Endoscopic detection and differentiation of esophageal lesions using a deep neural network

Diagnosing esophageal squamous cell carcinoma (SCC) depends on individual physician expertise and may be subject to interobserver variability. Therefore, we developed a computerized image-analysis system to detect and differentiate esophageal SCC. A total of 9591 nonmagnified endoscopy (non-ME) and...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Gastrointestinal endoscopy Ročník 91; číslo 2; s. 301 - 309.e1
Hlavní autori:	Ohmori, Masayasu, Ishihara, Ryu, Aoyama, Kazuharu, Nakagawa, Kentaro, Iwagami, Hiroyoshi, Matsuura, Noriko, Shichijo, Satoki, Yamamoto, Katsumi, Nagaike, Koji, Nakahara, Masanori, Inoue, Takuya, Aoi, Kenji, Okada, Hiroyuki, Tada, Tomohiro
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States Elsevier Inc 01.02.2020
Predmet:	Adult Aged Aged, 80 and over Deep Learning Esophageal Diseases - diagnostic imaging Esophageal Diseases - pathology Esophageal Neoplasms - diagnostic imaging Esophageal Neoplasms - pathology Esophageal Squamous Cell Carcinoma - diagnostic imaging Esophageal Squamous Cell Carcinoma - pathology Esophagus - pathology Female Humans Image Processing, Computer-Assisted - methods Male Middle Aged Narrow Band Imaging - methods Neoplasm Invasiveness Neural Networks, Computer Observer Variation Optical Imaging - methods Precancerous Conditions - diagnostic imaging Precancerous Conditions - pathology Reproducibility of Results Sensitivity and Specificity CNN SCC NBI WLI AI ME BLI
ISSN:	0016-5107, 1097-6779, 1097-6779
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Diagnosing esophageal squamous cell carcinoma (SCC) depends on individual physician expertise and may be subject to interobserver variability. Therefore, we developed a computerized image-analysis system to detect and differentiate esophageal SCC. A total of 9591 nonmagnified endoscopy (non-ME) and 7844 ME images of pathologically confirmed superficial esophageal SCCs and 1692 non-ME and 3435 ME images from noncancerous lesions or normal esophagus were used as training image data. Validation was performed using 255 non-ME white-light images, 268 non-ME narrow-band images/blue-laser images, and 204 ME narrow-band images/blue-laser images from 135 patients. The same validation test data were diagnosed by 15 board-certified specialists (experienced endoscopists). Regarding diagnosis by non-ME with narrow-band imaging/blue-laser imaging, the sensitivity, specificity, and accuracy were 100%, 63%, and 77%, respectively, for the artificial intelligence (AI) system and 92%, 69%, and 78%, respectively, for the experienced endoscopists. Regarding diagnosis by non-ME with white-light imaging, the sensitivity, specificity, and accuracy were 90%, 76%, and 81%, respectively, for the AI system and 87%, 67%, and 75%, respectively, for the experienced endoscopists. Regarding diagnosis by ME, the sensitivity, specificity, and accuracy were 98%, 56%, and 77%, respectively, for the AI system and 83%, 70%, and 76%, respectively, for the experienced endoscopists. There was no significant difference in the diagnostic performance between the AI system and the experienced endoscopists. Our AI system showed high sensitivity for detecting SCC by non-ME and high accuracy for differentiating SCC from noncancerous lesions by ME.
AbstractList	Diagnosing esophageal squamous cell carcinoma (SCC) depends on individual physician expertise and may be subject to interobserver variability. Therefore, we developed a computerized image-analysis system to detect and differentiate esophageal SCC.BACKGROUND AND AIMSDiagnosing esophageal squamous cell carcinoma (SCC) depends on individual physician expertise and may be subject to interobserver variability. Therefore, we developed a computerized image-analysis system to detect and differentiate esophageal SCC.A total of 9591 nonmagnified endoscopy (non-ME) and 7844 ME images of pathologically confirmed superficial esophageal SCCs and 1692 non-ME and 3435 ME images from noncancerous lesions or normal esophagus were used as training image data. Validation was performed using 255 non-ME white-light images, 268 non-ME narrow-band images/blue-laser images, and 204 ME narrow-band images/blue-laser images from 135 patients. The same validation test data were diagnosed by 15 board-certified specialists (experienced endoscopists).METHODSA total of 9591 nonmagnified endoscopy (non-ME) and 7844 ME images of pathologically confirmed superficial esophageal SCCs and 1692 non-ME and 3435 ME images from noncancerous lesions or normal esophagus were used as training image data. Validation was performed using 255 non-ME white-light images, 268 non-ME narrow-band images/blue-laser images, and 204 ME narrow-band images/blue-laser images from 135 patients. The same validation test data were diagnosed by 15 board-certified specialists (experienced endoscopists).Regarding diagnosis by non-ME with narrow-band imaging/blue-laser imaging, the sensitivity, specificity, and accuracy were 100%, 63%, and 77%, respectively, for the artificial intelligence (AI) system and 92%, 69%, and 78%, respectively, for the experienced endoscopists. Regarding diagnosis by non-ME with white-light imaging, the sensitivity, specificity, and accuracy were 90%, 76%, and 81%, respectively, for the AI system and 87%, 67%, and 75%, respectively, for the experienced endoscopists. Regarding diagnosis by ME, the sensitivity, specificity, and accuracy were 98%, 56%, and 77%, respectively, for the AI system and 83%, 70%, and 76%, respectively, for the experienced endoscopists. There was no significant difference in the diagnostic performance between the AI system and the experienced endoscopists.RESULTSRegarding diagnosis by non-ME with narrow-band imaging/blue-laser imaging, the sensitivity, specificity, and accuracy were 100%, 63%, and 77%, respectively, for the artificial intelligence (AI) system and 92%, 69%, and 78%, respectively, for the experienced endoscopists. Regarding diagnosis by non-ME with white-light imaging, the sensitivity, specificity, and accuracy were 90%, 76%, and 81%, respectively, for the AI system and 87%, 67%, and 75%, respectively, for the experienced endoscopists. Regarding diagnosis by ME, the sensitivity, specificity, and accuracy were 98%, 56%, and 77%, respectively, for the AI system and 83%, 70%, and 76%, respectively, for the experienced endoscopists. There was no significant difference in the diagnostic performance between the AI system and the experienced endoscopists.Our AI system showed high sensitivity for detecting SCC by non-ME and high accuracy for differentiating SCC from noncancerous lesions by ME.CONCLUSIONSOur AI system showed high sensitivity for detecting SCC by non-ME and high accuracy for differentiating SCC from noncancerous lesions by ME. Diagnosing esophageal squamous cell carcinoma (SCC) depends on individual physician expertise and may be subject to interobserver variability. Therefore, we developed a computerized image-analysis system to detect and differentiate esophageal SCC. A total of 9591 nonmagnified endoscopy (non-ME) and 7844 ME images of pathologically confirmed superficial esophageal SCCs and 1692 non-ME and 3435 ME images from noncancerous lesions or normal esophagus were used as training image data. Validation was performed using 255 non-ME white-light images, 268 non-ME narrow-band images/blue-laser images, and 204 ME narrow-band images/blue-laser images from 135 patients. The same validation test data were diagnosed by 15 board-certified specialists (experienced endoscopists). Regarding diagnosis by non-ME with narrow-band imaging/blue-laser imaging, the sensitivity, specificity, and accuracy were 100%, 63%, and 77%, respectively, for the artificial intelligence (AI) system and 92%, 69%, and 78%, respectively, for the experienced endoscopists. Regarding diagnosis by non-ME with white-light imaging, the sensitivity, specificity, and accuracy were 90%, 76%, and 81%, respectively, for the AI system and 87%, 67%, and 75%, respectively, for the experienced endoscopists. Regarding diagnosis by ME, the sensitivity, specificity, and accuracy were 98%, 56%, and 77%, respectively, for the AI system and 83%, 70%, and 76%, respectively, for the experienced endoscopists. There was no significant difference in the diagnostic performance between the AI system and the experienced endoscopists. Our AI system showed high sensitivity for detecting SCC by non-ME and high accuracy for differentiating SCC from noncancerous lesions by ME.
Author	Yamamoto, Katsumi Nakahara, Masanori Okada, Hiroyuki Aoyama, Kazuharu Inoue, Takuya Ohmori, Masayasu Aoi, Kenji Matsuura, Noriko Tada, Tomohiro Iwagami, Hiroyoshi Nakagawa, Kentaro Shichijo, Satoki Nagaike, Koji Ishihara, Ryu
Author_xml	– sequence: 1 givenname: Masayasu surname: Ohmori fullname: Ohmori, Masayasu organization: Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan – sequence: 2 givenname: Ryu surname: Ishihara fullname: Ishihara, Ryu organization: Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan – sequence: 3 givenname: Kazuharu surname: Aoyama fullname: Aoyama, Kazuharu organization: AI Medical Service Inc, Tokyo, Japan – sequence: 4 givenname: Kentaro surname: Nakagawa fullname: Nakagawa, Kentaro organization: Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan – sequence: 5 givenname: Hiroyoshi surname: Iwagami fullname: Iwagami, Hiroyoshi organization: Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan – sequence: 6 givenname: Noriko surname: Matsuura fullname: Matsuura, Noriko organization: Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan – sequence: 7 givenname: Satoki surname: Shichijo fullname: Shichijo, Satoki organization: Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan – sequence: 8 givenname: Katsumi surname: Yamamoto fullname: Yamamoto, Katsumi organization: Department of Gastroenterology, Japan Community Healthcare Organization, Osaka Hospital, Osaka, Japan – sequence: 9 givenname: Koji surname: Nagaike fullname: Nagaike, Koji organization: Department of Gastroenterology, Suita Municipal Hospital, Osaka, Japan – sequence: 10 givenname: Masanori surname: Nakahara fullname: Nakahara, Masanori organization: Department of Gastroenterology, Ikeda Municipal Hospital, Osaka, Japan – sequence: 11 givenname: Takuya surname: Inoue fullname: Inoue, Takuya organization: Department of Gastroenterology, Osaka General Medical Center, Osaka, Japan – sequence: 12 givenname: Kenji surname: Aoi fullname: Aoi, Kenji organization: Department of Gastroenterology, Kaiduka City Hospital, Osaka, Japan – sequence: 13 givenname: Hiroyuki surname: Okada fullname: Okada, Hiroyuki organization: Department of Gastroenterology and Hepatology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan – sequence: 14 givenname: Tomohiro surname: Tada fullname: Tada, Tomohiro organization: AI Medical Service Inc, Tokyo, Japan
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/31585124$$D View this record in MEDLINE/PubMed
BookMark	eNqFkU1rHCEYgKWkNJuPH5BLmGMus3kddZwlpxDSDwj00l56EUdft25mdaIzKfn3dbNpDjmkIAivzyPyeEQOQgxIyBmFJQXaXm6Wa4_LBuhqCWUx_oEsKKxk3Uq5OiALKFAtKMhDcpTzBgC6htFP5JBR0Qna8AX5dRtszCaO3lQWJzSTj6HSwVbWO4cJw-T18yy6CnMcf-s16qEaMJdhrubsw7rSxcWxCjinchZw-hPT_Qn56PSQ8fRlPyY_P9_-uPla333_8u3m-q425QlTjQKg7500fYeUubbVTjIOHfLONQyBGS5boTmXFl3fcUCuhbRGCt1K4Xp2TC72944pPsyYJ7X12eAw6IBxzqphQDmnvBEFPX9B536LVo3Jb3V6Uv96FIDuAZNizgndK0JB7ZqrjSrN1a65grLYzpFvHOOn52ZT0n5417zam1jyPHpMKhuPwaD1qfyEstG_a6_e2GbwwRs93OPTf9y_LVivQw
CitedBy_id	crossref_primary_10_1007_s11517_023_02777_3 crossref_primary_10_1136_gutjnl_2021_326271 crossref_primary_10_3748_wjg_v27_i40_6794 crossref_primary_10_1007_s00464_021_08666_w crossref_primary_10_3390_diagnostics13193023 crossref_primary_10_3389_fphy_2022_1033422 crossref_primary_10_1007_s12672_023_00694_3 crossref_primary_10_1016_j_inffus_2022_11_023 crossref_primary_10_1038_s41598_021_87405_6 crossref_primary_10_1002_lary_29894 crossref_primary_10_1007_s11938_021_00353_y crossref_primary_10_1109_TAI_2021_3134600 crossref_primary_10_1259_bjr_20210934 crossref_primary_10_1177_26345161231211752 crossref_primary_10_1111_den_13908 crossref_primary_10_1016_j_gie_2020_05_043 crossref_primary_10_1093_dote_doac010 crossref_primary_10_3390_cancers14235996 crossref_primary_10_1007_s00521_024_09615_z crossref_primary_10_1097_JS9_0000000000002748 crossref_primary_10_3390_diagnostics11040694 crossref_primary_10_1016_j_bpg_2020_101723 crossref_primary_10_1111_jgh_15354 crossref_primary_10_1016_j_giec_2024_09_003 crossref_primary_10_3389_fonc_2022_766243 crossref_primary_10_1055_a_1500_3730 crossref_primary_10_4251_wjgo_v16_i4_1180 crossref_primary_10_3390_diagnostics12092222 crossref_primary_10_1097_MCG_0000000000001629 crossref_primary_10_3390_diagnostics15131664 crossref_primary_10_3389_fonc_2024_1423405 crossref_primary_10_4251_wjgo_v14_i5_989 crossref_primary_10_1016_j_gie_2022_12_003 crossref_primary_10_1007_s00464_020_08150_x crossref_primary_10_1097_CM9_0000000000003490 crossref_primary_10_3748_wjg_v27_i14_1392 crossref_primary_10_1007_s10620_021_07086_z crossref_primary_10_3748_wjg_v26_i39_5959 crossref_primary_10_1111_den_13934 crossref_primary_10_1016_j_giec_2024_10_003 crossref_primary_10_1111_apt_16778 crossref_primary_10_1186_s12876_023_02788_2 crossref_primary_10_1016_j_canlet_2025_217555 crossref_primary_10_1093_dote_doad048 crossref_primary_10_1111_den_13897 crossref_primary_10_1016_j_dld_2020_11_017 crossref_primary_10_1055_a_1950_5694 crossref_primary_10_3390_diagnostics11091719 crossref_primary_10_3390_diagnostics13182862 crossref_primary_10_4251_wjgo_v15_i11_1998 crossref_primary_10_1097_MEG_0000000000002162 crossref_primary_10_1159_000518232 crossref_primary_10_3892_ol_2025_15039 crossref_primary_10_1186_s13640_024_00634_3 crossref_primary_10_1007_s11042_024_18910_9 crossref_primary_10_1007_s10620_020_06643_2 crossref_primary_10_3389_frai_2024_1446693 crossref_primary_10_1111_1751_2980_12992 crossref_primary_10_3748_wjg_v31_i36_110742 crossref_primary_10_1002_mp_16041 crossref_primary_10_1053_j_gastro_2021_11_040 crossref_primary_10_14309_ctg_0000000000000433 crossref_primary_10_1007_s00595_023_02708_7 crossref_primary_10_1111_den_13800 crossref_primary_10_1136_gutjnl_2020_321922 crossref_primary_10_14309_ctg_0000000000000154 crossref_primary_10_3390_jcm11092529 crossref_primary_10_3748_wjg_v26_i38_5784 crossref_primary_10_1111_den_14538 crossref_primary_10_1016_j_eswa_2024_124838 crossref_primary_10_14309_ctg_0000000000000393 crossref_primary_10_1038_s41598_025_86829_8 crossref_primary_10_1002_deo2_72 crossref_primary_10_1016_j_gie_2020_11_025 crossref_primary_10_3390_cancers13215494 crossref_primary_10_1007_s10278_023_00803_2 crossref_primary_10_3390_medicina56070364 crossref_primary_10_1111_den_13837 crossref_primary_10_1016_j_compbiomed_2020_104026 crossref_primary_10_1111_jgh_15725 crossref_primary_10_3233_XST_230111 crossref_primary_10_1016_j_gie_2020_06_034 crossref_primary_10_3748_wjg_v31_i19_104897 crossref_primary_10_3390_cancers13020321 crossref_primary_10_3748_wjg_v26_i35_5256 crossref_primary_10_1111_jgh_15689 crossref_primary_10_3389_fonc_2023_1215729 crossref_primary_10_1038_s41598_022_10739_2 crossref_primary_10_3389_fonc_2023_1198941 crossref_primary_10_1159_000540251
Cites_doi	10.1111/j.1572-0241.2005.30189.x 10.1186/s12885-016-3011-9 10.1038/ajg.2013.8 10.1007/s10388-009-0169-0 10.1055/s-2007-966761 10.1001/jama.2016.17216 10.1111/j.1442-2050.2009.01039.x 10.1038/nature21056 10.1016/j.gie.2018.07.037 10.2307/2529310 10.1016/S1010-7940(01)01003-X 10.1155/2016/6140854 10.1002/ijc.31937 10.1007/s10388-018-0651-7 10.1200/JCO.2009.25.4680 10.1007/s10120-018-0793-2 10.1002/(SICI)1097-0142(19980715)83:2<220::AID-CNCR4>3.0.CO;2-U 10.1055/a-0756-8754 10.1038/ajg.2011.42 10.1117/1.1695563 10.1038/ajg.2014.94 10.1038/bmt.2012.244 10.1016/S0039-6060(98)70165-5 10.1016/S0016-5107(02)70043-6 10.1055/s-0034-1390707 10.1038/ajg.2009.426 10.1007/s11263-015-0816-y
ContentType	Journal Article
Copyright	2020 American Society for Gastrointestinal Endoscopy Copyright © 2020 American Society for Gastrointestinal Endoscopy. Published by Elsevier Inc. All rights reserved.
Copyright_xml	– notice: 2020 American Society for Gastrointestinal Endoscopy – notice: Copyright © 2020 American Society for Gastrointestinal Endoscopy. Published by Elsevier Inc. All rights reserved.
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1016/j.gie.2019.09.034
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 - Academic MEDLINE
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
EISSN	1097-6779
EndPage	309.e1
ExternalDocumentID	31585124 10_1016_j_gie_2019_09_034 S0016510719323016
Genre	Journal Article
GroupedDBID	--- --K --M .1- .55 .FO .GJ .~1 0R~ 1B1 1P~ 1RT 1~. 1~5 3O- 4.4 457 4G. 53G 5GY 5RE 5VS 7-5 71M 8P~ 9JM AABNK AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQQT AAQXK AATTM AAWTL AAXKI AAXUO AAYWO ABBQC ABFNM ABFRF ABJNI ABMAC ABMZM ABWVN ABXDB ACDAQ ACGFO ACGFS ACIEU ACLOT ACRLP ACRPL ACVFH ADBBV ADCNI ADEZE ADMUD ADNMO ADVLN AEBSH AEFWE AEIPS AEKER AENEX AEUPX AEVXI AFFNX AFJKZ AFPUW AFRHN AFTJW AFXIZ AGHFR AGQPQ AGUBO AGYEJ AHHHB AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX APXCP ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC BNPGV CS3 DU5 EBS EFJIC EFKBS EFLBG EJD EO8 EO9 EP2 EP3 EX3 F5P FD8 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HDZ HMK HMO HVGLF HZ~ IHE J1W K-O KOM L7B LZ1 M28 M41 MO0 N4W N9A O-L O9- OAUVE OC. ON0 OZT P-8 P-9 P2P PC. Q38 R2- ROL RPZ SAE SDF SDG SEL SES SEW SJN SPCBC SSH SSZ T5K UNMZH UV1 WH7 WOW X7M Z5R ZGI ZXP ~G- ~HD AACTN AAIAV ABLVK ABYKQ AFCTW AFKWA AHPSJ AJBFU AJOXV AMFUW LCYCR RIG 9DU AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8
ID	FETCH-LOGICAL-c512t-e500bbf7cb8e13f66af73408e48f23e03c4765a447defb840e4a57dc75a675fb3
ISICitedReferencesCount	99
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000508567300013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0016-5107 1097-6779
IngestDate	Sun Sep 28 01:24:04 EDT 2025 Thu Apr 03 07:08:03 EDT 2025 Tue Nov 18 22:13:33 EST 2025 Sat Nov 29 07:35:02 EST 2025 Fri Feb 23 02:49:32 EST 2024 Tue Oct 14 19:36:04 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	2
Keywords	CNN SCC NBI WLI AI ME BLI
Language	English
License	Copyright © 2020 American Society for Gastrointestinal Endoscopy. Published by Elsevier Inc. All rights reserved.
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c512t-e500bbf7cb8e13f66af73408e48f23e03c4765a447defb840e4a57dc75a675fb3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
OpenAccessLink	https://doi.org/10.1016/j.gie.2019.09.034
PMID	31585124
PQID	2301441425
PQPubID	23479
ParticipantIDs	proquest_miscellaneous_2301441425 pubmed_primary_31585124 crossref_primary_10_1016_j_gie_2019_09_034 crossref_citationtrail_10_1016_j_gie_2019_09_034 elsevier_sciencedirect_doi_10_1016_j_gie_2019_09_034 elsevier_clinicalkey_doi_10_1016_j_gie_2019_09_034
PublicationCentury	2000
PublicationDate	February 2020 2020-02-00 20200201
PublicationDateYYYYMMDD	2020-02-01
PublicationDate_xml	– month: 02 year: 2020 text: February 2020
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	Gastrointestinal endoscopy
PublicationTitleAlternate	Gastrointest Endosc
PublicationYear	2020
Publisher	Elsevier Inc
Publisher_xml	– name: Elsevier Inc
References	Tomie, Dohi, Yagi (bib15) 2016; 2016 Ishihara, Takeuchi, Chatani (bib28) 2010; 23 Ishihara, Takeuchi, Chatani (bib13) 2010; 23 Gono, Obi, Yamaguchi (bib10) 2004; 9 Morita, Bernardo, Ide (bib16) 2017; 17 Hirasawa, Aoyama, Tanimoto (bib21) 2018; 21 Horie, Yoshio, Aoyama (bib22) 2019; 89 Esteva, Kuprel, Novoa (bib19) 2017; 542 Zhao, Xue, Wang (bib26) 2019; 51 Nagami, Tominaga, Machida (bib17) 2014; 109 Russakovsky, Deng, Su (bib18) 2015; 115 Kanda (bib25) 2013; 48 Yamamoto, Ishihara, Motoori (bib7) 2011; 106 Landis, Koch (bib24) 1977; 33 Dawsey, Fleischer, Wang (bib9) 1998; 83 Katada, Muto, Momma (bib4) 2007; 39 Yamashina, Ishihara, Nagai (bib3) 2013; 108 Society (bib23) 2009; 6 Shimizu, Tsukagoshi, Fujita (bib5) 2002; 56 Kumagai, Takubo, Kawada (bib27) 2019; 16 Kodama, Kakegawa (bib2) 1998; 123 Igaki, Kato, Tachimori (bib6) 2001; 20 Kaneko, Oono, Yano (bib14) 2014; 2 Takenaka, Kawahara, Okada (bib12) 2009; 104 Hashimoto, Iriya, Baba (bib8) 2005; 100 Ferlay, Colombet, Soerjomataram (bib1) 2019; 144 Muto, Minashi, Yano (bib11) 2010; 28 Gulshan, Peng, Coram (bib20) 2016; 316 Tomie (10.1016/j.gie.2019.09.034_bib15) 2016; 2016 Shimizu (10.1016/j.gie.2019.09.034_bib5) 2002; 56 Yamamoto (10.1016/j.gie.2019.09.034_bib7) 2011; 106 Hashimoto (10.1016/j.gie.2019.09.034_bib8) 2005; 100 Muto (10.1016/j.gie.2019.09.034_bib11) 2010; 28 Hirasawa (10.1016/j.gie.2019.09.034_bib21) 2018; 21 Landis (10.1016/j.gie.2019.09.034_bib24) 1977; 33 Dawsey (10.1016/j.gie.2019.09.034_bib9) 1998; 83 Morita (10.1016/j.gie.2019.09.034_bib16) 2017; 17 Ishihara (10.1016/j.gie.2019.09.034_bib28) 2010; 23 Yamashina (10.1016/j.gie.2019.09.034_bib3) 2013; 108 Kaneko (10.1016/j.gie.2019.09.034_bib14) 2014; 2 Igaki (10.1016/j.gie.2019.09.034_bib6) 2001; 20 Ferlay (10.1016/j.gie.2019.09.034_bib1) 2019; 144 Gono (10.1016/j.gie.2019.09.034_bib10) 2004; 9 Kanda (10.1016/j.gie.2019.09.034_bib25) 2013; 48 Katada (10.1016/j.gie.2019.09.034_bib4) 2007; 39 Nagami (10.1016/j.gie.2019.09.034_bib17) 2014; 109 Takenaka (10.1016/j.gie.2019.09.034_bib12) 2009; 104 Horie (10.1016/j.gie.2019.09.034_bib22) 2019; 89 Zhao (10.1016/j.gie.2019.09.034_bib26) 2019; 51 Gulshan (10.1016/j.gie.2019.09.034_bib20) 2016; 316 Kodama (10.1016/j.gie.2019.09.034_bib2) 1998; 123 Russakovsky (10.1016/j.gie.2019.09.034_bib18) 2015; 115 Ishihara (10.1016/j.gie.2019.09.034_bib13) 2010; 23 Esteva (10.1016/j.gie.2019.09.034_bib19) 2017; 542 Society (10.1016/j.gie.2019.09.034_bib23) 2009; 6 Kumagai (10.1016/j.gie.2019.09.034_bib27) 2019; 16
References_xml	– volume: 21 start-page: 653 year: 2018 end-page: 660 ident: bib21 article-title: Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images publication-title: Gastric Cancer – volume: 108 start-page: 544 year: 2013 end-page: 551 ident: bib3 article-title: Long-term outcome and metastatic risk after endoscopic resection of superficial esophageal squamous cell carcinoma publication-title: Am J Gastroenterol – volume: 23 start-page: 480 year: 2010 end-page: 486 ident: bib28 article-title: Prospective evaluation of narrow-band imaging endoscopy for screening of esophageal squamous mucosal high-grade neoplasia in experienced and less experienced endoscopists publication-title: Dis Esophagus – volume: 9 start-page: 568 year: 2004 end-page: 577 ident: bib10 article-title: Appearance of enhanced tissue features in narrow-band endoscopic imaging publication-title: J Biomed Opt – volume: 144 start-page: 1941 year: 2019 end-page: 1953 ident: bib1 article-title: Estimating the global cancer incidence and mortality in 2018: GLOBOCAN sources and methods publication-title: Int J Cancer – volume: 100 start-page: 275 year: 2005 end-page: 282 ident: bib8 article-title: Lugol's dye spray chromoendoscopy establishes early diagnosis of esophageal cancer in patients with primary head and neck cancer publication-title: Am J Gastroenterol – volume: 39 start-page: 779 year: 2007 end-page: 783 ident: bib4 article-title: Clinical outcome after endoscopic mucosal resection for esophageal squamous cell carcinoma invading the muscularis mucosae-a multicenter retrospective cohort study publication-title: Endoscopy – volume: 23 start-page: 480 year: 2010 end-page: 486 ident: bib13 article-title: Prospective evaluation of narrow-band imaging endoscopy for screening of esophageal squamous mucosal high-grade neoplasia in experienced and less experienced endoscopists publication-title: Dis Esophagus – volume: 51 start-page: 333 year: 2019 end-page: 341 ident: bib26 article-title: Computer-assisted diagnosis of early esophageal squamous cell carcinoma using narrow-band imaging magnifying endoscopy publication-title: Endoscopy – volume: 20 start-page: 1089 year: 2001 end-page: 1094 ident: bib6 article-title: Clinicopathologic characteristics and survival of patients with clinical stage I squamous cell carcinomas of the thoracic esophagus treated with three-field lymph node dissection publication-title: Eur J Cardiothorac Surg – volume: 115 start-page: 211 year: 2015 end-page: 252 ident: bib18 article-title: ImageNet large scale visual recognition challenge publication-title: Int J Computer Vision – volume: 106 start-page: 1048 year: 2011 end-page: 1054 ident: bib7 article-title: Comparison between definitive chemoradiotherapy and esophagectomy in patients with clinical stage I esophageal squamous cell carcinoma publication-title: Am J Gastroenterol – volume: 89 start-page: 25 year: 2019 end-page: 32 ident: bib22 article-title: Diagnostic outcomes of esophageal cancer by artificial intelligence using convolutional neural networks publication-title: Gastrointest Endosc – volume: 104 start-page: 2942 year: 2009 end-page: 2948 ident: bib12 article-title: Narrow-band imaging provides reliable screening for esophageal malignancy in patients with head and neck cancers publication-title: Am J Gastroenterol – volume: 48 start-page: 452 year: 2013 end-page: 458 ident: bib25 article-title: Investigation of the freely available easy-to-use software “EZR” for medical statistics publication-title: Bone Marrow Transplant – volume: 28 start-page: 1566 year: 2010 end-page: 1572 ident: bib11 article-title: Early detection of superficial squamous cell carcinoma in the head and neck region and esophagus by narrow band imaging: a multicenter randomized controlled trial publication-title: J Clin Oncol – volume: 123 start-page: 432 year: 1998 end-page: 439 ident: bib2 article-title: Treatment of superficial cancer of the esophagus: a summary of responses to a questionnaire on superficial cancer of the esophagus in Japan publication-title: Surgery – volume: 17 start-page: 54 year: 2017 ident: bib16 article-title: Narrow band imaging versus Lugol chromoendoscopy to diagnose squamous cell carcinoma of the esophagus: a systematic review and meta-analysis publication-title: BMC Cancer – volume: 56 start-page: 387 year: 2002 end-page: 390 ident: bib5 article-title: Long-term outcome after endoscopic mucosal resection in patients with esophageal squamous cell carcinoma invading the muscularis mucosae or deeper publication-title: Gastrointest Endosc – volume: 542 start-page: 115 year: 2017 end-page: 118 ident: bib19 article-title: Dermatologist-level classification of skin cancer with deep neural networks publication-title: Nature – volume: 83 start-page: 220 year: 1998 end-page: 231 ident: bib9 article-title: Mucosal iodine staining improves endoscopic visualization of squamous dysplasia and squamous cell carcinoma of the esophagus in Linxian, China publication-title: Cancer – volume: 2016 start-page: 6140854 year: 2016 ident: bib15 article-title: Blue laser imaging-bright improves endoscopic recognition of superficial esophageal squamous cell carcinoma publication-title: Gastroenterol Res Pract – volume: 6 start-page: 1 year: 2009 end-page: 25 ident: bib23 article-title: Japanese classification of esophageal cancer, tenth edition: part I publication-title: Esophagus – volume: 2 start-page: E212 year: 2014 end-page: E219 ident: bib14 article-title: Effect of novel bright image enhanced endoscopy using blue laser imaging (BLI) publication-title: Endosc Int Open – volume: 16 start-page: 180 year: 2019 end-page: 187 ident: bib27 article-title: Diagnosis using deep-learning artificial intelligence based on the endocytoscopic observation of the esophagus publication-title: Esophagus – volume: 109 start-page: 845 year: 2014 end-page: 854 ident: bib17 article-title: Usefulness of non-magnifying narrow-band imaging in screening of early esophageal squamous cell carcinoma: a prospective comparative study using propensity score matching publication-title: Am J Gastroenterol – volume: 316 start-page: 2402 year: 2016 end-page: 2410 ident: bib20 article-title: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs publication-title: JAMA – volume: 33 start-page: 159 year: 1977 end-page: 174 ident: bib24 article-title: The measurement of observer agreement for categorical data publication-title: Biometrics – volume: 100 start-page: 275 year: 2005 ident: 10.1016/j.gie.2019.09.034_bib8 article-title: Lugol's dye spray chromoendoscopy establishes early diagnosis of esophageal cancer in patients with primary head and neck cancer publication-title: Am J Gastroenterol doi: 10.1111/j.1572-0241.2005.30189.x – volume: 17 start-page: 54 year: 2017 ident: 10.1016/j.gie.2019.09.034_bib16 article-title: Narrow band imaging versus Lugol chromoendoscopy to diagnose squamous cell carcinoma of the esophagus: a systematic review and meta-analysis publication-title: BMC Cancer doi: 10.1186/s12885-016-3011-9 – volume: 108 start-page: 544 year: 2013 ident: 10.1016/j.gie.2019.09.034_bib3 article-title: Long-term outcome and metastatic risk after endoscopic resection of superficial esophageal squamous cell carcinoma publication-title: Am J Gastroenterol doi: 10.1038/ajg.2013.8 – volume: 6 start-page: 1 year: 2009 ident: 10.1016/j.gie.2019.09.034_bib23 article-title: Japanese classification of esophageal cancer, tenth edition: part I publication-title: Esophagus doi: 10.1007/s10388-009-0169-0 – volume: 39 start-page: 779 year: 2007 ident: 10.1016/j.gie.2019.09.034_bib4 article-title: Clinical outcome after endoscopic mucosal resection for esophageal squamous cell carcinoma invading the muscularis mucosae-a multicenter retrospective cohort study publication-title: Endoscopy doi: 10.1055/s-2007-966761 – volume: 316 start-page: 2402 year: 2016 ident: 10.1016/j.gie.2019.09.034_bib20 article-title: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs publication-title: JAMA doi: 10.1001/jama.2016.17216 – volume: 23 start-page: 480 year: 2010 ident: 10.1016/j.gie.2019.09.034_bib13 article-title: Prospective evaluation of narrow-band imaging endoscopy for screening of esophageal squamous mucosal high-grade neoplasia in experienced and less experienced endoscopists publication-title: Dis Esophagus doi: 10.1111/j.1442-2050.2009.01039.x – volume: 542 start-page: 115 year: 2017 ident: 10.1016/j.gie.2019.09.034_bib19 article-title: Dermatologist-level classification of skin cancer with deep neural networks publication-title: Nature doi: 10.1038/nature21056 – volume: 89 start-page: 25 year: 2019 ident: 10.1016/j.gie.2019.09.034_bib22 article-title: Diagnostic outcomes of esophageal cancer by artificial intelligence using convolutional neural networks publication-title: Gastrointest Endosc doi: 10.1016/j.gie.2018.07.037 – volume: 33 start-page: 159 year: 1977 ident: 10.1016/j.gie.2019.09.034_bib24 article-title: The measurement of observer agreement for categorical data publication-title: Biometrics doi: 10.2307/2529310 – volume: 20 start-page: 1089 year: 2001 ident: 10.1016/j.gie.2019.09.034_bib6 article-title: Clinicopathologic characteristics and survival of patients with clinical stage I squamous cell carcinomas of the thoracic esophagus treated with three-field lymph node dissection publication-title: Eur J Cardiothorac Surg doi: 10.1016/S1010-7940(01)01003-X – volume: 2016 start-page: 6140854 year: 2016 ident: 10.1016/j.gie.2019.09.034_bib15 article-title: Blue laser imaging-bright improves endoscopic recognition of superficial esophageal squamous cell carcinoma publication-title: Gastroenterol Res Pract doi: 10.1155/2016/6140854 – volume: 144 start-page: 1941 year: 2019 ident: 10.1016/j.gie.2019.09.034_bib1 article-title: Estimating the global cancer incidence and mortality in 2018: GLOBOCAN sources and methods publication-title: Int J Cancer doi: 10.1002/ijc.31937 – volume: 16 start-page: 180 year: 2019 ident: 10.1016/j.gie.2019.09.034_bib27 article-title: Diagnosis using deep-learning artificial intelligence based on the endocytoscopic observation of the esophagus publication-title: Esophagus doi: 10.1007/s10388-018-0651-7 – volume: 28 start-page: 1566 year: 2010 ident: 10.1016/j.gie.2019.09.034_bib11 article-title: Early detection of superficial squamous cell carcinoma in the head and neck region and esophagus by narrow band imaging: a multicenter randomized controlled trial publication-title: J Clin Oncol doi: 10.1200/JCO.2009.25.4680 – volume: 21 start-page: 653 year: 2018 ident: 10.1016/j.gie.2019.09.034_bib21 article-title: Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images publication-title: Gastric Cancer doi: 10.1007/s10120-018-0793-2 – volume: 83 start-page: 220 year: 1998 ident: 10.1016/j.gie.2019.09.034_bib9 article-title: Mucosal iodine staining improves endoscopic visualization of squamous dysplasia and squamous cell carcinoma of the esophagus in Linxian, China publication-title: Cancer doi: 10.1002/(SICI)1097-0142(19980715)83:2<220::AID-CNCR4>3.0.CO;2-U – volume: 51 start-page: 333 year: 2019 ident: 10.1016/j.gie.2019.09.034_bib26 article-title: Computer-assisted diagnosis of early esophageal squamous cell carcinoma using narrow-band imaging magnifying endoscopy publication-title: Endoscopy doi: 10.1055/a-0756-8754 – volume: 106 start-page: 1048 year: 2011 ident: 10.1016/j.gie.2019.09.034_bib7 article-title: Comparison between definitive chemoradiotherapy and esophagectomy in patients with clinical stage I esophageal squamous cell carcinoma publication-title: Am J Gastroenterol doi: 10.1038/ajg.2011.42 – volume: 9 start-page: 568 year: 2004 ident: 10.1016/j.gie.2019.09.034_bib10 article-title: Appearance of enhanced tissue features in narrow-band endoscopic imaging publication-title: J Biomed Opt doi: 10.1117/1.1695563 – volume: 109 start-page: 845 year: 2014 ident: 10.1016/j.gie.2019.09.034_bib17 article-title: Usefulness of non-magnifying narrow-band imaging in screening of early esophageal squamous cell carcinoma: a prospective comparative study using propensity score matching publication-title: Am J Gastroenterol doi: 10.1038/ajg.2014.94 – volume: 48 start-page: 452 year: 2013 ident: 10.1016/j.gie.2019.09.034_bib25 article-title: Investigation of the freely available easy-to-use software “EZR” for medical statistics publication-title: Bone Marrow Transplant doi: 10.1038/bmt.2012.244 – volume: 123 start-page: 432 year: 1998 ident: 10.1016/j.gie.2019.09.034_bib2 article-title: Treatment of superficial cancer of the esophagus: a summary of responses to a questionnaire on superficial cancer of the esophagus in Japan publication-title: Surgery doi: 10.1016/S0039-6060(98)70165-5 – volume: 56 start-page: 387 year: 2002 ident: 10.1016/j.gie.2019.09.034_bib5 article-title: Long-term outcome after endoscopic mucosal resection in patients with esophageal squamous cell carcinoma invading the muscularis mucosae or deeper publication-title: Gastrointest Endosc doi: 10.1016/S0016-5107(02)70043-6 – volume: 2 start-page: E212 year: 2014 ident: 10.1016/j.gie.2019.09.034_bib14 article-title: Effect of novel bright image enhanced endoscopy using blue laser imaging (BLI) publication-title: Endosc Int Open doi: 10.1055/s-0034-1390707 – volume: 104 start-page: 2942 year: 2009 ident: 10.1016/j.gie.2019.09.034_bib12 article-title: Narrow-band imaging provides reliable screening for esophageal malignancy in patients with head and neck cancers publication-title: Am J Gastroenterol doi: 10.1038/ajg.2009.426 – volume: 115 start-page: 211 year: 2015 ident: 10.1016/j.gie.2019.09.034_bib18 article-title: ImageNet large scale visual recognition challenge publication-title: Int J Computer Vision doi: 10.1007/s11263-015-0816-y – volume: 23 start-page: 480 year: 2010 ident: 10.1016/j.gie.2019.09.034_bib28 article-title: Prospective evaluation of narrow-band imaging endoscopy for screening of esophageal squamous mucosal high-grade neoplasia in experienced and less experienced endoscopists publication-title: Dis Esophagus doi: 10.1111/j.1442-2050.2009.01039.x
SSID	ssj0008231
Score	2.6142087
Snippet	Diagnosing esophageal squamous cell carcinoma (SCC) depends on individual physician expertise and may be subject to interobserver variability. Therefore, we...
SourceID	proquest pubmed crossref elsevier
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	301
SubjectTerms	Adult Aged Aged, 80 and over Deep Learning Esophageal Diseases - diagnostic imaging Esophageal Diseases - pathology Esophageal Neoplasms - diagnostic imaging Esophageal Neoplasms - pathology Esophageal Squamous Cell Carcinoma - diagnostic imaging Esophageal Squamous Cell Carcinoma - pathology Esophagus - pathology Female Humans Image Processing, Computer-Assisted - methods Male Middle Aged Narrow Band Imaging - methods Neoplasm Invasiveness Neural Networks, Computer Observer Variation Optical Imaging - methods Precancerous Conditions - diagnostic imaging Precancerous Conditions - pathology Reproducibility of Results Sensitivity and Specificity
Title	Endoscopic detection and differentiation of esophageal lesions using a deep neural network
URI	https://www.clinicalkey.com/#!/content/1-s2.0-S0016510719323016 https://dx.doi.org/10.1016/j.gie.2019.09.034 https://www.ncbi.nlm.nih.gov/pubmed/31585124 https://www.proquest.com/docview/2301441425
Volume	91
WOSCitedRecordID	wos000508567300013&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1097-6779 dateEnd: 20200430 omitProxy: false ssIdentifier: ssj0008231 issn: 0016-5107 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLa6DiFeEHfKZTIS4oEpk5M4tfNYoY6Luo6HTqp4iZzY3jq6pLTpWPkJ_GqOYyetBhvjAamKKicniXy-nHPsc0Potc-k1F1KvIDD50Z1GHtpxokXa03jgHVZKqoirgM2HPLxOP7cav2sc2HOpyzP-cVFPPuvrIYxYLZJnf0Hdjc3hQH4D0yHI7AdjjdifD-Xhck1mWS7UpXKtQLPZdMLpZw0ZqIyTQxAogCfpmpRxcQtq80DAbRqtmuqXcK53MaKbxqy78WinBem2ATICGPRKvfYZov-8OSssGnsB2IhVsJ2WLEwPJmYOtEVe1fNcK9YiTOXofZjCRc0Z4biqzgW34VLJCrFvNjcrYClKWkiP6yAJTHzusw2kNlTfxhzUjn2N9AXbIjY0N7uN9FvdyFO944npvqpH9vytXSt52rf_vAw2T8aDJJRfzx6M_vmmQ5kxlPv2rFsoe2ARTFvo-3ex_74U6PXjcO08p27t6195FW04KWnXmXlXLWKqayZ0T101y1DcM_C5z5qqfwBun3gAi0eoi9rFOEGRRhQhC-hCBcar1GEHYpwhSIssEERtijCDkWP0NF-f_Tug-facHgZWIOlpyJC0lSzLOXKD3W3KzQLKeGKch2EioQZZd1IUMqk0imnRFERMZmxSMBqVKfhY9TOi1w9RdhnREk_FFmcwUpZS1AnkqeSq4BpIWTUQaSetiRzNepNq5RpUgcjniYw04mZ6YTAL6Qd9LYhmdkCLdddHNS8SOrMY9CVCWDoOiLaEDmz1JqbfyN7VTM7AZFt_HAiV8VykQR2GwO0ZQc9sShoXj30jZ8-oM9uQP0c3Vl_Yi9Qu5wv1Ut0KzsvJ4v5DtpiY77jQPwL1TLFmw
linkProvider	Elsevier
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=Endoscopic+detection+and+differentiation+of+esophageal+lesions+using+a+deep+neural+network&rft.jtitle=Gastrointestinal+endoscopy&rft.au=Ohmori%2C+Masayasu&rft.au=Ishihara%2C+Ryu&rft.au=Aoyama%2C+Kazuharu&rft.au=Nakagawa%2C+Kentaro&rft.date=2020-02-01&rft.issn=1097-6779&rft.eissn=1097-6779&rft.volume=91&rft.issue=2&rft.spage=301&rft_id=info:doi/10.1016%2Fj.gie.2019.09.034&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0016-5107&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0016-5107&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0016-5107&client=summon