Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226502176> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4226502176 endingPage "102447" @default.
- W4226502176 startingPage "102447" @default.
- W4226502176 abstract "Due to the difficulty in accessing a large amount of labeled data, semi-supervised learning is becoming an attractive solution in medical image segmentation. To make use of unlabeled data, current popular semi-supervised methods (e.g., temporal ensembling, mean teacher) mainly impose data-level and model-level consistency on unlabeled data. In this paper, we argue that in addition to these strategies, we could further utilize auxiliary tasks and consider task-level consistency to better excavate effective representations from unlabeled data for segmentation. Specifically, we introduce two auxiliary tasks, i.e., a foreground and background reconstruction task for capturing semantic information and a signed distance field (SDF) prediction task for imposing shape constraint, and explore the mutual promotion effect between the two auxiliary and the segmentation tasks based on mean teacher architecture. Moreover, to handle the potential bias of the teacher model caused by annotation scarcity, we develop a tripled-uncertainty guided framework to encourage the three tasks in the student model to learn more reliable knowledge from the teacher. When calculating uncertainty, we propose an uncertainty weighted integration (UWI) strategy for yielding the segmentation predictions of the teacher. In addition, following the advance of unsupervised learning in leveraging the unlabeled data, we also incorporate a contrastive learning based constraint to help the encoders extract more distinct representations to promote the medical image segmentation performance. Extensive experiments on the public 2017 ACDC dataset and the PROMISE12 dataset have demonstrated the effectiveness of our method." @default.
- W4226502176 created "2022-05-05" @default.
- W4226502176 creator A5003642180 @default.
- W4226502176 creator A5009301235 @default.
- W4226502176 creator A5021875517 @default.
- W4226502176 creator A5030763508 @default.
- W4226502176 creator A5041675502 @default.
- W4226502176 creator A5072543841 @default.
- W4226502176 creator A5089126739 @default.
- W4226502176 date "2022-07-01" @default.
- W4226502176 modified "2023-10-17" @default.
- W4226502176 title "Semi-supervised medical image segmentation via a tripled-uncertainty guided mean teacher model with contrastive learning" @default.
- W4226502176 cites W2106033751 @default.
- W4226502176 cites W2789588857 @default.
- W4226502176 cites W2804047627 @default.
- W4226502176 cites W2888570268 @default.
- W4226502176 cites W2903356598 @default.
- W4226502176 cites W2968254841 @default.
- W4226502176 cites W3005650525 @default.
- W4226502176 cites W3006300626 @default.
- W4226502176 cites W3008646806 @default.
- W4226502176 cites W3083779147 @default.
- W4226502176 cites W3092624683 @default.
- W4226502176 cites W3093116876 @default.
- W4226502176 cites W3133858468 @default.
- W4226502176 cites W3163478524 @default.
- W4226502176 cites W4205457781 @default.
- W4226502176 cites W4212775495 @default.
- W4226502176 doi "https://doi.org/10.1016/j.media.2022.102447" @default.
- W4226502176 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35509136" @default.
- W4226502176 hasPublicationYear "2022" @default.
- W4226502176 type Work @default.
- W4226502176 citedByCount "43" @default.
- W4226502176 countsByYear W42265021762022 @default.
- W4226502176 countsByYear W42265021762023 @default.
- W4226502176 crossrefType "journal-article" @default.
- W4226502176 hasAuthorship W4226502176A5003642180 @default.
- W4226502176 hasAuthorship W4226502176A5009301235 @default.
- W4226502176 hasAuthorship W4226502176A5021875517 @default.
- W4226502176 hasAuthorship W4226502176A5030763508 @default.
- W4226502176 hasAuthorship W4226502176A5041675502 @default.
- W4226502176 hasAuthorship W4226502176A5072543841 @default.
- W4226502176 hasAuthorship W4226502176A5089126739 @default.
- W4226502176 hasConcept C119857082 @default.
- W4226502176 hasConcept C153180895 @default.
- W4226502176 hasConcept C154945302 @default.
- W4226502176 hasConcept C162324750 @default.
- W4226502176 hasConcept C187736073 @default.
- W4226502176 hasConcept C2524010 @default.
- W4226502176 hasConcept C2776036281 @default.
- W4226502176 hasConcept C2776436953 @default.
- W4226502176 hasConcept C2780451532 @default.
- W4226502176 hasConcept C33923547 @default.
- W4226502176 hasConcept C41008148 @default.
- W4226502176 hasConcept C58973888 @default.
- W4226502176 hasConcept C89600930 @default.
- W4226502176 hasConceptScore W4226502176C119857082 @default.
- W4226502176 hasConceptScore W4226502176C153180895 @default.
- W4226502176 hasConceptScore W4226502176C154945302 @default.
- W4226502176 hasConceptScore W4226502176C162324750 @default.
- W4226502176 hasConceptScore W4226502176C187736073 @default.
- W4226502176 hasConceptScore W4226502176C2524010 @default.
- W4226502176 hasConceptScore W4226502176C2776036281 @default.
- W4226502176 hasConceptScore W4226502176C2776436953 @default.
- W4226502176 hasConceptScore W4226502176C2780451532 @default.
- W4226502176 hasConceptScore W4226502176C33923547 @default.
- W4226502176 hasConceptScore W4226502176C41008148 @default.
- W4226502176 hasConceptScore W4226502176C58973888 @default.
- W4226502176 hasConceptScore W4226502176C89600930 @default.
- W4226502176 hasFunder F4320321001 @default.
- W4226502176 hasFunder F4320333335 @default.
- W4226502176 hasLocation W42265021761 @default.
- W4226502176 hasLocation W42265021762 @default.
- W4226502176 hasOpenAccess W4226502176 @default.
- W4226502176 hasPrimaryLocation W42265021761 @default.
- W4226502176 hasRelatedWork W1510768092 @default.
- W4226502176 hasRelatedWork W1603736412 @default.
- W4226502176 hasRelatedWork W2061685118 @default.
- W4226502176 hasRelatedWork W2230808081 @default.
- W4226502176 hasRelatedWork W2462100143 @default.
- W4226502176 hasRelatedWork W2807251790 @default.
- W4226502176 hasRelatedWork W3006282800 @default.
- W4226502176 hasRelatedWork W4304185162 @default.
- W4226502176 hasRelatedWork W4379231730 @default.
- W4226502176 hasRelatedWork W2611003898 @default.
- W4226502176 hasVolume "79" @default.
- W4226502176 isParatext "false" @default.
- W4226502176 isRetracted "false" @default.
- W4226502176 workType "article" @default.