Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382655345> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4382655345 endingPage "102884" @default.
- W4382655345 startingPage "102884" @default.
- W4382655345 abstract "Deep neural networks (DNNs) have been widely applied in the medical image community, contributing to automatic ophthalmic screening systems for some common diseases. However, the incidence of fundus diseases patterns exhibits a typical long-tailed distribution. In clinic, a small number of common fundus diseases have sufficient observed cases for large-scale analysis while most of the fundus diseases are infrequent. For these rare diseases with extremely low-data regimes, it is challenging to train DNNs to realize automatic diagnosis. In this work, we develop an automatic diagnosis system for rare fundus diseases, based on the meta-learning framework. The system incorporates a co-regularization loss and the ensemble-learning strategy into the meta-learning framework, fully leveraging the advantage of multi-scale hierarchical feature embedding. We initially conduct comparative experiments on our newly-constructed lightweight multi-disease fundus images dataset for the few-shot recognition task (namely, FundusData-FS). Moreover, we verify the cross-domain transferability from miniImageNet to FundusData-FS, and further confirm our method’s good repeatability. Rigorous experiments demonstrate that our method can detect rare fundus diseases, and is superior to the state-of-the-art methods. These investigations demonstrate that the potential of our method for the real clinical practice is promising." @default.
- W4382655345 created "2023-07-01" @default.
- W4382655345 creator A5001143650 @default.
- W4382655345 creator A5018389659 @default.
- W4382655345 creator A5021681759 @default.
- W4382655345 creator A5060475920 @default.
- W4382655345 creator A5065821874 @default.
- W4382655345 creator A5076745341 @default.
- W4382655345 creator A5082320568 @default.
- W4382655345 date "2023-10-01" @default.
- W4382655345 modified "2023-10-15" @default.
- W4382655345 title "Discriminative ensemble meta-learning with co-regularization for rare fundus diseases diagnosis" @default.
- W4382655345 cites W1983393113 @default.
- W4382655345 cites W2123215356 @default.
- W4382655345 cites W2222577885 @default.
- W4382655345 cites W2557738935 @default.
- W4382655345 cites W2788633781 @default.
- W4382655345 cites W2899951262 @default.
- W4382655345 cites W2912072952 @default.
- W4382655345 cites W2938600289 @default.
- W4382655345 cites W2952436003 @default.
- W4382655345 cites W3003770199 @default.
- W4382655345 cites W3034942609 @default.
- W4382655345 cites W3100236889 @default.
- W4382655345 cites W3128220181 @default.
- W4382655345 cites W3134475970 @default.
- W4382655345 cites W3175581533 @default.
- W4382655345 cites W3191934798 @default.
- W4382655345 cites W4205750574 @default.
- W4382655345 cites W4206250312 @default.
- W4382655345 cites W4306728644 @default.
- W4382655345 doi "https://doi.org/10.1016/j.media.2023.102884" @default.
- W4382655345 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37459674" @default.
- W4382655345 hasPublicationYear "2023" @default.
- W4382655345 type Work @default.
- W4382655345 citedByCount "0" @default.
- W4382655345 crossrefType "journal-article" @default.
- W4382655345 hasAuthorship W4382655345A5001143650 @default.
- W4382655345 hasAuthorship W4382655345A5018389659 @default.
- W4382655345 hasAuthorship W4382655345A5021681759 @default.
- W4382655345 hasAuthorship W4382655345A5060475920 @default.
- W4382655345 hasAuthorship W4382655345A5065821874 @default.
- W4382655345 hasAuthorship W4382655345A5076745341 @default.
- W4382655345 hasAuthorship W4382655345A5082320568 @default.
- W4382655345 hasConcept C108583219 @default.
- W4382655345 hasConcept C118487528 @default.
- W4382655345 hasConcept C119857082 @default.
- W4382655345 hasConcept C153180895 @default.
- W4382655345 hasConcept C154945302 @default.
- W4382655345 hasConcept C2776135515 @default.
- W4382655345 hasConcept C2776391266 @default.
- W4382655345 hasConcept C41008148 @default.
- W4382655345 hasConcept C71924100 @default.
- W4382655345 hasConcept C97931131 @default.
- W4382655345 hasConceptScore W4382655345C108583219 @default.
- W4382655345 hasConceptScore W4382655345C118487528 @default.
- W4382655345 hasConceptScore W4382655345C119857082 @default.
- W4382655345 hasConceptScore W4382655345C153180895 @default.
- W4382655345 hasConceptScore W4382655345C154945302 @default.
- W4382655345 hasConceptScore W4382655345C2776135515 @default.
- W4382655345 hasConceptScore W4382655345C2776391266 @default.
- W4382655345 hasConceptScore W4382655345C41008148 @default.
- W4382655345 hasConceptScore W4382655345C71924100 @default.
- W4382655345 hasConceptScore W4382655345C97931131 @default.
- W4382655345 hasFunder F4320322919 @default.
- W4382655345 hasFunder F4320324787 @default.
- W4382655345 hasFunder F4320326705 @default.
- W4382655345 hasLocation W43826553451 @default.
- W4382655345 hasLocation W43826553452 @default.
- W4382655345 hasOpenAccess W4382655345 @default.
- W4382655345 hasPrimaryLocation W43826553451 @default.
- W4382655345 hasRelatedWork W1482209366 @default.
- W4382655345 hasRelatedWork W2110523656 @default.
- W4382655345 hasRelatedWork W2153315159 @default.
- W4382655345 hasRelatedWork W2521627374 @default.
- W4382655345 hasRelatedWork W259157601 @default.
- W4382655345 hasRelatedWork W2761785940 @default.
- W4382655345 hasRelatedWork W2965546495 @default.
- W4382655345 hasRelatedWork W3103844505 @default.
- W4382655345 hasRelatedWork W4205463238 @default.
- W4382655345 hasRelatedWork W4380075502 @default.
- W4382655345 hasVolume "89" @default.
- W4382655345 isParatext "false" @default.
- W4382655345 isRetracted "false" @default.
- W4382655345 workType "article" @default.