File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: DoFE: Domain-Oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets

TitleDoFE: Domain-Oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets
Authors
Keywordsoptic cup segmentation
vessel segmentation
Optic disc segmentation
domain generalization
feature embedding
Issue Date2020
Citation
IEEE Transactions on Medical Imaging, 2020, v. 39, n. 12, p. 4237-4248 How to Cite?
AbstractDeep convolutional neural networks have significantly boosted the performance of fundus image segmentation when test datasets have the same distribution as the training datasets. However, in clinical practice, medical images often exhibit variations in appearance for various reasons, e.g., different scanner vendors and image quality. These distribution discrepancies could lead the deep networks to over-fit on the training datasets and lack generalization ability on the unseen test datasets. To alleviate this issue, we present a novel Domain-oriented Feature Embedding (DoFE) framework to improve the generalization ability of CNNs on unseen target domains by exploring the knowledge from multiple source domains. Our DoFE framework dynamically enriches the image features with additional domain prior knowledge learned from multi-source domains to make the semantic features more discriminative. Specifically, we introduce a Domain Knowledge Pool to learn and memorize the prior information extracted from multi-source domains. Then the original image features are augmented with domain-oriented aggregated features, which are induced from the knowledge pool based on the similarity between the input image and multi-source domain images. We further design a novel domain code prediction branch to infer this similarity and employ an attention-guided mechanism to dynamically combine the aggregated features with the semantic features. We comprehensively evaluate our DoFE framework on two fundus image segmentation tasks, including the optic cup and disc segmentation and vessel segmentation. Our DoFE framework generates satisfying segmentation results on unseen datasets and surpasses other domain generalization and network regularization methods.
Persistent Identifierhttp://hdl.handle.net/10722/299480
ISSN
2023 Impact Factor: 8.9
2023 SCImago Journal Rankings: 3.703
ISI Accession Number ID

 

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.accessioned2021-05-21T03:34:30Z-
dc.date.available2021-05-21T03:34:30Z-
dc.date.issued2020-
dc.identifier.citationIEEE Transactions on Medical Imaging, 2020, v. 39, n. 12, p. 4237-4248-
dc.identifier.issn0278-0062-
dc.identifier.urihttp://hdl.handle.net/10722/299480-
dc.description.abstractDeep convolutional neural networks have significantly boosted the performance of fundus image segmentation when test datasets have the same distribution as the training datasets. However, in clinical practice, medical images often exhibit variations in appearance for various reasons, e.g., different scanner vendors and image quality. These distribution discrepancies could lead the deep networks to over-fit on the training datasets and lack generalization ability on the unseen test datasets. To alleviate this issue, we present a novel Domain-oriented Feature Embedding (DoFE) framework to improve the generalization ability of CNNs on unseen target domains by exploring the knowledge from multiple source domains. Our DoFE framework dynamically enriches the image features with additional domain prior knowledge learned from multi-source domains to make the semantic features more discriminative. Specifically, we introduce a Domain Knowledge Pool to learn and memorize the prior information extracted from multi-source domains. Then the original image features are augmented with domain-oriented aggregated features, which are induced from the knowledge pool based on the similarity between the input image and multi-source domain images. We further design a novel domain code prediction branch to infer this similarity and employ an attention-guided mechanism to dynamically combine the aggregated features with the semantic features. We comprehensively evaluate our DoFE framework on two fundus image segmentation tasks, including the optic cup and disc segmentation and vessel segmentation. Our DoFE framework generates satisfying segmentation results on unseen datasets and surpasses other domain generalization and network regularization methods.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Medical Imaging-
dc.subjectoptic cup segmentation-
dc.subjectvessel segmentation-
dc.subjectOptic disc segmentation-
dc.subjectdomain generalization-
dc.subjectfeature embedding-
dc.titleDoFE: Domain-Oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TMI.2020.3015224-
dc.identifier.pmid32776876-
dc.identifier.scopuseid_2-s2.0-85097003916-
dc.identifier.volume39-
dc.identifier.issue12-
dc.identifier.spage4237-
dc.identifier.epage4248-
dc.identifier.eissn1558-254X-
dc.identifier.isiWOS:000595547500042-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats