File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ISBI48211.2021.9433866
- Scopus: eid_2-s2.0-85107221882
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Memory-assisted dual-end adaptation network for choroid segmentation in multi-domain optical coherence tomography
Title | Memory-assisted dual-end adaptation network for choroid segmentation in multi-domain optical coherence tomography |
---|---|
Authors | |
Keywords | Choroid segmentation Multiple target domains Unsupervised domain adaptation |
Issue Date | 2021 |
Citation | Proceedings - International Symposium on Biomedical Imaging, 2021, v. 2021-April, p. 1614-1617 How to Cite? |
Abstract | Accurate measurement of choroid layer in optical coherence tomography (OCT) is crucial in the diagnosis of many ocular diseases, such as pathological myopia and glaucoma. Deep learning has shown its superiority in automatic choroid segmentation. However, because of the domain discrepancies among datasets obtained by the OCT devices of different manufacturers, the generalization capability of trained models is limited. We propose a memory-assisted dual-end adaptation network to address the universality problem. Different from the existing works that can only perform one-to-one domain adaptation, our method is capable of performing one-to-many adaptation. In the proposed method, we introduce a memory module to memorize the encoded style features of every involved domain. Both input and output space adaptation are employed to regularize the choroid segmentation. We evaluate the proposed method over different datasets acquired by four major OCT manufacturers (TOPCON, NIDEK, ZEISS, HEIDELBERG). Experiments show that our proposed method outperforms existing methods with significant margins of improvement in terms of all metrics. |
Persistent Identifier | http://hdl.handle.net/10722/345130 |
ISSN | 2020 SCImago Journal Rankings: 0.601 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chai, Zhenjie | - |
dc.contributor.author | Yang, Jianlong | - |
dc.contributor.author | Zhou, Kang | - |
dc.contributor.author | Chen, Zhi | - |
dc.contributor.author | Zhao, Yitian | - |
dc.contributor.author | Gao, Shenghua | - |
dc.contributor.author | Liu, Jiang | - |
dc.date.accessioned | 2024-08-15T09:25:26Z | - |
dc.date.available | 2024-08-15T09:25:26Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Proceedings - International Symposium on Biomedical Imaging, 2021, v. 2021-April, p. 1614-1617 | - |
dc.identifier.issn | 1945-7928 | - |
dc.identifier.uri | http://hdl.handle.net/10722/345130 | - |
dc.description.abstract | Accurate measurement of choroid layer in optical coherence tomography (OCT) is crucial in the diagnosis of many ocular diseases, such as pathological myopia and glaucoma. Deep learning has shown its superiority in automatic choroid segmentation. However, because of the domain discrepancies among datasets obtained by the OCT devices of different manufacturers, the generalization capability of trained models is limited. We propose a memory-assisted dual-end adaptation network to address the universality problem. Different from the existing works that can only perform one-to-one domain adaptation, our method is capable of performing one-to-many adaptation. In the proposed method, we introduce a memory module to memorize the encoded style features of every involved domain. Both input and output space adaptation are employed to regularize the choroid segmentation. We evaluate the proposed method over different datasets acquired by four major OCT manufacturers (TOPCON, NIDEK, ZEISS, HEIDELBERG). Experiments show that our proposed method outperforms existing methods with significant margins of improvement in terms of all metrics. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings - International Symposium on Biomedical Imaging | - |
dc.subject | Choroid segmentation | - |
dc.subject | Multiple target domains | - |
dc.subject | Unsupervised domain adaptation | - |
dc.title | Memory-assisted dual-end adaptation network for choroid segmentation in multi-domain optical coherence tomography | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ISBI48211.2021.9433866 | - |
dc.identifier.scopus | eid_2-s2.0-85107221882 | - |
dc.identifier.volume | 2021-April | - |
dc.identifier.spage | 1614 | - |
dc.identifier.epage | 1617 | - |
dc.identifier.eissn | 1945-8452 | - |