgg33QIhFh_Trho37hILhZTjlpI1YqoCLpm4gPPPmL9TbUZ_r57itEvlKXs8uKngs7t4wr69f_f17GN9fvHh09nb89pL6OZ66DUHJ3Gl2rUYENTa9JKDFrrnrkMlhO9BOw9OdcNq5bjvtBkkV0q3rRG8PWFv9rppWW1w7ekG2symTHvnnY1utH-_hPHKXsat1YbLzkgSeHUnkOOPBctsN2PxOE0uYFyKFTSQd0DDCH35D3odl0wfRpSRvVRa3VKwp3yOpWQcHpYBbm8ctWDJUSsUJXtHqefFn1c8dNxbSECzB0oa8ffY_yv-AjX1rnY
CitedBy_id crossref_primary_10_3389_fonc_2022_1087438
crossref_primary_10_1007_s10462_021_10034_y
crossref_primary_10_1016_j_ijmedinf_2023_105142
crossref_primary_10_3390_cancers13215494
crossref_primary_10_3390_jcm11092431
crossref_primary_10_3748_wjg_v27_i21_2681
crossref_primary_10_7717_peerj_cs_2059
crossref_primary_10_1007_s00371_021_02322_z
crossref_primary_10_3390_cancers13092025
crossref_primary_10_3904_kjim_2023_332
crossref_primary_10_1016_j_canlet_2023_216238
crossref_primary_10_3390_jcm11144056
ContentType Journal Article
Copyright The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.
2021. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
2021 The Authors 2021 The Authors
Copyright_xml – notice: The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.
– notice: 2021. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: 2021 The Authors 2021 The Authors
DBID NPM
AAYXX
CITATION
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
8FE
8FH
ABUWG
AFKRA
AZQEC
BBNVY
BENPR
BHPHI
CCPQU
DWQXO
F28
FR3
GNUQQ
H8D
H8G
HCIFZ
JG9
JQ2
KR7
L7M
LK8
L~C
L~D
M7P
P64
PIMPY
PQEST
PQQKQ
PQUKI
7X8
5PM
DOI 10.1117/1.JBO.26.1.015001
DatabaseName PubMed
CrossRef
Aluminium Industry Abstracts
Biotechnology Research Abstracts
Ceramic Abstracts
Computer and Information Systems Abstracts
Corrosion Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
Materials Business File
Mechanical & Transportation Engineering Abstracts
Solid State and Superconductivity Abstracts
METADEX
Technology Research Database
ProQuest SciTech Collection
ProQuest Natural Science Collection
ProQuest Central (Alumni)
ProQuest Central
ProQuest Central Essentials
Biological Science Collection
ProQuest Central
Natural Science Collection
ProQuest One Community College
ProQuest Central Korea
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
ProQuest Central Student
Aerospace Database
Copper Technical Reference Library
SciTech Premium Collection
Materials Research Database
ProQuest Computer Science Collection
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Biological Sciences
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Biological Science Database
Biotechnology and BioEngineering Abstracts
Publicly Available Content (ProQuest)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic
ProQuest One Academic UKI Edition
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle PubMed
CrossRef
Publicly Available Content Database
Materials Research Database
ProQuest Central Student
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Natural Science Collection
Materials Business File
ProQuest Central
Aerospace Database
Copper Technical Reference Library
Engineered Materials Abstracts
Biotechnology Research Abstracts
Natural Science Collection
ProQuest Central Korea
Biological Science Collection
Advanced Technologies Database with Aerospace
ANTE: Abstracts in New Technology & Engineering
Civil Engineering Abstracts
Aluminium Industry Abstracts
ProQuest Biological Science Collection
ProQuest One Academic Eastern Edition
Electronics & Communications Abstracts
Ceramic Abstracts
Biological Science Database
ProQuest SciTech Collection
METADEX
Biotechnology and BioEngineering Abstracts
Computer and Information Systems Abstracts Professional
ProQuest One Academic UKI Edition
Solid State and Superconductivity Abstracts
Engineering Research Database
ProQuest One Academic
Corrosion Abstracts
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
Publicly Available Content Database
PubMed


Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: BENPR
  name: AUTh Library subscriptions: ProQuest Central
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Biology
Physics
EISSN 1560-2281
EndPage 015001
ExternalDocumentID 10_1117_1_JBO_26_1_015001
33442965
Genre Journal Article
GrantInformation_xml – fundername: University of California, Riverside
  funderid: https://doi.org/10.13039/100007602
– fundername: City of Hope National Medical Center
– fundername: University of California, Riverside
GroupedDBID -
0R
29J
53G
5GY
ABPTK
ACGFS
ADBBV
ADCOW
AENEX
ALMA_UNASSIGNED_HOLDINGS
BCNDV
CS3
DU5
EBS
F5P
FQ0
GROUPED_DOAJ
HZ
O9-
OK1
P2P
RNS
RPM
SPBNH
UPT
UT2
W2D
---
0R~
4.4
AAFWJ
ACBEA
ACGFO
AFKRA
AFPKN
BBNVY
BENPR
BHPHI
CCPQU
EJD
HCIFZ
HYE
HZ~
M4W
M4X
M7P
NPM
NU.
PBYJJ
PIMPY
YQT
AAYXX
CITATION
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
8FE
8FH
ABUWG
AZQEC
DWQXO
F28
FR3
GNUQQ
H8D
H8G
JG9
JQ2
KR7
L7M
LK8
L~C
L~D
P64
PQEST
PQQKQ
PQUKI
7X8
5PM
ID FETCH-LOGICAL-c514t-f9701a5eb63d2fe16d8950172790a4e622c917ac1a64fbba0c478f50667338203
IEDL.DBID RPM
ISSN 1083-3668
IngestDate Tue Sep 17 21:38:22 EDT 2024
Fri Jun 28 13:45:51 EDT 2024
Thu Oct 10 19:11:37 EDT 2024
Fri Dec 06 05:44:02 EST 2024
Wed Oct 16 00:44:42 EDT 2024
Tue Feb 02 04:31:32 EST 2021
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords artificial intelligence algorithms
deep learning
color channel separation
colorectal cancer
polyp discrimination
narrow-band imaging
Language English
License Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c514t-f9701a5eb63d2fe16d8950172790a4e622c917ac1a64fbba0c478f50667338203
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0001-8085-998X
0000-0002-1138-2492
0000-0001-6639-4485
OpenAccessLink https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7805485/
PMID 33442965
PQID 2859567682
PQPubID 2049439
PageCount 1
ParticipantIDs proquest_miscellaneous_2478041382
proquest_journals_2859567682
spie_journals_10_1117_1_JBO_26_1_015001
pubmedcentral_primary_oai_pubmedcentral_nih_gov_7805485
pubmed_primary_33442965
crossref_primary_10_1117_1_JBO_26_1_015001
ProviderPackageCode FQ0
SPBNH
UT2
PublicationCentury 2000
PublicationDate 2021-01-01
PublicationDateYYYYMMDD 2021-01-01
PublicationDate_xml – month: 01
  year: 2021
  text: 2021-01-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Bellingham
PublicationTitle Journal of biomedical optics
PublicationTitleAlternate J. Biomed. Opt
PublicationYear 2021
Publisher Society of Photo-Optical Instrumentation Engineers
S P I E - International Society for
Publisher_xml – name: Society of Photo-Optical Instrumentation Engineers
– name: S P I E - International Society for
SSID ssj0008696
Score 2.443171
Snippet Significance: Colorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on...
Colorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on polyp detection...
SIGNIFICANCEColorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on polyp...
Significance : Colorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on...
SourceID pubmedcentral
proquest
crossref
pubmed
spie
SourceType Open Access Repository
Aggregation Database
Index Database
Publisher
StartPage 015001
SubjectTerms Artificial intelligence
Artificial neural networks
Cancer
Channels
Colon
Colonoscopy
Color
Color imagery
Colorectal carcinoma
Endoscopy
Image acquisition
Image processing
Machine learning
Medical imaging
Multilayers
Neural networks
Patients
Polyps
Rectum
Separation
Surveillance
Tumors
White light
SummonAdditionalLinks – databaseName: ProQuest Central
  dbid: BENPR
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3daxQxEA96RbAPovXrtEoEQRByvXxsNvskVlpKwSpqoW_LJpvQA93d3l4f7r93JpvbXin6tCGZ_chOMh_J5DeEvM-sNM4Hz0ThFENAJWaFlSwYZ3MLGkoGdBS_numTc3V6kV2kBbc-hVVuZGIU1HXrcI38AIHWMg3GsfjUXTHMGoW7qymFxn2yI7g0ZkJ2Do_Ovv8YZbHRMUMXB0ODSa1N2tfkPD_gs9PDbzOhZ3yGXn_KCjNqpjvm5t2oyUnfLfyWNjp-TB4lM5J-Hvj-hNzzzR55MCSWXO-R3S2YQaiPYZ6uf0qWP_2A9d02tA0UEauXFM_-NqAiKR41odth6JGgafHkypou_oDo6eGCqxBQqL3vKMJhAl0zBJND3SqGdsWnd-3vddc_I-fHR7--nLCUdYE5MJ5WLBT5nFeZt1rWIniua1Nk6CnmxbxSXgvhwMWrHK-0CtZWc6dyE7KYP1SCPSGfk0nTNv4locKBw4KIaaHQyovMAo2zHkSIqYPg9ZR83PzxshvANcrBKclLXgJ7SqGhMLBnSvY3PCnTPOvLm1ExJe_GZpghuO1RNb69BhoVQZYk0rwYWDi-TUoFCllnU5LfYu5IgOjbt1uaxWVE4cZkEMrAnR9wGNx80j878Or_HXhNHgqMl4nLO_tkslpe-zdg8Kzs2zSq_wIrS_6E
  priority: 102
  providerName: ProQuest
Title Separation of color channels from conventional colonoscopy images improves deep neural network detection of polyps
URI http://www.dx.doi.org/10.1117/1.JBO.26.1.015001
https://www.ncbi.nlm.nih.gov/pubmed/33442965
https://www.proquest.com/docview/2859567682
https://search.proquest.com/docview/2478041382
https://pubmed.ncbi.nlm.nih.gov/PMC7805485
Volume 26
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3fa9swED7ajMH2MLbul7cueDAYDOxEki3bj2tpKYV2ZVuhb8aSJRpoZBOnD_nvdyfbWUrZy55s7MOWfZLuTvruO4AvqRK5NtZEvNBJRIRKkeJKRDbXKlNooYSlQPHiUp5dJ-c36c0epGMujAfta7WI3d0ydotbj61sl3o24sRmVxfHxMOf5OlsH_bR_I4h-jD95tIX5WLoW0RCynzYymQsm7H4_OhHzGXMYgr051QmRogEp2SyLbt26ZGz-RgzOenahdmxRacv4cXgRIbf-8a-gj3jDuBpX1ZycwDPd0gG8boHeeruNax-mZ7pu3FhY0Piq16FlPnr0ECGlGgS7oLQvYBrKG9lEy6WOPF0eKA1CDypjWlDIsNEOddDyfHa2gO7_NPb5m7Tdm_g-vTk9_FZNNRciDS6TuvIFtmcValRUtTcGibrvEgpTsyKeZUYybnGAK_SrJKJVaqa6yTLbeqrhwr0JsRbmLjGmfcQco3hCvGl2UImhqcKZbQyOIHkteWsDuDb-MfLtqfWKPuQJCtZiZoqucSTXlMBHI46KYdR1pVEvpdKDJh4AJ-3t3F80KZH5UxzjzKJp1gSJPOuV-H2baPuA8geKHcrQNzbD-9gl_Qc3EMXDOArdYO_TfrnB3z473d8hGecgDR-3ecQJuvVvfmEntBaTeHJ0cnl1c-pX0mY-nHwBxOXCKA
link.rule.ids 230,314,727,780,784,864,885,21388,27924,27925,33744,33745,43805,53791,53793,74302
linkProvider National Library of Medicine
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3db9MwED9BJ8T2gGAwKAwIEhISUrraTpzkadrQpjK2gmCT9hbFji0qDSdruof-99w5adZpgqdY9uXDOfs-7PPvAD7GSqTaWBPyTEchASqFiisR2lSrRKGGEpYcxbOpnFxEJ5fxZbfg1nRhlSuZ6AV1WWlaI98joLVYonHM9-vrkLJG0e5ql0LjIWwQcno8gI3Do-mPn70sTqXP0MXQ0AiFlGm3r8lYssdGJ4ffR1yO2Ii8_i4rTK-Z7pmb96MmB009M2va6PgpPOnMyOCg5fszeGDcNjxqE0sut2FrDWYQ632Yp26ew_yXabG-KxdUNiDE6nlAZ38dqsiAjpoE62HonsBVdHJlGcz-oOhp8EKrEFgojakDgsNEOtcGk2Pdwod2-afX1dWybl7AxfHR-ZdJ2GVdCDUaT4vQZsmYFbFRUpTcGibLNIvJU0yycREZyblGF6_QrJCRVaoY6yhJbezzhwq0J8QODFzlzCsIuEaHhRDTbCYjw2OFNFoZFCFpaTkrh_B59cfzugXXyFunJMlZjuzJucRCy54h7K54knfzrMlvR8UQPvTNOENo26NwprpBmsiDLAmiedmysH-bEBEqZBkPIbnD3J6A0LfvtrjZb4_CTckgohTv_ETD4PaT_tmB1__vwHt4PDk_O81Pv06_vYFNTrEzfqlnFwaL-Y15i8bPQr3rRvhfNB8Bew
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3db9MwED9BJxA8IBgfKxsQJCQkpLS1nTjJE2KwagwoEzBpb1Hs2KLSlmRN99D_fneOm3Wa4ClRckmb3OU-7J9_B_AuViLVxpqQZzoKiVApVFyJ0KZaJQojlLBUKP6YycOT6Og0PvX4p9bDKtc-0TnqstY0Rj4morVYYnLMx9bDIo6_TD82FyF1kKKZVt9O4y5sYVSc8AFs7R_Mjn_1fjmVrlsXw6QjFFKmfo6TsWTMRkf7P0dcjtiIRgB8h5g-St1KPW8jKAdtMzcbkWn6GB75lDL41NnAE7hjqm241zWZXG3Dww3KQTzuIJ-6fQqL36bj_a6roLYBsVcvAloHXGG4DGjZSbAJSXcCVU2rWFbB_BzdUIsbGpHAndKYJiBqTJSrOmA5Hls6mJe7e1OfrZr2GZxMD_58Pgx9B4ZQYyK1DG2WTFgRGyVFya1hskyzmKrGJJsUkZGcayz3Cs0KGVmliomOktTGrpeowNxCPIdBVVdmBwKusXgh9jSbycjwWKGMVgbdSVpazsohfFi_8bzpiDbyrkBJcpajenIucadTzxD21jrJ_TfX5tcWMoS3_Wn8WmgKpKhMfYkykSNcEiTzolNh_2tCRBicZTyE5IZyewFi4r55ppr_dYzc1BgiSvHK92QG13_pnw_w8v8P8Abuo3Hn37_Ovu3CA04wGjfqsweD5eLSvMI8aKleewO_AkeLBag
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=Separation+of+color+channels+from+conventional+colonoscopy+images+improves+deep+neural+network+detection+of+polyps&rft.jtitle=Journal+of+biomedical+optics&rft.au=Lai%2C+Lily+L&rft.au=Blakely%2C+Andrew&rft.au=Invernizzi%2C+Marta&rft.au=Lin%2C+James&rft.date=2021-01-01&rft.pub=Society+of+Photo-Optical+Instrumentation+Engineers&rft.issn=1083-3668&rft.eissn=1560-2281&rft.volume=26&rft.issue=1&rft.spage=015001&rft.epage=015001&rft_id=info:doi/10.1117%2F1.JBO.26.1.015001&rft.externalDocID=10_1117_1_JBO_26_1_015001
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1083-3668&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1083-3668&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1083-3668&client=summon