Matches in SemOpenAlex for { <https://semopenalex.org/work/W2921900517> ?p ?o ?g. }
- W2921900517 endingPage "45" @default.
- W2921900517 startingPage "37" @default.
- W2921900517 abstract "PurposeAnterior segment optical coherence tomography (AS-OCT) provides an objective imaging modality for visually identifying anterior segment structures. An automated detection system could assist ophthalmologists in interpreting AS-OCT images for the presence of angle closure.DesignDevelopment of an artificial intelligence automated detection system for the presence of angle closure.MethodsA deep learning system for automated angle-closure detection in AS-OCT images was developed, and this was compared with another automated angle-closure detection system based on quantitative features. A total of 4135 Visante AS-OCT images from 2113 subjects (8270 anterior chamber angle images with 7375 open-angle and 895 angle-closure) were examined. The deep learning angle-closure detection system for a 2-class classification problem was tested by 5-fold cross-validation. The deep learning system and the automated angle-closure detection system based on quantitative features were evaluated against clinicians' grading of AS-OCT images as the reference standard.ResultsThe area under the receiver operating characteristic curve of the system using quantitative features was 0.90 (95% confidence interval [CI] 0.891–0.914) with a sensitivity of 0.79 ± 0.037 and a specificity of 0.87 ± 0.009, while the area under the receiver operating characteristic curve of the deep learning system was 0.96 (95% CI 0.953–0.968) with a sensitivity of 0.90 ± 0.02 and a specificity of 0.92 ± 0.008, against clinicians' grading of AS-OCT images as the reference standard.ConclusionsThe results demonstrate the potential of the deep learning system for angle-closure detection in AS-OCT images. Anterior segment optical coherence tomography (AS-OCT) provides an objective imaging modality for visually identifying anterior segment structures. An automated detection system could assist ophthalmologists in interpreting AS-OCT images for the presence of angle closure. Development of an artificial intelligence automated detection system for the presence of angle closure. A deep learning system for automated angle-closure detection in AS-OCT images was developed, and this was compared with another automated angle-closure detection system based on quantitative features. A total of 4135 Visante AS-OCT images from 2113 subjects (8270 anterior chamber angle images with 7375 open-angle and 895 angle-closure) were examined. The deep learning angle-closure detection system for a 2-class classification problem was tested by 5-fold cross-validation. The deep learning system and the automated angle-closure detection system based on quantitative features were evaluated against clinicians' grading of AS-OCT images as the reference standard. The area under the receiver operating characteristic curve of the system using quantitative features was 0.90 (95% confidence interval [CI] 0.891–0.914) with a sensitivity of 0.79 ± 0.037 and a specificity of 0.87 ± 0.009, while the area under the receiver operating characteristic curve of the deep learning system was 0.96 (95% CI 0.953–0.968) with a sensitivity of 0.90 ± 0.02 and a specificity of 0.92 ± 0.008, against clinicians' grading of AS-OCT images as the reference standard. The results demonstrate the potential of the deep learning system for angle-closure detection in AS-OCT images." @default.
- W2921900517 created "2019-03-22" @default.
- W2921900517 creator A5004658590 @default.
- W2921900517 creator A5005936176 @default.
- W2921900517 creator A5010107902 @default.
- W2921900517 creator A5010906829 @default.
- W2921900517 creator A5010970485 @default.
- W2921900517 creator A5022464374 @default.
- W2921900517 creator A5025114648 @default.
- W2921900517 creator A5052850959 @default.
- W2921900517 creator A5057053486 @default.
- W2921900517 creator A5063146071 @default.
- W2921900517 date "2019-07-01" @default.
- W2921900517 modified "2023-10-18" @default.
- W2921900517 title "A Deep Learning System for Automated Angle-Closure Detection in Anterior Segment Optical Coherence Tomography Images" @default.
- W2921900517 cites W2017366622 @default.
- W2921900517 cites W2018083974 @default.
- W2921900517 cites W2057266151 @default.
- W2921900517 cites W2062810408 @default.
- W2921900517 cites W2076063813 @default.
- W2921900517 cites W2079069831 @default.
- W2921900517 cites W2079552429 @default.
- W2921900517 cites W2080281518 @default.
- W2921900517 cites W2113270177 @default.
- W2921900517 cites W2117539524 @default.
- W2921900517 cites W2123509284 @default.
- W2921900517 cites W2125829195 @default.
- W2921900517 cites W2130509936 @default.
- W2921900517 cites W2153635508 @default.
- W2921900517 cites W2155429661 @default.
- W2921900517 cites W2160605010 @default.
- W2921900517 cites W2162244567 @default.
- W2921900517 cites W2165698076 @default.
- W2921900517 cites W2169176543 @default.
- W2921900517 cites W217075555 @default.
- W2921900517 cites W2469369919 @default.
- W2921900517 cites W2581082771 @default.
- W2921900517 cites W2582821003 @default.
- W2921900517 cites W2586562547 @default.
- W2921900517 cites W2613836512 @default.
- W2921900517 cites W2618530766 @default.
- W2921900517 cites W2752747624 @default.
- W2921900517 cites W2758333670 @default.
- W2921900517 cites W2772246530 @default.
- W2921900517 cites W2772723798 @default.
- W2921900517 cites W2788633781 @default.
- W2921900517 cites W2792026451 @default.
- W2921900517 cites W2919115771 @default.
- W2921900517 cites W3101386228 @default.
- W2921900517 cites W3101507774 @default.
- W2921900517 doi "https://doi.org/10.1016/j.ajo.2019.02.028" @default.
- W2921900517 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30849350" @default.
- W2921900517 hasPublicationYear "2019" @default.
- W2921900517 type Work @default.
- W2921900517 sameAs 2921900517 @default.
- W2921900517 citedByCount "100" @default.
- W2921900517 countsByYear W29219005172019 @default.
- W2921900517 countsByYear W29219005172020 @default.
- W2921900517 countsByYear W29219005172021 @default.
- W2921900517 countsByYear W29219005172022 @default.
- W2921900517 countsByYear W29219005172023 @default.
- W2921900517 crossrefType "journal-article" @default.
- W2921900517 hasAuthorship W2921900517A5004658590 @default.
- W2921900517 hasAuthorship W2921900517A5005936176 @default.
- W2921900517 hasAuthorship W2921900517A5010107902 @default.
- W2921900517 hasAuthorship W2921900517A5010906829 @default.
- W2921900517 hasAuthorship W2921900517A5010970485 @default.
- W2921900517 hasAuthorship W2921900517A5022464374 @default.
- W2921900517 hasAuthorship W2921900517A5025114648 @default.
- W2921900517 hasAuthorship W2921900517A5052850959 @default.
- W2921900517 hasAuthorship W2921900517A5057053486 @default.
- W2921900517 hasAuthorship W2921900517A5063146071 @default.
- W2921900517 hasBestOaLocation W29219005171 @default.
- W2921900517 hasConcept C108583219 @default.
- W2921900517 hasConcept C118487528 @default.
- W2921900517 hasConcept C119857082 @default.
- W2921900517 hasConcept C146834321 @default.
- W2921900517 hasConcept C154945302 @default.
- W2921900517 hasConcept C162324750 @default.
- W2921900517 hasConcept C2778818243 @default.
- W2921900517 hasConcept C2780226545 @default.
- W2921900517 hasConcept C31972630 @default.
- W2921900517 hasConcept C34447519 @default.
- W2921900517 hasConcept C41008148 @default.
- W2921900517 hasConcept C58471807 @default.
- W2921900517 hasConcept C71924100 @default.
- W2921900517 hasConceptScore W2921900517C108583219 @default.
- W2921900517 hasConceptScore W2921900517C118487528 @default.
- W2921900517 hasConceptScore W2921900517C119857082 @default.
- W2921900517 hasConceptScore W2921900517C146834321 @default.
- W2921900517 hasConceptScore W2921900517C154945302 @default.
- W2921900517 hasConceptScore W2921900517C162324750 @default.
- W2921900517 hasConceptScore W2921900517C2778818243 @default.
- W2921900517 hasConceptScore W2921900517C2780226545 @default.
- W2921900517 hasConceptScore W2921900517C31972630 @default.
- W2921900517 hasConceptScore W2921900517C34447519 @default.
- W2921900517 hasConceptScore W2921900517C41008148 @default.
- W2921900517 hasConceptScore W2921900517C58471807 @default.