Show simple item record

dc.contributor.authorKeprate, Arvind
dc.date.accessioned2022-03-22T11:58:22Z
dc.date.available2022-03-22T11:58:22Z
dc.date.created2022-01-24T17:01:46Z
dc.date.issued2021-11-01
dc.identifier.issn2703-9196
dc.identifier.urihttps://hdl.handle.net/11250/2986788
dc.description.abstractThis paper aims to describe the methodology used to develop, fine-tune and analyze a UNet model for creating masks for two datasets: Polyp Segmentation and Instrument Segmentation, which are part of MedAI challenge. For training and validation, we have used the same methodology on both tasks and finally on the hidden testing dataset the model resulted in an accuracy of 0.9721, dice score of 0.7980 for the instrumentation task, and the accuracy of 0.5646 and a dice score of 0.4100 was achieved for the Polyp Segmentation.en_US
dc.language.isoengen_US
dc.publisherUniversitetet i Osloen_US
dc.relation.ispartofseriesNordic Machine Intelligence (NMI);Vol. 1 No. 1 (2021): MedAI: Transparency in Medical Image Segmentation
dc.rightsNavngivelse 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/deed.no*
dc.subjectUNeten_US
dc.subjectSegmentationen_US
dc.subjectDeep learningen_US
dc.subjectPolypsen_US
dc.subjectInstrumentationen_US
dc.titleKvasir-Instruments and Polyp Segmentation Using UNeten_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionpublishedVersionen_US
dc.rights.holderCopyright (c) 2021 Nordic Machine Intelligenceen_US
cristin.ispublishedtrue
cristin.fulltextoriginal
dc.identifier.doihttps://doi.org/10.5617/nmi.9130
dc.identifier.cristin1988896
dc.source.journalNordic Machine Intelligence (NMI)en_US
dc.source.volume1en_US
dc.source.issue1en_US
dc.source.pagenumber26-28en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Navngivelse 4.0 Internasjonal
Except where otherwise noted, this item's license is described as Navngivelse 4.0 Internasjonal