Matches in SemOpenAlex for { <https://semopenalex.org/work/W2969554168> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2969554168 endingPage "126" @default.
- W2969554168 startingPage "121" @default.
- W2969554168 abstract "Purpose: To evaluate the efficacy of deep learning in judging the need for rebubbling after Descemet's endothelial membrane keratoplasty (DMEK). Methods: This retrospective study included eyes that underwent rebubbling after DMEK (rebubbling group: RB group) and the same number of eyes that did not require rebubbling (non-RB group), based on medical records. To classify the RB group, randomly selected images from anterior segment optical coherence tomography at postoperative day 5 were evaluated by corneal specialists. The criterion for rebubbling was the condition where graft detachment reached the central 4.0-mm pupil area. We trained nine types of deep neural network structures (VGG16, VGG19, ResNet50, InceptionV3, InceptionResNetV2, Xception, DenseNet121, DenseNet169, and DenseNet201) and built nine models. Using each model, we tested the validation data and evaluated the model. Results: This study included 496 images (31 eyes from 24 patients) in the RB group and 496 images (31 eyes from 29 patients) in the non-RB group. Because 16 picture images were obtained from the same point of each eye, a total of 992 images were obtained. The VGG19 model was found to have the highest area under the receiver operating characteristic curve (AUC) of all models. The AUC, sensitivity, and specificity of the VGG19 model were 0.964, 0.967, and 0.915, respectively, whereas those of the best ensemble model were 0.956, 0.913, and 0.921, respectively. Conclusions: This automated system that enables the physician to be aware of the requirement of RB might be clinically useful." @default.
- W2969554168 created "2019-08-29" @default.
- W2969554168 creator A5015580677 @default.
- W2969554168 creator A5023011213 @default.
- W2969554168 creator A5032313766 @default.
- W2969554168 creator A5042812183 @default.
- W2969554168 creator A5061017746 @default.
- W2969554168 creator A5067337466 @default.
- W2969554168 creator A5076874766 @default.
- W2969554168 creator A5082805355 @default.
- W2969554168 date "2020-03-01" @default.
- W2969554168 modified "2023-10-11" @default.
- W2969554168 title "A Deep Learning Approach in Rebubbling After Descemet's Membrane Endothelial Keratoplasty" @default.
- W2969554168 cites W113463448 @default.
- W2969554168 cites W1970391673 @default.
- W2969554168 cites W1980287119 @default.
- W2969554168 cites W1995865377 @default.
- W2969554168 cites W1997989069 @default.
- W2969554168 cites W2010992449 @default.
- W2969554168 cites W2013309362 @default.
- W2969554168 cites W2069796630 @default.
- W2969554168 cites W2098860390 @default.
- W2969554168 cites W2108464386 @default.
- W2969554168 cites W2117539524 @default.
- W2969554168 cites W2135803964 @default.
- W2969554168 cites W2159920218 @default.
- W2969554168 cites W2260167907 @default.
- W2969554168 cites W2311347471 @default.
- W2969554168 cites W2567342045 @default.
- W2969554168 cites W2640386719 @default.
- W2969554168 cites W2775229577 @default.
- W2969554168 cites W2886173263 @default.
- W2969554168 cites W2897020177 @default.
- W2969554168 doi "https://doi.org/10.1097/icl.0000000000000634" @default.
- W2969554168 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31425350" @default.
- W2969554168 hasPublicationYear "2020" @default.
- W2969554168 type Work @default.
- W2969554168 sameAs 2969554168 @default.
- W2969554168 citedByCount "21" @default.
- W2969554168 countsByYear W29695541682020 @default.
- W2969554168 countsByYear W29695541682021 @default.
- W2969554168 countsByYear W29695541682022 @default.
- W2969554168 countsByYear W29695541682023 @default.
- W2969554168 crossrefType "journal-article" @default.
- W2969554168 hasAuthorship W2969554168A5015580677 @default.
- W2969554168 hasAuthorship W2969554168A5023011213 @default.
- W2969554168 hasAuthorship W2969554168A5032313766 @default.
- W2969554168 hasAuthorship W2969554168A5042812183 @default.
- W2969554168 hasAuthorship W2969554168A5061017746 @default.
- W2969554168 hasAuthorship W2969554168A5067337466 @default.
- W2969554168 hasAuthorship W2969554168A5076874766 @default.
- W2969554168 hasAuthorship W2969554168A5082805355 @default.
- W2969554168 hasConcept C118487528 @default.
- W2969554168 hasConcept C126322002 @default.
- W2969554168 hasConcept C154945302 @default.
- W2969554168 hasConcept C2778818243 @default.
- W2969554168 hasConcept C41008148 @default.
- W2969554168 hasConcept C58471807 @default.
- W2969554168 hasConcept C71924100 @default.
- W2969554168 hasConceptScore W2969554168C118487528 @default.
- W2969554168 hasConceptScore W2969554168C126322002 @default.
- W2969554168 hasConceptScore W2969554168C154945302 @default.
- W2969554168 hasConceptScore W2969554168C2778818243 @default.
- W2969554168 hasConceptScore W2969554168C41008148 @default.
- W2969554168 hasConceptScore W2969554168C58471807 @default.
- W2969554168 hasConceptScore W2969554168C71924100 @default.
- W2969554168 hasIssue "2" @default.
- W2969554168 hasLocation W29695541681 @default.
- W2969554168 hasOpenAccess W2969554168 @default.
- W2969554168 hasPrimaryLocation W29695541681 @default.
- W2969554168 hasRelatedWork W1129222023 @default.
- W2969554168 hasRelatedWork W1459292431 @default.
- W2969554168 hasRelatedWork W1976666420 @default.
- W2969554168 hasRelatedWork W2001318290 @default.
- W2969554168 hasRelatedWork W2069676834 @default.
- W2969554168 hasRelatedWork W2167304739 @default.
- W2969554168 hasRelatedWork W2412448159 @default.
- W2969554168 hasRelatedWork W2472580294 @default.
- W2969554168 hasRelatedWork W2940525222 @default.
- W2969554168 hasRelatedWork W4308993413 @default.
- W2969554168 hasVolume "46" @default.
- W2969554168 isParatext "false" @default.
- W2969554168 isRetracted "false" @default.
- W2969554168 magId "2969554168" @default.
- W2969554168 workType "article" @default.