Show simple item record

dc.contributor.authorWang, J
dc.contributor.authorZhao, Y
dc.contributor.authorQian, L
dc.contributor.authorYu, X
dc.contributor.authorGao, Y
dc.date.accessioned2022-03-01T05:41:53Z
dc.date.available2022-03-01T05:41:53Z
dc.date.issued2021
dc.identifier.isbn9781665417099
dc.identifier.doi10.1109/DICTA52665.2021.9647299
dc.identifier.urihttp://hdl.handle.net/10072/412785
dc.description.abstractThe precise detection of blood vessels in retinal images is crucial to the early diagnosis of the retinal vascular diseases, e.g., diabetic, hypertensive and solar retinopathies. Existing works often fail in predicting the abnormal areas, e.g, sudden brighter and darker areas and are inclined to predict a pixel to background due to the significant class imbalance, leading to high accuracy and specificity while low sensitivity. To that end, we propose a novel error attention refining network (ERA-Net) that is capable of learning and predicting the potential false predictions in a two-stage manner for effective retinal vessel segmentation. The proposed ERA-Net in the refine stage drives the model to focus on and refine the segmentation errors produced in the initial training stage. To achieve this, unlike most previous attention approaches that run in an unsupervised manner, we introduce a novel error attention mechanism which considers the differences between the ground truth and the initial segmentation masks as the ground truth to supervise the attention map learning. Experimental results demonstrate that our method achieves state-of-the-art performance on two common retinal blood vessel datasets. Code is available at this link.
dc.description.peerreviewedYes
dc.description.sponsorshipGriffith University
dc.languageEnglish
dc.publisherIEEE
dc.publisher.placePiscataway, NJ
dc.relation.ispartofconferencename2021 Digital Image Computing: Techniques and Applications (DICTA)
dc.relation.ispartofconferencetitleDICTA 2021 - 2021 International Conference on Digital Image Computing: Techniques and Applications
dc.relation.ispartofdatefrom2021-11-29
dc.relation.ispartofdateto2021-12-01
dc.relation.ispartoflocationGold Coast, Australia
dc.subject.fieldofresearchBiomedical engineering
dc.subject.fieldofresearchcode4003
dc.titleEAR-NET: Error Attention Refining Network for Retinal Vessel Segmentation
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationWang, J; Zhao, Y; Qian, L; Yu, X; Gao, Y, EAR-NET: Error Attention Refining Network for Retinal Vessel Segmentation, DICTA 2021 - 2021 International Conference on Digital Image Computing: Techniques and Applications, 2021
dc.date.updated2022-02-28T23:26:14Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© 2021 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.
gro.hasfulltextFull Text
gro.griffith.authorGao, Yongsheng


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record