Impact of Image Resolution on Deep Learning Performance in Endoscopy Image Classification: An Experimental Study Using a Large Dataset of Endoscopic Images

Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in endoscopy. Impressive results are achieved, but many medical studies use a very small image resolution to save computing resources at the cost of...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Diagnostics (Basel) Ročník 11; číslo 12; s. 2183
Hlavní autori:	Thambawita, Vajira, Strümke, Inga, Hicks, Steven A., Halvorsen, Pål, Parasa, Sravanthi, Riegler, Michael A.
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Switzerland MDPI AG 24.11.2021 MDPI
Predmet:	Automation Classification convolutional neural networks Datasets Deep learning endoscopic images Endoscopy Experiments image resolution Neural networks Performance evaluation endoscopic images image resolution convolutional neural networks
ISSN:	2075-4418, 2075-4418
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in endoscopy. Impressive results are achieved, but many medical studies use a very small image resolution to save computing resources at the cost of losing details. Today, no conventions between resolution and performance exist, and monitoring the performance of various CNN architectures as a function of image resolution provides insights into how subtleties of different lesions on endoscopy affect performance. This can help set standards for image or video characteristics for future CNN-based models in gastrointestinal (GI) endoscopy. This study examines the performance of CNNs on the HyperKvasir dataset, consisting of 10,662 images from 23 different findings. We evaluate two CNN models for endoscopic image classification under quality distortions with image resolutions ranging from 32 × 32 to 512 × 512 pixels. The performance is evaluated using two-fold cross-validation and F1-score, maximum Matthews correlation coefficient (MCC), precision, and sensitivity as metrics. Increased performance was observed with higher image resolution for all findings in the dataset. MCC was achieved at image resolutions between 512 × 512 pixels for classification for the entire dataset after including all subclasses. The highest performance was observed with an MCC value of 0.9002 when the models were trained on the highest resolution and tested on the same resolution. Different resolutions and their effect on CNNs are explored. We show that image resolution has a clear influence on the performance which calls for standards in the field in the future.
AbstractList	Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in endoscopy. Impressive results are achieved, but many medical studies use a very small image resolution to save computing resources at the cost of losing details. Today, no conventions between resolution and performance exist, and monitoring the performance of various CNN architectures as a function of image resolution provides insights into how subtleties of different lesions on endoscopy affect performance. This can help set standards for image or video characteristics for future CNN-based models in gastrointestinal (GI) endoscopy. This study examines the performance of CNNs on the HyperKvasir dataset, consisting of 10,662 images from 23 different findings. We evaluate two CNN models for endoscopic image classification under quality distortions with image resolutions ranging from 32 × 32 to 512 × 512 pixels. The performance is evaluated using two-fold cross-validation and F1-score, maximum Matthews correlation coefficient (MCC), precision, and sensitivity as metrics. Increased performance was observed with higher image resolution for all findings in the dataset. MCC was achieved at image resolutions between 512 × 512 pixels for classification for the entire dataset after including all subclasses. The highest performance was observed with an MCC value of 0.9002 when the models were trained on the highest resolution and tested on the same resolution. Different resolutions and their effect on CNNs are explored. We show that image resolution has a clear influence on the performance which calls for standards in the field in the future. Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in endoscopy. Impressive results are achieved, but many medical studies use a very small image resolution to save computing resources at the cost of losing details. Today, no conventions between resolution and performance exist, and monitoring the performance of various CNN architectures as a function of image resolution provides insights into how subtleties of different lesions on endoscopy affect performance. This can help set standards for image or video characteristics for future CNN-based models in gastrointestinal (GI) endoscopy. This study examines the performance of CNNs on the HyperKvasir dataset, consisting of 10,662 images from 23 different findings. We evaluate two CNN models for endoscopic image classification under quality distortions with image resolutions ranging from 32 × 32 to 512 × 512 pixels. The performance is evaluated using two-fold cross-validation and F1-score, maximum Matthews correlation coefficient (MCC), precision, and sensitivity as metrics. Increased performance was observed with higher image resolution for all findings in the dataset. MCC was achieved at image resolutions between 512 × 512 pixels for classification for the entire dataset after including all subclasses. The highest performance was observed with an MCC value of 0.9002 when the models were trained on the highest resolution and tested on the same resolution. Different resolutions and their effect on CNNs are explored. We show that image resolution has a clear influence on the performance which calls for standards in the field in the future.Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in endoscopy. Impressive results are achieved, but many medical studies use a very small image resolution to save computing resources at the cost of losing details. Today, no conventions between resolution and performance exist, and monitoring the performance of various CNN architectures as a function of image resolution provides insights into how subtleties of different lesions on endoscopy affect performance. This can help set standards for image or video characteristics for future CNN-based models in gastrointestinal (GI) endoscopy. This study examines the performance of CNNs on the HyperKvasir dataset, consisting of 10,662 images from 23 different findings. We evaluate two CNN models for endoscopic image classification under quality distortions with image resolutions ranging from 32 × 32 to 512 × 512 pixels. The performance is evaluated using two-fold cross-validation and F1-score, maximum Matthews correlation coefficient (MCC), precision, and sensitivity as metrics. Increased performance was observed with higher image resolution for all findings in the dataset. MCC was achieved at image resolutions between 512 × 512 pixels for classification for the entire dataset after including all subclasses. The highest performance was observed with an MCC value of 0.9002 when the models were trained on the highest resolution and tested on the same resolution. Different resolutions and their effect on CNNs are explored. We show that image resolution has a clear influence on the performance which calls for standards in the field in the future.
Author	Parasa, Sravanthi Riegler, Michael A. Strümke, Inga Thambawita, Vajira Halvorsen, Pål Hicks, Steven A.
AuthorAffiliation	3 Swedish Medical Group, Department of Gastroenterology, Seattle, WA 98104, USA; vaidhya209@gmail.com 2 Faculty of Technology, Art and Design (TKD), Oslo Metropolitan University, 0167 Oslo, Norway 1 Simula Metropolitan Center for Digital Engineering, 0167 Oslo, Norway; inga@simula.no (I.S.); steven@simula.no (S.A.H.); paalh@simula.no (P.H.); michael@simula.no (M.A.R.)
AuthorAffiliation_xml	– name: 2 Faculty of Technology, Art and Design (TKD), Oslo Metropolitan University, 0167 Oslo, Norway – name: 1 Simula Metropolitan Center for Digital Engineering, 0167 Oslo, Norway; inga@simula.no (I.S.); steven@simula.no (S.A.H.); paalh@simula.no (P.H.); michael@simula.no (M.A.R.) – name: 3 Swedish Medical Group, Department of Gastroenterology, Seattle, WA 98104, USA; vaidhya209@gmail.com
Author_xml	– sequence: 1 givenname: Vajira orcidid: 0000-0001-6026-0929 surname: Thambawita fullname: Thambawita, Vajira – sequence: 2 givenname: Inga orcidid: 0000-0003-1820-6544 surname: Strümke fullname: Strümke, Inga – sequence: 3 givenname: Steven A. surname: Hicks fullname: Hicks, Steven A. – sequence: 4 givenname: Pål orcidid: 0000-0003-2073-7029 surname: Halvorsen fullname: Halvorsen, Pål – sequence: 5 givenname: Sravanthi surname: Parasa fullname: Parasa, Sravanthi – sequence: 6 givenname: Michael A. surname: Riegler fullname: Riegler, Michael A.
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/34943421$$D View this record in MEDLINE/PubMed
BookMark	eNp9kl1rFDEUhgep2Lr2FwgS8Mab1XxNZuKFULZVFxYUtdfhTJJZs8wkYzIj7m_xz5r9kraIISQhed8nJyfnaXHmg7dF8Zzg14xJ_MY4WPuQRqcTIYRSUrNHxQXFVTnnnNRnd9bnxWVKG5ybJKym5ZPinHHJGafkovi97AfQIwotWvawtuiLTaGbRhc8yv3a2gGtLETv_Bp9trENsQevLXIe3XgTkg7D9mhddJCSa52Gnf0tusqSX4ONrrd-hA59HSezRbdphwK0gpg91zBCsvv7TzinD7z0rHjcQpfs5XGeFbfvb74tPs5Xnz4sF1eruS5FOc5Fw7ghTSuJ0FKWmMiyaUVTMcyNrcCypsSYGVkxKYRscE6WAMONBgKWamCzYnngmgAbNeR4IW5VAKf2GyGuFcSc6c4qKg0QQ0RjWsJrbhpaC91gDC0tS57vmhXvDqxhanprdH55hO4e9P6Jd9_VOvxUdYUx5SIDXh0BMfyYbBpV75K2XQfehikpKgineairLH35QLoJU_Q5VTsVrcq65jvVi7sR_Q3lVANZIA8CHUNK0bZKu3H_hTlA1ymC1a7k1D9KLnvZA-8J_z_XHwyQ330
CitedBy_id	crossref_primary_10_1002_ps_8464 crossref_primary_10_1371_journal_pone_0297536 crossref_primary_10_1109_ACCESS_2024_3443638 crossref_primary_10_1109_ACCESS_2025_3583688 crossref_primary_10_3390_technologies12110231 crossref_primary_10_1016_j_cpcardiol_2023_102129 crossref_primary_10_5230_jgc_2025_25_e39 crossref_primary_10_1016_j_bspc_2023_105118 crossref_primary_10_1109_TGRS_2022_3209340 crossref_primary_10_1016_j_ecoinf_2023_102361 crossref_primary_10_7717_peerj_14939 crossref_primary_10_1016_j_media_2024_103224 crossref_primary_10_3390_rs14143299 crossref_primary_10_1016_j_heliyon_2024_e38920 crossref_primary_10_1145_3579831 crossref_primary_10_3389_fphy_2025_1582245 crossref_primary_10_1088_1742_6596_2402_1_012009 crossref_primary_10_3390_s23063176 crossref_primary_10_3390_bios15010019 crossref_primary_10_1007_s10596_023_10227_0 crossref_primary_10_1007_s13721_023_00412_7 crossref_primary_10_1109_JBHI_2022_3225416 crossref_primary_10_1016_j_gie_2022_08_043 crossref_primary_10_1016_j_knosys_2024_112213 crossref_primary_10_1016_j_rse_2024_114122 crossref_primary_10_1002_alr_23525 crossref_primary_10_1016_j_gie_2022_10_016 crossref_primary_10_3390_diagnostics13040747 crossref_primary_10_1016_j_foohum_2024_100378 crossref_primary_10_1016_j_iswa_2025_200505 crossref_primary_10_1080_15481603_2023_2287291 crossref_primary_10_3390_s23177635 crossref_primary_10_1109_ACCESS_2025_3530297 crossref_primary_10_1177_26317745241306562 crossref_primary_10_1186_s41984_023_00213_0 crossref_primary_10_1016_j_crmeth_2023_100500 crossref_primary_10_1371_journal_pone_0309740 crossref_primary_10_1016_j_atech_2025_101405 crossref_primary_10_3389_fonc_2024_1379624 crossref_primary_10_3390_rs17132179 crossref_primary_10_1038_s41598_024_72237_x crossref_primary_10_1016_j_compag_2023_108465 crossref_primary_10_34133_plantphenomics_0278 crossref_primary_10_1038_s41598_025_14408_y crossref_primary_10_1016_j_rsase_2024_101333 crossref_primary_10_1007_s00167_023_07338_7 crossref_primary_10_1097_RTI_0000000000000833 crossref_primary_10_3390_bdcc7010051 crossref_primary_10_1080_10400419_2024_2339667 crossref_primary_10_1016_j_gassur_2025_102195 crossref_primary_10_1186_s40494_023_01094_0 crossref_primary_10_1038_s41598_024_82904_8 crossref_primary_10_1109_ACCESS_2024_3469155 crossref_primary_10_1021_acssensors_5c01433 crossref_primary_10_3390_rs16152786 crossref_primary_10_1016_j_isci_2024_110822 crossref_primary_10_1049_cim2_70039
Cites_doi	10.1038/s41598-017-02606-2 10.1145/3386295 10.1109/CBMS.2016.63 10.1038/s41597-020-00622-y 10.1109/TIP.2005.859378 10.1136/gutjnl-2019-319914 10.1038/s41551-018-0301-3 10.1371/journal.pone.0177678 10.1109/CVPR.2017.243 10.1016/j.neucom.2015.09.116 10.1016/j.ipm.2009.03.002 10.1109/TMI.2016.2528162 10.1109/72.298224 10.1109/CVPR.2009.5206848 10.1148/ryai.2019190015 10.1109/CVPR.2016.90
ContentType	Journal Article
Copyright	2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2021 by the authors. 2021
Copyright_xml	– notice: 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2021 by the authors. 2021
DBID	AAYXX CITATION NPM 3V. 7XB 8FK 8G5 ABUWG AFKRA AZQEC BENPR CCPQU DWQXO GNUQQ GUQSH M2O MBDVC PHGZM PHGZT PIMPY PKEHL PQEST PQQKQ PQUKI PRINS Q9U 7X8 5PM DOA
DOI	10.3390/diagnostics11122183
DatabaseName	CrossRef PubMed ProQuest Central (Corporate) ProQuest Central (purchase pre-March 2016) ProQuest Central (Alumni) (purchase pre-March 2016) Research Library (Alumni Edition) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One Community College ProQuest Central ProQuest Central Student Research Library Prep Proquest Research Library Research Library (Corporate) ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef PubMed Publicly Available Content Database Research Library Prep ProQuest Central Student ProQuest One Academic Middle East (New) ProQuest Central Basic ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) ProQuest One Community College Research Library (Alumni Edition) ProQuest Central China ProQuest Central ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Research Library ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic Publicly Available Content Database CrossRef PubMed
Database_xml	– sequence: 1 dbid: DOA name: Directory of Open Access Journals (DOAJ) url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Medicine
EISSN	2075-4418
ExternalDocumentID	oai_doaj_org_article_29da1d16bdf1484db286cb00af2554ae PMC8700246 34943421 10_3390_diagnostics11122183
Genre	Journal Article
GroupedDBID	53G 5VS 8G5 AADQD AAFWJ AAYXX ABDBF ABUWG ACUHS ADBBV AFFHD AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS AOIJS AZQEC BCNDV BENPR BPHCQ CCPQU CITATION DWQXO EBD ESX GNUQQ GROUPED_DOAJ GUQSH HYE IAO IHR ITC KQ8 M2O M48 MODMG M~E OK1 PGMZT PHGZM PHGZT PIMPY PQQKQ PROAC RPM 3V. NPM 7XB 8FK MBDVC PKEHL PQEST PQUKI PRINS Q9U 7X8 5PM
ID	FETCH-LOGICAL-c565t-6b34d1bf916c9950195bf6b7304de7ae3b5003d9739669b02216ad4dca1ae2ca3
IEDL.DBID	PIMPY
ISICitedReferencesCount	71
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000736817700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2075-4418
IngestDate	Fri Oct 03 12:29:30 EDT 2025 Tue Nov 04 01:43:44 EST 2025 Sun Nov 09 11:06:30 EST 2025 Sun Nov 30 05:28:26 EST 2025 Thu Jan 02 22:56:02 EST 2025 Tue Nov 18 21:59:36 EST 2025 Sat Nov 29 07:18:05 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	12
Keywords	endoscopic images image resolution convolutional neural networks
Language	English
License	Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c565t-6b34d1bf916c9950195bf6b7304de7ae3b5003d9739669b02216ad4dca1ae2ca3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Consultant Covidien LP; Medical advisory board-Fujifilm. Board member of Augere Medical.
ORCID	0000-0003-1820-6544 0000-0003-2073-7029 0000-0001-6026-0929
OpenAccessLink	https://www.proquest.com/publiccontent/docview/2612758847?pq-origsite=%requestingapplication%
PMID	34943421
PQID	2612758847
PQPubID	2032410
ParticipantIDs	doaj_primary_oai_doaj_org_article_29da1d16bdf1484db286cb00af2554ae pubmedcentral_primary_oai_pubmedcentral_nih_gov_8700246 proquest_miscellaneous_2614226187 proquest_journals_2612758847 pubmed_primary_34943421 crossref_citationtrail_10_3390_diagnostics11122183 crossref_primary_10_3390_diagnostics11122183
PublicationCentury	2000
PublicationDate	20211124
PublicationDateYYYYMMDD	2021-11-24
PublicationDate_xml	– month: 11 year: 2021 text: 20211124 day: 24
PublicationDecade	2020
PublicationPlace	Switzerland
PublicationPlace_xml	– name: Switzerland – name: Basel
PublicationTitle	Diagnostics (Basel)
PublicationTitleAlternate	Diagnostics (Basel)
PublicationYear	2021
Publisher	MDPI AG MDPI
Publisher_xml	– name: MDPI AG – name: MDPI
References	Hassan (ref_1) 2020; 69 ref_13 ref_12 ref_11 ref_10 Shin (ref_5) 2016; 35 Battiti (ref_8) 1994; 5 Thambawita (ref_16) 2020; 1 Wang (ref_3) 2018; 2 ref_17 Borgli (ref_9) 2020; 7 Boughorbel (ref_15) 2017; 12 Sokolova (ref_14) 2009; 45 Sheikh (ref_6) 2006; 15 Guo (ref_4) 2016; 187 Sabottke (ref_7) 2020; 2 Mossotto (ref_2) 2017; 7
References_xml	– volume: 7 start-page: 2427 year: 2017 ident: ref_2 article-title: Classification of paediatric inflammatory bowel disease using machine learning publication-title: Sci. Rep. doi: 10.1038/s41598-017-02606-2 – volume: 1 start-page: 1 year: 2020 ident: ref_16 article-title: An extensive study on cross-dataset bias and evaluation metrics interpretation for machine learning applied to gastrointestinal tract abnormality classification publication-title: ACM Trans. Comput. Healthc. doi: 10.1145/3386295 – ident: ref_17 doi: 10.1109/CBMS.2016.63 – volume: 7 start-page: 283 year: 2020 ident: ref_9 article-title: HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy publication-title: Sci. Data doi: 10.1038/s41597-020-00622-y – volume: 15 start-page: 430 year: 2006 ident: ref_6 article-title: Image information and visual quality publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2005.859378 – volume: 69 start-page: 799 year: 2020 ident: ref_1 article-title: New artificial intelligence system: First validation study versus experienced endoscopists for colorectal polyp detection publication-title: Gut doi: 10.1136/gutjnl-2019-319914 – volume: 2 start-page: 741 year: 2018 ident: ref_3 article-title: Development and validation of a deeplearning algorithm for the detection of polyps during colonoscopy publication-title: Nat. Biomed. Eng. doi: 10.1038/s41551-018-0301-3 – volume: 12 start-page: e0177678 year: 2017 ident: ref_15 article-title: Optimal classifier for imbalanced data using matthews correlation coefficient metric publication-title: PLoS ONE doi: 10.1371/journal.pone.0177678 – ident: ref_11 doi: 10.1109/CVPR.2017.243 – ident: ref_12 – volume: 187 start-page: 27 year: 2016 ident: ref_4 article-title: Deep learning for visual understanding: A review publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.09.116 – volume: 45 start-page: 427 year: 2009 ident: ref_14 article-title: A systematic analysis of performance measures for classification tasks publication-title: Inf. Process. Manag. doi: 10.1016/j.ipm.2009.03.002 – volume: 35 start-page: 1285 year: 2016 ident: ref_5 article-title: Deep convolutional neural networks for computer-aided detection: Cnn architectures, dataset characteristics and transfer learning publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2016.2528162 – volume: 5 start-page: 537 year: 1994 ident: ref_8 article-title: Using mutual information for selecting features in supervised neural net learning publication-title: IEEE Trans. Neural Netw. doi: 10.1109/72.298224 – ident: ref_13 doi: 10.1109/CVPR.2009.5206848 – volume: 2 start-page: e190015 year: 2020 ident: ref_7 article-title: The effect of image resolution on deep learning in radiography publication-title: Radiol. Artif. Intell. doi: 10.1148/ryai.2019190015 – ident: ref_10 doi: 10.1109/CVPR.2016.90
SSID	ssj0000913825
Score	2.5072927
Snippet	Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in...
SourceID	doaj pubmedcentral proquest pubmed crossref
SourceType	Open Website Open Access Repository Aggregation Database Index Database Enrichment Source
StartPage	2183
SubjectTerms	Automation Classification convolutional neural networks Datasets Deep learning endoscopic images Endoscopy Experiments image resolution Neural networks Performance evaluation
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9NAEB6hqkJcEJSXoVSLxBGr3V3b6-XW0latVKoeQOrNmn0YIoFTNSlSfwt_lpldJySoggtSTvHY2WRe32ZnvgF4S0nBedNi2WB0ZaX2evK5Opa-1Q69jKhxLw2bMOfn7eWlvVgZ9cU1YZkeOP9wu8oGlEE2LvSE3KvgVNvwVHnsCQxXGDn6EupZ2UylGGyZW6_ONEOa9vW7IVeuMfcxubdiZLCWihJj_10w889qyZX0c_wIHo64Uezn9T6Ge3HYgvsfx5PxJ_DzNLU7imkvTr9TjBD8v3y2KkGvwxivxMil-kVc_O4WEJNBHA1hyt0pt-OtaVAmlxAlrb0X-ySyMghAcO3hrUjFBgLFGdeSi0OcUz5Mn7943MTn582ewufjo08fTspx8ELpCd_Ny8bpKkjXE3T01tbcU-j6xlEwqEI0GLWrKRgEazRtlqwjGCAbDFXwKDEqj_oZbAzTIb4AwRnSBhVMsOkEz2Ewuja9cbG3bcQC1EIHnR9ZyXk4xreOdiesuO4OxRXwbnnTVSbl-Lv4ASt3KcqM2ukNsrNutLPuX3ZWwPbCNLrRzWcd868ZbvU1BbxZXiYH5VMXHOL0Jslwt7JsSeZ5tqTlSpgbSFdKFmDWbGxtqetXhsnXRAJOcZbgVfPyf3y3V_BAcamOlKWqtmFjfn0TX8Om_zGfzK53kmf9AvBILnA priority: 102 providerName: Directory of Open Access Journals
Title	Impact of Image Resolution on Deep Learning Performance in Endoscopy Image Classification: An Experimental Study Using a Large Dataset of Endoscopic Images
URI	https://www.ncbi.nlm.nih.gov/pubmed/34943421 https://www.proquest.com/docview/2612758847 https://www.proquest.com/docview/2614226187 https://pubmed.ncbi.nlm.nih.gov/PMC8700246 https://doaj.org/article/29da1d16bdf1484db286cb00af2554ae
Volume	11
WOSCitedRecordID	wos000736817700001&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: PRVAON databaseName: Directory of Open Access Journals (DOAJ) customDbUrl: eissn: 2075-4418 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913825 issn: 2075-4418 databaseCode: DOA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2075-4418 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913825 issn: 2075-4418 databaseCode: M~E dateStart: 20110101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: ProQuest Central - New (Subscription) customDbUrl: eissn: 2075-4418 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913825 issn: 2075-4418 databaseCode: BENPR dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2075-4418 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913825 issn: 2075-4418 databaseCode: PIMPY dateStart: 20110101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: Research Library (subscription) customDbUrl: eissn: 2075-4418 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913825 issn: 2075-4418 databaseCode: M2O dateStart: 20110101 isFulltext: true titleUrlDefault: https://search.proquest.com/pqrl providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nb9NAEB3RBCEufBcMJVokjlip147X5oJamopIJFgIpHCy9sslEtghSZH6W_izzKw3boOqnpCiHOKxs1Hevp3ZnXkD8BoXBaVFJsNUWhUm_LDCOTeyoc5iJXVkZSwPXbMJMZtl83le-PLotU-r3HKiI-pW7ZnytpGEh6bRtGM-JOErQTWW4t3yV0g9pOis1TfU2IM-CW9lPegXk2nxrdtzIQ1MjIha8aEYo_2hafPZSBEZJz0nf2FngXI6_tc5n__mUF5ZlE7v_9-f8wDueeeUHbVoegi3bP0I7kz98ftj-DNxNZWsqdjkJxIRo83_FroMXyfWLpkXbD1jxWVJAlvUbFybhkpgLvytrhsn5Sk5aLxlR2hypdsAowTHC-YyGphkHylhnZ3IDS667vu3j1vo9nnrJ_D1dPzl_YfQd3cINTqRmzBVcWIiVaF_qvN8RIWLqkoVMk5irJA2ViNkHJOLGCOyXKGvEaXSJEbLSFquZbwPvbqp7TNgtAznhhthcndMqKQR8UhUQtkqz6wMgG__0lJ76XPqwPGjxBCIcFBeg4MA3nQ3LVvlj5vNjwkrnSnJdrsPmtVZ6Vmg5LmRkYlSZSoMQxOjeJZqJD5ZYWSXSBvAwRYtpeeSdXkJjgBedZeRBehoR9a2OXc2VBIdZWjztAVmNxISIIoTHgUgdiC7M9TdK_Xiu1MaRzJHHy59fvOwXsBdTpk-URTy5AB6m9W5fQm39e_NYr0awJ6YZwPoH49nxeeB2_PA9yn_NPDT8y_RsE1E
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB6VFAEX3g9DgUWCG1bjteO1kRAqpFWjJlEORSond18ukcAOSQrKb-E_8BuZWT_aoKq3HpByiseblfPNyzvzDcBrdApKi0T6sbTKj3g3R53rWV8noZI6sDKUXTdsQozHydFROtmAP00vDJVVNjbRGWpTanpHvk1UV4K6KsWH2Q-fpkbR6WozQqOCxYFd_cKUbfF-0Mf_9w3ne7uHn_b9eqqArzF4WfqxCiMTqBzjIp2mPWqYU3msEOmRsULaUPUQ6SYVIWYCqUIfF8TSREbLQFquZYjrXoPNCMGedGBzMhhNvrRvdYhlE3Ouit4oDNPutqkq5ohzGc0Kp4hkzQW6SQEXhbf_Vmmec3t7d_63B3YXbtcBNtupNOIebNjiPtwY1SUED-D3wPWFsjJng-9oTBkdYFTqx_DTt3bGatLZEzY5a6tg04LtFqakNp5VfaubKEq1Vg7e79gOipybmMCoSHPFXFUGk2xIRfesL5cYOLjfb5ab6mq9xUP4fCWP5hF0irKwT4BRKJEaboRJ3VGnkkaEPZELZfM0sdID3oAm0zV9O00R-ZZhGkdIyy5Amgdv25tmFXvJ5eIfCY2tKFGPuy_K-UlWW7KMp0YGJoiVyTGVjoziSazReMscs9NIWg-2GjxmtT1cZGdg9OBVexktGR1PycKWp06G2rqDBGUeV9Bvd0IkSmHEAw_EmlKsbXX9SjH96tjS0SFhHBo_vXxbL-Hm_uFomA0H44NncItT5VIQ-Dzags5yfmqfw3X9czldzF_UKs_g-KqV5i-jHpno
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB6VFFVceD8MBRYJbliJ147XRkKokEZEbSMfQCond18ukVo7JCkov4V_wq9jZm2nDap66wEpp3i8WTnfvLzfzAC8RqegtEikH0ur_Ij3CtS5vvV1EiqpAytD2XPDJsR4nBweptkG_GlrYYhW2dpEZ6hNpekdeZdaXQmqqhTdoqFFZIPhh-kPnyZI0UlrO06jhsieXf7C9G3-fjTA__oN58PdL58--82EAV9jILPwYxVGJlAFxkg6TftUPKeKWCHqI2OFtKHqI-pNKkLMClKF_i6IpYmMloG0XMsQ170BmxiSR1EHNrPRQfZt9YaHOm5i_lW3OgrDtNc1NXuO-i-jieEUnay5Qzc14LJQ91_G5gUXOLzzPz-8u3C7CbzZTq0p92DDlvdh66ChFjyA3yNXL8qqgo1O0cgyOtio1ZLhZ2DtlDXNaI9Zdl5uwSYl2y1NReU9y-ZWN2mUOFgO9u_YDopcmKTAiLy5ZI6twSTbJzI-G8gFBhTu99vlJrpeb_4Qvl7Lo3kEnbIq7RNgFGKkhhthUncEqqQRYV8UQtkiTaz0gLcAynXT1p2mi5zkmN4R6vJLUOfB29VN07qrydXiHwmZK1FqSe6-qGbHeWPhcp4aGZggVqbAFDsyiiexRqMuC8xaI2k92G6xmTd2cp6fA9ODV6vLaOHo2EqWtjpzMlTuHSQo87hWg9VOqLlSGPHAA7GmIGtbXb9STr67LuroqDA-jZ9eva2XsIWaku-PxnvP4BYnQlMQ-Dzahs5idmafw039czGZz1402s_g6Lp15i9t5KKp
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=Impact+of+Image+Resolution+on+Deep+Learning+Performance+in+Endoscopy+Image+Classification%3A+An+Experimental+Study+Using+a+Large+Dataset+of+Endoscopic+Images&rft.jtitle=Diagnostics+%28Basel%29&rft.au=Thambawita%2C+Vajira&rft.au=Str%C3%BCmke%2C+Inga&rft.au=Hicks%2C+Steven+A&rft.au=Halvorsen%2C+P%C3%A5l&rft.date=2021-11-24&rft.pub=MDPI+AG&rft.eissn=2075-4418&rft.volume=11&rft.issue=12&rft.spage=2183&rft_id=info:doi/10.3390%2Fdiagnostics11122183&rft.externalDBID=HAS_PDF_LINK
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2075-4418&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2075-4418&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2075-4418&client=summon