Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366996414> ?p ?o ?g. }
- W4366996414 endingPage "2960" @default.
- W4366996414 startingPage "2948" @default.
- W4366996414 abstract "Federated learning is an emerging paradigm allowing large-scale decentralized learning without sharing data across different data owners, which helps address the concern of data privacy in medical image analysis. However, the requirement for label consistency across clients by the existing methods largely narrows its application scope. In practice, each clinical site may only annotate certain organs of interest with partial or no overlap with other sites. Incorporating such partially labeled data into a unified federation is an unexplored problem with clinical significance and urgency. This work tackles the challenge by using a novel federated multi-encoding U-Net (Fed-MENU) method for multi-organ segmentation. In our method, a multi-encoding U-Net (MENU-Net) is proposed to extract organ-specific features through different encoding sub-networks. Each sub-network can be seen as an expert of a specific organ and trained for that client. Moreover, to encourage the organ-specific features extracted by different sub-networks to be informative and distinctive, we regularize the training of the MENU-Net by designing an auxiliary generic decoder (AGD). Extensive experiments on six public abdominal CT datasets show that our Fed-MENU method can effectively obtain a federated learning model using the partially labeled datasets with superior performance to other models trained by either localized or centralized learning methods. Source code is publicly available at https://github.com/DIAL-RPI/Fed-MENU." @default.
- W4366996414 created "2023-04-27" @default.
- W4366996414 creator A5000641105 @default.
- W4366996414 creator A5038061910 @default.
- W4366996414 creator A5057836774 @default.
- W4366996414 creator A5065085502 @default.
- W4366996414 date "2023-10-01" @default.
- W4366996414 modified "2023-10-10" @default.
- W4366996414 title "Federated Multi-organ Segmentation with Inconsistent Labels" @default.
- W4366996414 cites W2757528734 @default.
- W4366996414 cites W2962858109 @default.
- W4366996414 cites W2962914239 @default.
- W4366996414 cites W3033511014 @default.
- W4366996414 cites W3035367255 @default.
- W4366996414 cites W3098488418 @default.
- W4366996414 cites W3112701542 @default.
- W4366996414 cites W3117686595 @default.
- W4366996414 cites W3127057363 @default.
- W4366996414 cites W3127107873 @default.
- W4366996414 cites W3128304793 @default.
- W4366996414 cites W3162595961 @default.
- W4366996414 cites W3165750456 @default.
- W4366996414 cites W3169044395 @default.
- W4366996414 cites W3172681723 @default.
- W4366996414 cites W3176031707 @default.
- W4366996414 cites W3189411510 @default.
- W4366996414 cites W3200636593 @default.
- W4366996414 cites W3200840849 @default.
- W4366996414 cites W3201745428 @default.
- W4366996414 cites W4205228770 @default.
- W4366996414 cites W4205307011 @default.
- W4366996414 cites W4206953207 @default.
- W4366996414 cites W4221141759 @default.
- W4366996414 cites W4294106961 @default.
- W4366996414 cites W4306409944 @default.
- W4366996414 cites W4307936170 @default.
- W4366996414 cites W4312464145 @default.
- W4366996414 doi "https://doi.org/10.1109/tmi.2023.3270140" @default.
- W4366996414 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37097793" @default.
- W4366996414 hasPublicationYear "2023" @default.
- W4366996414 type Work @default.
- W4366996414 citedByCount "0" @default.
- W4366996414 crossrefType "journal-article" @default.
- W4366996414 hasAuthorship W4366996414A5000641105 @default.
- W4366996414 hasAuthorship W4366996414A5038061910 @default.
- W4366996414 hasAuthorship W4366996414A5057836774 @default.
- W4366996414 hasAuthorship W4366996414A5065085502 @default.
- W4366996414 hasBestOaLocation W43669964142 @default.
- W4366996414 hasConcept C111919701 @default.
- W4366996414 hasConcept C119857082 @default.
- W4366996414 hasConcept C124101348 @default.
- W4366996414 hasConcept C125411270 @default.
- W4366996414 hasConcept C154945302 @default.
- W4366996414 hasConcept C177264268 @default.
- W4366996414 hasConcept C199360897 @default.
- W4366996414 hasConcept C23123220 @default.
- W4366996414 hasConcept C2776436953 @default.
- W4366996414 hasConcept C2776760102 @default.
- W4366996414 hasConcept C2778012447 @default.
- W4366996414 hasConcept C41008148 @default.
- W4366996414 hasConcept C43126263 @default.
- W4366996414 hasConcept C89600930 @default.
- W4366996414 hasConceptScore W4366996414C111919701 @default.
- W4366996414 hasConceptScore W4366996414C119857082 @default.
- W4366996414 hasConceptScore W4366996414C124101348 @default.
- W4366996414 hasConceptScore W4366996414C125411270 @default.
- W4366996414 hasConceptScore W4366996414C154945302 @default.
- W4366996414 hasConceptScore W4366996414C177264268 @default.
- W4366996414 hasConceptScore W4366996414C199360897 @default.
- W4366996414 hasConceptScore W4366996414C23123220 @default.
- W4366996414 hasConceptScore W4366996414C2776436953 @default.
- W4366996414 hasConceptScore W4366996414C2776760102 @default.
- W4366996414 hasConceptScore W4366996414C2778012447 @default.
- W4366996414 hasConceptScore W4366996414C41008148 @default.
- W4366996414 hasConceptScore W4366996414C43126263 @default.
- W4366996414 hasConceptScore W4366996414C89600930 @default.
- W4366996414 hasFunder F4320306076 @default.
- W4366996414 hasFunder F4320332161 @default.
- W4366996414 hasIssue "10" @default.
- W4366996414 hasLocation W43669964141 @default.
- W4366996414 hasLocation W43669964142 @default.
- W4366996414 hasLocation W43669964143 @default.
- W4366996414 hasLocation W43669964144 @default.
- W4366996414 hasOpenAccess W4366996414 @default.
- W4366996414 hasPrimaryLocation W43669964141 @default.
- W4366996414 hasRelatedWork W1603736412 @default.
- W4366996414 hasRelatedWork W2057738282 @default.
- W4366996414 hasRelatedWork W2060429446 @default.
- W4366996414 hasRelatedWork W2061685118 @default.
- W4366996414 hasRelatedWork W2355022049 @default.
- W4366996414 hasRelatedWork W2462100143 @default.
- W4366996414 hasRelatedWork W3006282800 @default.
- W4366996414 hasRelatedWork W3081644756 @default.
- W4366996414 hasRelatedWork W4304185162 @default.
- W4366996414 hasRelatedWork W4379231730 @default.
- W4366996414 hasVolume "42" @default.
- W4366996414 isParatext "false" @default.
- W4366996414 isRetracted "false" @default.