Show simple item record

dc.contributor.authorJha, Debesh
dc.contributor.authorSmedsrud, Pia
dc.contributor.authorJohansen, Dag
dc.contributor.authorde Lange, Thomas
dc.contributor.authorJohansen, Håvard D.
dc.contributor.authorHalvorsen, Pål
dc.contributor.authorRiegler, Michael Alexander
dc.date.accessioned2021-01-15T14:38:59Z
dc.date.available2021-01-15T14:38:59Z
dc.date.issued2021-01-05
dc.description.abstractColonoscopy is considered the gold standard for detection of colorectal cancer and its precursors. Existing examination methods are, however, hampered by high overall miss-rate, and many abnormalities are left undetected. Computer-Aided Diagnosis systems based on advanced machine learning algorithms are touted as a game-changer that can identify regions in the colon overlooked by the physicians during endoscopic examinations, and help detect and characterize lesions. In previous work, we have proposed the ResUNet++ architecture and demonstrated that it produces more efficient results compared with its counterparts U-Net and ResUNet. In this paper, we demonstrate that further improvements to the overall prediction performance of the ResUNet++ architecture can be achieved by using CRF and TTA. We have performed extensive evaluations and validated the improvements using six publicly available datasets: Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, ETIS-Larib Polyp DB, ASU-Mayo Clinic Colonoscopy Video Database, and CVC-VideoClinicDB. Moreover, we compare our proposed architecture and resulting model with other State-of-the-art methods. To explore the generalization capability of ResUNet++ on different publicly available polyp datasets, so that it could be used in a real-world setting, we performed an extensive cross-dataset evaluation. The experimental results show that applying CRF and TTA improves the performance on various polyp segmentation datasets both on the same dataset and cross-dataset. To check the model's performance on difficult to detect polyps, we selected, with the help of an expert gastroenterologist, 196 sessile or flat polyps that are less than ten millimeters in size. This additional data has been made available as a subset of Kvasir-SEG. Our approaches showed good results for flat or sessile and smaller polyps, which are known to be one of the major reasons for high polyp miss-rates. This is one of the significant strengths of our work and indicates that our methods should be investigated further for use in clinical practice.en_US
dc.identifier.citationJha, Smedsrud, Johansen, de Lange, Johansen, Halvorsen, Riegler. A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation. IEEE journal of biomedical and health informatics. 2021en_US
dc.identifier.cristinIDFRIDAID 1871151
dc.identifier.doi10.1109/JBHI.2021.3049304
dc.identifier.issn2168-2194
dc.identifier.issn2168-2208
dc.identifier.urihttps://hdl.handle.net/10037/20301
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.relation.ispartofJha, D. (2022). Machine Learning-based Classification, Detection, and Segmentation of Medical Images. (Doctoral thesis). <a href=https://hdl.handle.net/10037/23693>https://hdl.handle.net/10037/23693</a>.
dc.relation.journalIEEE journal of biomedical and health informatics
dc.relation.projectIDinfo:eu-repo/grantAgreement/RCN/IKTPLUSS/263248/Norway/Protecting Shared Data with Privacy Automatons//en_US
dc.relation.projectIDinfo:eu-repo/grantAgreement/RCN/FORINFRA/270053/Norway/Experimental Infrastructure for Exploration of Exascale Computing//en_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2021 The Author(s)en_US
dc.subjectVDP::Medical disciplines: 700::Basic medical, dental and veterinary science disciplines: 710en_US
dc.subjectVDP::Medisinske Fag: 700::Basale medisinske, odontologiske og veterinærmedisinske fag: 710en_US
dc.titleA Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentationen_US
dc.type.versionpublishedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record