File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Boundary and entropy-driven adversarial learning for fundus image segmentation

TitleBoundary and entropy-driven adversarial learning for fundus image segmentation
Authors
KeywordsAdversarial learning
Optic disc and cup segmentation
Unsupervised domain adaptation
Fundus images
Issue Date2019
PublisherSpringer.
Citation
22nd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2019), Shenzhen, China, 13-17 October 2019. In Shen, D, Liu, T, Peters, TM, et al. (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part I, p. 102-110. Cham, Switzerland: Springer, 2019 How to Cite?
AbstractAccurate segmentation of the optic disc (OD) and cup (OC) in fundus images from different datasets is critical for glaucoma disease screening. The cross-domain discrepancy (domain shift) hinders the generalization of deep neural networks to work on different domain datasets. In this work, we present an unsupervised domain adaptation framework, called Boundary and Entropy-driven Adversarial Learning (BEAL), to improve the OD and OC segmentation performance, especially on the ambiguous boundary regions. In particular, our proposed BEAL framework utilizes the adversarial learning to encourage the boundary prediction and mask probability entropy map (uncertainty map) of the target domain to be similar to the source ones, generating more accurate boundaries and suppressing the high uncertainty predictions of OD and OC segmentation. We evaluate the proposed BEAL framework on two public retinal fundus image datasets (Drishti-GS and RIM-ONE-r3), and the experiment results demonstrate that our method outperforms the state-of-the-art unsupervised domain adaptation methods. Our code is available at https://github.com/EmmaW8/BEAL.
Persistent Identifierhttp://hdl.handle.net/10722/299610
ISBN
ISSN
2020 SCImago Journal Rankings: 0.249
ISI Accession Number ID
Series/Report no.Lecture Notes in Computer Science ; 11764

 

DC FieldValueLanguage
dc.contributor.authorWang, Shujun-
dc.contributor.authorYu, Lequan-
dc.contributor.authorLi, Kang-
dc.contributor.authorYang, Xin-
dc.contributor.authorFu, Chi Wing-
dc.contributor.authorHeng, Pheng Ann-
dc.date.accessioned2021-05-21T03:34:47Z-
dc.date.available2021-05-21T03:34:47Z-
dc.date.issued2019-
dc.identifier.citation22nd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2019), Shenzhen, China, 13-17 October 2019. In Shen, D, Liu, T, Peters, TM, et al. (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part I, p. 102-110. Cham, Switzerland: Springer, 2019-
dc.identifier.isbn9783030322380-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/299610-
dc.description.abstractAccurate segmentation of the optic disc (OD) and cup (OC) in fundus images from different datasets is critical for glaucoma disease screening. The cross-domain discrepancy (domain shift) hinders the generalization of deep neural networks to work on different domain datasets. In this work, we present an unsupervised domain adaptation framework, called Boundary and Entropy-driven Adversarial Learning (BEAL), to improve the OD and OC segmentation performance, especially on the ambiguous boundary regions. In particular, our proposed BEAL framework utilizes the adversarial learning to encourage the boundary prediction and mask probability entropy map (uncertainty map) of the target domain to be similar to the source ones, generating more accurate boundaries and suppressing the high uncertainty predictions of OD and OC segmentation. We evaluate the proposed BEAL framework on two public retinal fundus image datasets (Drishti-GS and RIM-ONE-r3), and the experiment results demonstrate that our method outperforms the state-of-the-art unsupervised domain adaptation methods. Our code is available at https://github.com/EmmaW8/BEAL.-
dc.languageeng-
dc.publisherSpringer.-
dc.relation.ispartofMedical Image Computing and Computer Assisted Intervention – MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part I-
dc.relation.ispartofseriesLecture Notes in Computer Science ; 11764-
dc.subjectAdversarial learning-
dc.subjectOptic disc and cup segmentation-
dc.subjectUnsupervised domain adaptation-
dc.subjectFundus images-
dc.titleBoundary and entropy-driven adversarial learning for fundus image segmentation-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/978-3-030-32239-7_12-
dc.identifier.scopuseid_2-s2.0-85075632012-
dc.identifier.spage102-
dc.identifier.epage110-
dc.identifier.eissn1611-3349-
dc.identifier.isiWOS:000548734200012-
dc.publisher.placeCham, Switzerland-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats