Please use this identifier to cite or link to this item: http://hdl.handle.net/1893/30446
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAli, Abder-Rahmanen_UK
dc.contributor.authorLi, Jingpengen_UK
dc.contributor.authorO'Shea, Sally Janeen_UK
dc.contributor.authorYang, Guangen_UK
dc.contributor.authorTrappenberg, Thomasen_UK
dc.contributor.authorYe, Xujiongen_UK
dc.date.accessioned2019-11-08T01:04:34Z-
dc.date.available2019-11-08T01:04:34Z-
dc.date.issued2019-09-30en_UK
dc.identifier.urihttp://hdl.handle.net/1893/30446-
dc.description.abstractLesion border detection is considered a crucial step in diagnosing skin cancer. However, performing such a task automatically is challenging due to the low contrast between the surrounding skin and lesion, ambiguous lesion borders, and the presence of artifacts such as hair. In this paper we propose a two-stage approach for skin lesion border detection: (i) segmenting the skin lesion dermoscopy image using U-Net, and (ii) extracting the edges from the segmented image using a novel approach we call FuzzEdge. The proposed approach is compared with another published skin lesion border detection approach, and the results show that our approach performs better in detecting the main borders of the lesion and is more robust to artifacts that might be present in the image. The approach is also compared with the manual border drawings of a dermatologist, resulting in an average Dice similarity of 87.7%.en_UK
dc.language.isoenen_UK
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_UK
dc.relationAli A, Li J, O'Shea SJ, Yang G, Trappenberg T & Ye X (2019) A Deep Learning Based Approach to Skin Lesion Border Extraction with a Novel Edge Detector in Dermoscopy Images. In: Proceedings of the 2019 International Joint Conference on Neural Networks, IJCNN 2019. International Joint Conference on Neural Networks (IJCNN 2019), Budapest, Hungary, 14.07.2019-19.07.2019. Piscataway, NJ, USA: Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/IJCNN.2019.8852134en_UK
dc.rights© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en_UK
dc.titleA Deep Learning Based Approach to Skin Lesion Border Extraction with a Novel Edge Detector in Dermoscopy Imagesen_UK
dc.typeConference Paperen_UK
dc.identifier.doi10.1109/IJCNN.2019.8852134en_UK
dc.citation.issn2161-4407en_UK
dc.citation.publicationstatusPublisheden_UK
dc.type.statusAM - Accepted Manuscripten_UK
dc.citation.btitleProceedings of the 2019 International Joint Conference on Neural Networks, IJCNN 2019en_UK
dc.citation.conferencedates2019-07-14 - 2019-07-19en_UK
dc.citation.conferencelocationBudapest, Hungaryen_UK
dc.citation.conferencenameInternational Joint Conference on Neural Networks (IJCNN 2019)en_UK
dc.citation.date30/09/2019en_UK
dc.citation.isbn978-1-7281-1986-1en_UK
dc.citation.isbn978-1-7281-1985-4en_UK
dc.publisher.addressPiscataway, NJ, USAen_UK
dc.contributor.affiliationComputing Scienceen_UK
dc.contributor.affiliationComputing Scienceen_UK
dc.contributor.affiliationMater Private Hospitalen_UK
dc.contributor.affiliationImperial College Londonen_UK
dc.contributor.affiliationDalhousie Universityen_UK
dc.identifier.scopusid2-s2.0-85073215269en_UK
dc.identifier.wtid1477471en_UK
dc.contributor.orcid0000-0002-5450-5472en_UK
dc.contributor.orcid0000-0002-6758-0084en_UK
dc.date.accepted2019-03-08en_UK
dc.description.refREF Eligible with Permitted Exceptionen_UK
dc.date.filedepositdate2019-11-07en_UK
Appears in Collections:Computing Science and Mathematics Conference Papers and Proceedings

Files in This Item:
File Description SizeFormat 
IJCNN paper.pdfFulltext - Accepted Version271.91 kBAdobe PDFView/Open


This item is protected by original copyright



Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

If you believe that any material held in STORRE infringes copyright, please contact library@stir.ac.uk providing details and we will remove the Work from public display in STORRE and investigate your claim.