A Novel Approach for Increased Convolutional Neural Network Performance in Gastric-Cancer Classification Using Endoscopic Images
Gastric cancer is the third-most-common cause of cancer-related deaths in the world. Fortunately, it can be detected using endoscopy equipment. Computer-aided diagnosis (CADx) systems can help clinicians identify cancer from gastric diseases more accurately. In this paper, we present a CADx system t...
Saved in:
Published in | IEEE access Vol. 9; pp. 51847 - 51854 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Piscataway
IEEE
2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Gastric cancer is the third-most-common cause of cancer-related deaths in the world. Fortunately, it can be detected using endoscopy equipment. Computer-aided diagnosis (CADx) systems can help clinicians identify cancer from gastric diseases more accurately. In this paper, we present a CADx system that distinguishes and classifies gastric cancer from pre-cancerous conditions, such as gastric polyps, gastric ulcers, gastritis, and bleeding. The system uses a deep-learning model, Xception, which involves depth-wise separable convolutions, to classify cancer and non-cancers. The proposed method consists of two steps: Google's AutoAugment for augmentation and the simple linear iterative clustering (SLIC) superpixel and fast and robust fuzzy C-means (FRFCM) algorithm for image segmentation during preprocessing. These approaches produce a feasible method of distinguishing and classifying cancers from other gastric diseases. Based on biopsy-supported ground truth, the performance metrics of the area under the receiver operating characteristic curve (i.e. Az) are measured on the test sets. Based on the classification results, the Az of the proposed classification model is 0.96, which is 0.06 up from 0.90 which is the Az of the original data. Our methods are fully automated without the manual specification of region-of-interests for the test and with a random selection of images for model training. This methodology may play a crucial role in selecting effective treatment options without the need for a surgical biopsy. |
---|---|
AbstractList | Gastric cancer is the third-most-common cause of cancer-related deaths in the world. Fortunately, it can be detected using endoscopy equipment. Computer-aided diagnosis (CADx) systems can help clinicians identify cancer from gastric diseases more accurately. In this paper, we present a CADx system that distinguishes and classifies gastric cancer from pre-cancerous conditions, such as gastric polyps, gastric ulcers, gastritis, and bleeding. The system uses a deep-learning model, Xception, which involves depth-wise separable convolutions, to classify cancer and non-cancers. The proposed method consists of two steps: Google’s AutoAugment for augmentation and the simple linear iterative clustering (SLIC) superpixel and fast and robust fuzzy C-means (FRFCM) algorithm for image segmentation during preprocessing. These approaches produce a feasible method of distinguishing and classifying cancers from other gastric diseases. Based on biopsy-supported ground truth, the performance metrics of the area under the receiver operating characteristic curve (i.e. Az) are measured on the test sets. Based on the classification results, the Az of the proposed classification model is 0.96, which is 0.06 up from 0.90 which is the Az of the original data. Our methods are fully automated without the manual specification of region-of-interests for the test and with a random selection of images for model training. This methodology may play a crucial role in selecting effective treatment options without the need for a surgical biopsy. |
Author | Cho, Hyun-Chong Cho, Hyun Chin Lee, Sin-Ae |
Author_xml | – sequence: 1 givenname: Sin-Ae orcidid: 0000-0002-1467-5530 surname: Lee fullname: Lee, Sin-Ae organization: Interdisciplinary Graduate Program~in BIT Medical Convergence, Kangwon National University, Chuncheon, Republic of Korea – sequence: 2 givenname: Hyun Chin surname: Cho fullname: Cho, Hyun Chin email: hccholuck@gmail.com organization: Department of Internal Medicine, Institute of Health Sciences, Gyeongsang National University School of Medicine and Gyeongsang National University Hospital, Jinju, Republic of Korea – sequence: 3 givenname: Hyun-Chong orcidid: 0000-0003-2122-468X surname: Cho fullname: Cho, Hyun-Chong email: hyuncho@kangwon.ac.kr organization: Interdisciplinary Graduate Program~in BIT Medical Convergence, Kangwon National University, Chuncheon, Republic of Korea |
BookMark | eNpNUU1r3DAUFCWFpml-QS6Cnr3Vhy1Lx8Vs04WQFtKcxbP8vNXWK20lb0pv_enVxiH0Xd5jmJkHM-_JRYgBCbnhbMU5M5_WXbd5eFgJJvhKMmXaun1DLgVXppKNVBf_3e_Idc57VkYXqGkvyd81vY9PONH18ZgiuB90jIlug0sIGQfaxfAUp9PsY4CJ3uMpPa_5d0w_6TdMhX2A4JD6QG8hz8m7qjsDiXYT5OxH7-Cspo_Zhx3dhCFmF4_e0e0Bdpg_kLcjTBmvX_YVefy8-d59qe6-3m679V3laqbnamRgkOMIokbZC6l6rLVslTCj0qCcZA3XQnEQhSI5CuC1qUUPrB9QMS6vyHbxHSLs7TH5A6Q_NoK3z0BMOwtp9m5C27q-7cdR1ICmdrzptZZgej1w1hjTsOL1cfEqkf06YZ7tPp5SCShb0XAhhDFCFpZcWC7FnBOOr185s-fm7NKcPTdnX5orqptF5RHxVWGkNi3T8h9K3ZcX |
CODEN | IAECCG |
CitedBy_id | crossref_primary_10_3389_fonc_2022_1087438 crossref_primary_10_1007_s10812_023_01552_4 crossref_primary_10_3389_fonc_2022_901475 crossref_primary_10_1007_s42452_023_05339_2 crossref_primary_10_1007_s11517_024_03093_0 crossref_primary_10_1080_00051144_2024_2304367 |
Cites_doi | 10.1016/j.gie.2018.11.011 10.5124/jkma.2019.62.8.398 10.1002/mp.13264 10.1016/j.neucom.2018.09.013 10.3322/caac.21492 10.1016/j.gie.2017.11.029 10.1007/s10120-019-00992-2 10.1109/TFUZZ.2018.2796074 10.1109/CVPR.2019.00020 10.1109/TPAMI.2012.120 10.1186/s40537-019-0197-0 10.1109/TMI.2019.2897538 10.4166/kjg.2018.72.5.245 10.3390/s20143903 10.1055/a-0981-6133 10.1055/s-2007-1004217 10.1145/3338472.3338492 10.1109/CVPR.2019.00874 10.5391/JKIIS.2019.29.3.204 10.5370/KIEE.2020.69.7.1033 10.1109/CVPR.2017.195 10.1007/s42835-019-00259-x |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA |
DOI | 10.1109/ACCESS.2021.3069747 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) Online IEEE Xplore CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals |
DatabaseTitle | CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional |
DatabaseTitleList | Materials Research Database |
Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE/IET Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering |
EISSN | 2169-3536 |
EndPage | 51854 |
ExternalDocumentID | oai_doaj_org_article_7cb7bff24ae94c15b883a9b8d1059950 10_1109_ACCESS_2021_3069747 9389708 |
Genre | orig-research |
GrantInformation_xml | – fundername: Korea government (MSIT) grantid: 2017R1E1A1A03070297 funderid: 10.13039/501100003621 – fundername: National Research Foundation of Korea (NRF) funderid: 10.13039/501100003725 – fundername: MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2020-2018-0-01433) supervised by the IITP (Institute for Information and communications Technology Promotion) |
GroupedDBID | 0R~ 4.4 5VS 6IK 97E AAJGR ABVLG ACGFS ADBBV ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IFIPE IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RIG RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D |
ID | FETCH-LOGICAL-c408t-f0a9e1efa24e3b236be4837629f68a6c30518261a2fa231e2a14942ba0bde6013 |
IEDL.DBID | RIE |
ISSN | 2169-3536 |
IngestDate | Thu Sep 05 15:37:29 EDT 2024 Thu Oct 10 19:46:29 EDT 2024 Fri Aug 23 02:46:21 EDT 2024 Wed Jun 26 19:27:13 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c408t-f0a9e1efa24e3b236be4837629f68a6c30518261a2fa231e2a14942ba0bde6013 |
ORCID | 0000-0003-2122-468X 0000-0002-1467-5530 |
OpenAccessLink | https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/document/9389708 |
PQID | 2512229923 |
PQPubID | 4845423 |
PageCount | 8 |
ParticipantIDs | proquest_journals_2512229923 crossref_primary_10_1109_ACCESS_2021_3069747 ieee_primary_9389708 doaj_primary_oai_doaj_org_article_7cb7bff24ae94c15b883a9b8d1059950 |
PublicationCentury | 2000 |
PublicationDate | 20210000 2021-00-00 20210101 2021-01-01 |
PublicationDateYYYYMMDD | 2021-01-01 |
PublicationDate_xml | – year: 2021 text: 20210000 |
PublicationDecade | 2020 |
PublicationPlace | Piscataway |
PublicationPlace_xml | – name: Piscataway |
PublicationTitle | IEEE access |
PublicationTitleAbbrev | Access |
PublicationYear | 2021 |
Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
References | krizhevsky (ref12) 2012 ref13 asperti (ref18) 2017 ref11 ref10 ref2 ref1 ref17 ref16 ref19 kim (ref14) 2018; 67 chowdhary (ref15) 2020; 20 misumi (ref4) 1989; 21 ref24 ref23 ref26 ref25 ref20 ref22 ref21 liu (ref8) 2016 ref27 ref7 ref9 ref3 ref6 ref5 |
References_xml | – ident: ref17 doi: 10.1016/j.gie.2018.11.011 – ident: ref2 doi: 10.5124/jkma.2019.62.8.398 – ident: ref11 doi: 10.1002/mp.13264 – ident: ref19 doi: 10.1016/j.neucom.2018.09.013 – volume: 21 start-page: 159 year: 1989 ident: ref4 article-title: Endoscopic diagnosis of minute, small, and flat early gastric cancers publication-title: Endoscopy contributor: fullname: misumi – ident: ref1 doi: 10.3322/caac.21492 – ident: ref6 doi: 10.1016/j.gie.2017.11.029 – ident: ref9 doi: 10.1007/s10120-019-00992-2 – ident: ref25 doi: 10.1109/TFUZZ.2018.2796074 – start-page: 1097 year: 2012 ident: ref12 article-title: ImageNet classification with deep convolutional neural networks publication-title: Proc Adv Neural Inf Process Syst (NIPS) contributor: fullname: krizhevsky – ident: ref22 doi: 10.1109/CVPR.2019.00020 – ident: ref24 doi: 10.1109/TPAMI.2012.120 – ident: ref23 doi: 10.1186/s40537-019-0197-0 – ident: ref21 doi: 10.1109/TMI.2019.2897538 – ident: ref3 doi: 10.4166/kjg.2018.72.5.245 – volume: 20 start-page: 3903 year: 2020 ident: ref15 article-title: An efficient segmentation and classification system in medical images using intuitionist possibilistic fuzzy C-mean clustering and fuzzy SVM algorithm publication-title: SENSORS doi: 10.3390/s20143903 contributor: fullname: chowdhary – ident: ref10 doi: 10.1055/a-0981-6133 – ident: ref5 doi: 10.1055/s-2007-1004217 – ident: ref7 doi: 10.1145/3338472.3338492 – ident: ref20 doi: 10.1109/CVPR.2019.00874 – ident: ref16 doi: 10.5391/JKIIS.2019.29.3.204 – start-page: 21 year: 2016 ident: ref8 article-title: SSD: Single shot multibox detector publication-title: Proc Eur Conf Comput Vis contributor: fullname: liu – volume: 67 start-page: 928 year: 2018 ident: ref14 article-title: Deep learning based computer-aided diagnosis system for gastric lesion using endoscope publication-title: Trans Korean Inst Elec Eng contributor: fullname: kim – year: 2017 ident: ref18 article-title: The effectiveness of data augmentation for detection of gastrointestinal diseases from endoscopical images publication-title: arXiv 1712 03689 contributor: fullname: asperti – ident: ref27 doi: 10.5370/KIEE.2020.69.7.1033 – ident: ref26 doi: 10.1109/CVPR.2017.195 – ident: ref13 doi: 10.1007/s42835-019-00259-x |
SSID | ssj0000816957 |
Score | 2.3122635 |
Snippet | Gastric cancer is the third-most-common cause of cancer-related deaths in the world. Fortunately, it can be detected using endoscopy equipment. Computer-aided... |
SourceID | doaj proquest crossref ieee |
SourceType | Open Website Aggregation Database Publisher |
StartPage | 51847 |
SubjectTerms | Algorithms Artificial neural networks Augmentation Biopsy Bleeding Cancer Clustering computer-aided diagnosis (CADx) deep learning Endoscopes Gastric cancer Ground truth Image classification Image color analysis Image segmentation Internet Iterative methods Lesions Medical imaging Performance measurement segmentation Training Ulcers |
SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8QwDI4QEwyIpzheysBIoUnTNhmPiueAGEBii5LUlRjoIThu5qdjpwEOMbAwVY2itLEd53PkfGbssFMCPZ7uMuLiylQty0xX-Bq8gaora6XbmG1xU13eq-uH8mGu1BflhA30wIPgTurga991UjkwKojSa10443VLwMCkaF2Uc8FU9MFaVKasE82QyM3JuGlwRhgQSnGMMJlg9I-tKDL2pxIrv_xy3GzOV9lKQol8PPzdGluAfp0tz3EHbrD3Mb-ZzAA7JVZwjvCT43KnLHNoeTPpZ8mscCTi4IiPmPTNb7-vC_DHnl84qt4RsoYaXngslEkpRFFrPGYV8LO-ndAVlsfAr57QCb1usvvzs7vmMkvlFLKgcj3NutwZENA5qaDwsqg8EJ18JU1XaVcFXPkUbAgnsUshQDqMnpT0LvctYNxWbLHFftLDNuMiCHBlizIOQRnZulAUOAZADbX3oR2xo0_J2ueBNcPGaCM3dlCEJUXYpIgROyXpf3UlyuvYgIZgkyHYvwxhxDZId1-DGIRida5HbO9TlzYtz1dLoE7iRiyLnf_49C5boukMJzN7bHH68gb7iFWm_iCa5Qe55eWp priority: 102 providerName: Directory of Open Access Journals |
Title | A Novel Approach for Increased Convolutional Neural Network Performance in Gastric-Cancer Classification Using Endoscopic Images |
URI | https://ieeexplore.ieee.org/document/9389708 https://www.proquest.com/docview/2512229923 https://doaj.org/article/7cb7bff24ae94c15b883a9b8d1059950 |
Volume | 9 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT9wwELYop_bQQmnVLRT50CNZYsdJ7OMSQaFSUQ9F4mb5MZFQ1QTBLoee-tOZcbzb56GnJJZjOfrG4xln5hvG3vdKoMbTfUFcXIVqZV3oBh-DN9D0dat0TNEWl835lfp4XV9vsaNNLgwApOAzmNNt-pcfx7Cio7Jjg7trS5m9T3Qpp1ytzXkKFZAwdZuJhURpjhddh9-ALqAUczSMyXD-bfNJHP25qMpfmjhtL2cv2Kf1xKaokq_z1dLPw_c_OBv_d-Y77Hm2M_liEoxdtgXDS_bsF_bBPfZjwS_HB8BOmVecowHLUWFQnDpE3o3DQxZMHIlYPNIlhY3zzz8TDvjNwD84qv8Rio4a7ngqtUlBSAl3nuIS-OkQR0qCuQn84huqsftX7Ors9Et3XuSCDEVQpV4WfekMCOidVFB5WTUeiJC-kaZvtGsC6g5yV4ST2KUSIB36X0p6V_oI6PlVr9n2MA7whnERBLg6ImYhKCOjC1WFYwC00Hof4owdrZGytxPvhk3-SmnsBKwlYG0GdsZOCM1NVyLNTg2Igs1r0LbBt77vpXJgVBC117pyxutINqapyxnbI-Q2g2TQZuxgLRs2L_B7S2ahxK1cVm___dY-e0oTnE5rDtj28m4F79B-WfrD5PcfJvF9BIAr8Ak |
link.rule.ids | 315,786,790,802,870,2115,4043,27954,27955,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwELaqcgAOvArqQgEfODbb2HEePm6jli20Kw6t1Jvlx0SqEEnV7vbAiZ_OjOPd8jpwSmI5lqPPnocz8w1jHzolUOI1XUZcXJmqZZk1FT56p6Hqylo1IUZbLKr5hfp0WV5usf1NLgwAxOAzmNJt_JcfBr-io7IDjdq1pszeB6jn83rM1tqcqFAJCV3WiVpI5Ppg1rb4FegESjFF05hM59_UT2TpT2VV_pLFUcEcP2Vn66mNcSVfp6ulm_rvf7A2_u_cn7EnydLks3FpPGdb0L9gj3_hH9xhP2Z8MdwBdkrM4hxNWI4igyLVIfB26O_S0sSRiMcjXmLgOP9yn3LAr3r-0VIFEJ-11HDDY7FNCkOKyPMYmcCP-jBQGsyV5yffUJDdvmQXx0fn7TxLJRkyr_JmmXW51SCgs1JB4WRROSBK-krqrmps5VF6kMMirMQuhQBp0QNT0tncBUDfr3jFtvuhh13GhRdgy4CYea-0DNYXBY4BUEPtnA8Ttr9GylyPzBsmeiy5NiOwhoA1CdgJOyQ0N12JNjs2IAom7UJTe1e7rpPKglZelK5pCqtdE8jK1GU-YTuE3GaQBNqE7a3Xhklb_NaQYShRmcvi9b_fes8ezs_PTs3pyeLzG_aIJjue3eyx7eXNCt6iNbN07-Ii_gma4vJo |
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=A+Novel+Approach+for+Increased+Convolutional+Neural+Network+Performance+in+Gastric-Cancer+Classification+Using+Endoscopic+Images&rft.jtitle=IEEE+access&rft.au=Lee%2C+Sin-Ae&rft.au=Cho%2C+Hyun+Chin&rft.au=Cho%2C+Hyun-Chong&rft.date=2021&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=9&rft.spage=51847&rft.epage=51854&rft_id=info:doi/10.1109%2FACCESS.2021.3069747&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2021_3069747 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon |