FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380677447> ?p ?o ?g. }

• W4380677447 endingPage "3294" @default.
• W4380677447 startingPage "3294" @default.
• W4380677447 abstract "Deep learning has been successfully applied to OCT segmentation. However, for data from different manufacturers and imaging protocols, and for different regions of interest (ROIs), it requires laborious and time-consuming data annotation and training, which is undesirable in many scenarios, such as surgical navigation and multi-center clinical trials. Here we propose an annotation-efficient learning method for OCT segmentation that could significantly reduce annotation costs. Leveraging self-supervised generative learning, we train a Transformer-based model to learn the OCT imagery. Then we connect the trained Transformer-based encoder to a CNN-based decoder, to learn the dense pixel-wise prediction in OCT segmentation. These training phases use open-access data and thus incur no annotation costs, and the pre-trained model can be adapted to different data and ROIs without re-training. Based on the greedy approximation for the k-center problem, we also introduce an algorithm for the selective annotation of the target data. We verified our method on publicly-available and private OCT datasets. Compared to the widely-used U-Net model with 100% training data, our method only requires ∼10% of the data for achieving the same segmentation accuracy, and it speeds the training up to ∼3.5 times. Furthermore, our proposed method outperforms other potential strategies that could improve annotation efficiency. We think this emphasis on learning efficiency may help improve the intelligence and application penetration of OCT-based technologies." @default.
• W4380677447 created "2023-06-15" @default.
• W4380677447 creator A5028427087 @default.
• W4380677447 creator A5050873947 @default.
• W4380677447 creator A5051880074 @default.
• W4380677447 creator A5090520343 @default.
• W4380677447 creator A5092169928 @default.
• W4380677447 date "2023-06-13" @default.
• W4380677447 modified "2023-10-06" @default.
• W4380677447 title "Annotation-efficient learning for OCT segmentation" @default.
• W4380677447 cites W1979102712 @default.
• W4380677447 cites W1993836555 @default.
• W4380677447 cites W2001080026 @default.
• W4380677447 cites W2011237852 @default.
• W4380677447 cites W2028082337 @default.
• W4380677447 cites W2033875770 @default.
• W4380677447 cites W2138157582 @default.
• W4380677447 cites W2165733437 @default.
• W4380677447 cites W2295043053 @default.
• W4380677447 cites W2418802570 @default.
• W4380677447 cites W2589435368 @default.
• W4380677447 cites W2608854843 @default.
• W4380677447 cites W2741520251 @default.
• W4380677447 cites W2788633781 @default.
• W4380677447 cites W2902502253 @default.
• W4380677447 cites W2908621325 @default.
• W4380677447 cites W2917393555 @default.
• W4380677447 cites W2919070891 @default.
• W4380677447 cites W2944774584 @default.
• W4380677447 cites W2964121744 @default.
• W4380677447 cites W2966312603 @default.
• W4380677447 cites W2997598994 @default.
• W4380677447 cites W3006962589 @default.
• W4380677447 cites W3034942609 @default.
• W4380677447 cites W3036782889 @default.
• W4380677447 cites W3084852986 @default.
• W4380677447 cites W3111741353 @default.
• W4380677447 cites W3142822462 @default.
• W4380677447 cites W3173151551 @default.
• W4380677447 cites W3177824328 @default.
• W4380677447 cites W3193917738 @default.
• W4380677447 cites W4206706211 @default.
• W4380677447 cites W4213328656 @default.
• W4380677447 cites W4282935002 @default.
• W4380677447 cites W4291023040 @default.
• W4380677447 cites W4310466409 @default.
• W4380677447 doi "https://doi.org/10.1364/boe.486276" @default.
• W4380677447 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37497504" @default.
• W4380677447 hasPublicationYear "2023" @default.
• W4380677447 type Work @default.
• W4380677447 citedByCount "1" @default.
• W4380677447 countsByYear W43806774472023 @default.
• W4380677447 crossrefType "journal-article" @default.
• W4380677447 hasAuthorship W4380677447A5028427087 @default.
• W4380677447 hasAuthorship W4380677447A5050873947 @default.
• W4380677447 hasAuthorship W4380677447A5051880074 @default.
• W4380677447 hasAuthorship W4380677447A5090520343 @default.
• W4380677447 hasAuthorship W4380677447A5092169928 @default.
• W4380677447 hasBestOaLocation W43806774471 @default.
• W4380677447 hasConcept C108583219 @default.
• W4380677447 hasConcept C111919701 @default.
• W4380677447 hasConcept C118505674 @default.
• W4380677447 hasConcept C119857082 @default.
• W4380677447 hasConcept C121332964 @default.
• W4380677447 hasConcept C124504099 @default.
• W4380677447 hasConcept C154945302 @default.
• W4380677447 hasConcept C165801399 @default.
• W4380677447 hasConcept C2776321320 @default.
• W4380677447 hasConcept C41008148 @default.
• W4380677447 hasConcept C62520636 @default.
• W4380677447 hasConcept C66322947 @default.
• W4380677447 hasConcept C89600930 @default.
• W4380677447 hasConceptScore W4380677447C108583219 @default.
• W4380677447 hasConceptScore W4380677447C111919701 @default.
• W4380677447 hasConceptScore W4380677447C118505674 @default.
• W4380677447 hasConceptScore W4380677447C119857082 @default.
• W4380677447 hasConceptScore W4380677447C121332964 @default.
• W4380677447 hasConceptScore W4380677447C124504099 @default.
• W4380677447 hasConceptScore W4380677447C154945302 @default.
• W4380677447 hasConceptScore W4380677447C165801399 @default.
• W4380677447 hasConceptScore W4380677447C2776321320 @default.
• W4380677447 hasConceptScore W4380677447C41008148 @default.
• W4380677447 hasConceptScore W4380677447C62520636 @default.
• W4380677447 hasConceptScore W4380677447C66322947 @default.
• W4380677447 hasConceptScore W4380677447C89600930 @default.
• W4380677447 hasFunder F4320321001 @default.
• W4380677447 hasIssue "7" @default.
• W4380677447 hasLocation W43806774471 @default.
• W4380677447 hasLocation W43806774472 @default.
• W4380677447 hasLocation W43806774473 @default.
• W4380677447 hasLocation W43806774474 @default.
• W4380677447 hasOpenAccess W4380677447 @default.
• W4380677447 hasPrimaryLocation W43806774471 @default.
• W4380677447 hasRelatedWork W2790662084 @default.
• W4380677447 hasRelatedWork W3014300295 @default.
• W4380677447 hasRelatedWork W4223943233 @default.
• W4380677447 hasRelatedWork W4225161397 @default.
• W4380677447 hasRelatedWork W4285827401 @default.

• next