FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2772059204> ?p ?o ?g. }

• W2772059204 endingPage "558" @default.
• W2772059204 startingPage "549" @default.
• W2772059204 abstract "PurposeDevelopment and validation of a fully automated method to detect and quantify macular fluid in conventional OCT images.DesignDevelopment of a diagnostic modality.ParticipantsThe clinical dataset for fluid detection consisted of 1200 OCT volumes of patients with neovascular age-related macular degeneration (AMD, n = 400), diabetic macular edema (DME, n = 400), or retinal vein occlusion (RVO, n = 400) acquired with Zeiss Cirrus (Carl Zeiss Meditec, Dublin, CA) (n = 600) or Heidelberg Spectralis (Heidelberg Engineering, Heidelberg, Germany) (n = 600) OCT devices.MethodsA method based on deep learning to automatically detect and quantify intraretinal cystoid fluid (IRC) and subretinal fluid (SRF) was developed. The performance of the algorithm in accurately identifying fluid localization and extent was evaluated against a manual consensus reading of 2 masked reading center graders.Main Outcome MeasuresPerformance of a fully automated method to accurately detect, differentiate, and quantify intraretinal and SRF using area under the receiver operating characteristics curves, precision, and recall.ResultsThe newly designed, fully automated diagnostic method based on deep learning achieved optimal accuracy for the detection and quantification of IRC for all 3 macular pathologies with a mean accuracy (AUC) of 0.94 (range, 0.91–0.97), a mean precision of 0.91, and a mean recall of 0.84. The detection and measurement of SRF were also highly accurate with an AUC of 0.92 (range, 0.86–0.98), a mean precision of 0.61, and a mean recall of 0.81, with superior performance in neovascular AMD and RVO compared with DME, which was represented rarely in the population studied. High linear correlation was confirmed between automated and manual fluid localization and quantification, yielding an average Pearson's correlation coefficient of 0.90 for IRC and of 0.96 for SRF.ConclusionsDeep learning in retinal image analysis achieves excellent accuracy for the differential detection of retinal fluid types across the most prevalent exudative macular diseases and OCT devices. Furthermore, quantification of fluid achieves a high level of concordance with manual expert assessment. Fully automated analysis of retinal OCT images from clinical routine provides a promising horizon in improving accuracy and reliability of retinal diagnosis for research and clinical practice in ophthalmology. Development and validation of a fully automated method to detect and quantify macular fluid in conventional OCT images. Development of a diagnostic modality. The clinical dataset for fluid detection consisted of 1200 OCT volumes of patients with neovascular age-related macular degeneration (AMD, n = 400), diabetic macular edema (DME, n = 400), or retinal vein occlusion (RVO, n = 400) acquired with Zeiss Cirrus (Carl Zeiss Meditec, Dublin, CA) (n = 600) or Heidelberg Spectralis (Heidelberg Engineering, Heidelberg, Germany) (n = 600) OCT devices. A method based on deep learning to automatically detect and quantify intraretinal cystoid fluid (IRC) and subretinal fluid (SRF) was developed. The performance of the algorithm in accurately identifying fluid localization and extent was evaluated against a manual consensus reading of 2 masked reading center graders. Performance of a fully automated method to accurately detect, differentiate, and quantify intraretinal and SRF using area under the receiver operating characteristics curves, precision, and recall. The newly designed, fully automated diagnostic method based on deep learning achieved optimal accuracy for the detection and quantification of IRC for all 3 macular pathologies with a mean accuracy (AUC) of 0.94 (range, 0.91–0.97), a mean precision of 0.91, and a mean recall of 0.84. The detection and measurement of SRF were also highly accurate with an AUC of 0.92 (range, 0.86–0.98), a mean precision of 0.61, and a mean recall of 0.81, with superior performance in neovascular AMD and RVO compared with DME, which was represented rarely in the population studied. High linear correlation was confirmed between automated and manual fluid localization and quantification, yielding an average Pearson's correlation coefficient of 0.90 for IRC and of 0.96 for SRF. Deep learning in retinal image analysis achieves excellent accuracy for the differential detection of retinal fluid types across the most prevalent exudative macular diseases and OCT devices. Furthermore, quantification of fluid achieves a high level of concordance with manual expert assessment. Fully automated analysis of retinal OCT images from clinical routine provides a promising horizon in improving accuracy and reliability of retinal diagnosis for research and clinical practice in ophthalmology." @default.
• W2772059204 created "2017-12-22" @default.
• W2772059204 creator A5003511566 @default.
• W2772059204 creator A5013494845 @default.
• W2772059204 creator A5013612641 @default.
• W2772059204 creator A5022559727 @default.
• W2772059204 creator A5023541609 @default.
• W2772059204 creator A5045723460 @default.
• W2772059204 creator A5053563726 @default.
• W2772059204 creator A5060814361 @default.
• W2772059204 creator A5070024582 @default.
• W2772059204 creator A5089575197 @default.
• W2772059204 date "2018-04-01" @default.
• W2772059204 modified "2023-10-11" @default.
• W2772059204 title "Fully Automated Detection and Quantification of Macular Fluid in OCT Using Deep Learning" @default.
• W2772059204 cites W1458919156 @default.
• W2772059204 cites W1745334888 @default.
• W2772059204 cites W1965018345 @default.
• W2772059204 cites W1980342089 @default.
• W2772059204 cites W1990374749 @default.
• W2772059204 cites W1990889412 @default.
• W2772059204 cites W2052102026 @default.
• W2772059204 cites W2074598933 @default.
• W2772059204 cites W2115527343 @default.
• W2772059204 cites W2127318120 @default.
• W2772059204 cites W2132830939 @default.
• W2772059204 cites W2134542952 @default.
• W2772059204 cites W2152575748 @default.
• W2772059204 cites W2170895371 @default.
• W2772059204 cites W2192471031 @default.
• W2772059204 cites W2225799082 @default.
• W2772059204 cites W2288961271 @default.
• W2772059204 cites W2304396421 @default.
• W2772059204 cites W2316418129 @default.
• W2772059204 cites W2319638030 @default.
• W2772059204 cites W2330952183 @default.
• W2772059204 cites W2343042175 @default.
• W2772059204 cites W2346873848 @default.
• W2772059204 cites W2399141010 @default.
• W2772059204 cites W2418802570 @default.
• W2772059204 cites W2529153069 @default.
• W2772059204 cites W2549799826 @default.
• W2772059204 cites W2589074029 @default.
• W2772059204 cites W2598442119 @default.
• W2772059204 doi "https://doi.org/10.1016/j.ophtha.2017.10.031" @default.
• W2772059204 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29224926" @default.
• W2772059204 hasPublicationYear "2018" @default.
• W2772059204 type Work @default.
• W2772059204 sameAs 2772059204 @default.
• W2772059204 citedByCount "355" @default.
• W2772059204 countsByYear W27720592042018 @default.
• W2772059204 countsByYear W27720592042019 @default.
• W2772059204 countsByYear W27720592042020 @default.
• W2772059204 countsByYear W27720592042021 @default.
• W2772059204 countsByYear W27720592042022 @default.
• W2772059204 countsByYear W27720592042023 @default.
• W2772059204 crossrefType "journal-article" @default.
• W2772059204 hasAuthorship W2772059204A5003511566 @default.
• W2772059204 hasAuthorship W2772059204A5013494845 @default.
• W2772059204 hasAuthorship W2772059204A5013612641 @default.
• W2772059204 hasAuthorship W2772059204A5022559727 @default.
• W2772059204 hasAuthorship W2772059204A5023541609 @default.
• W2772059204 hasAuthorship W2772059204A5045723460 @default.
• W2772059204 hasAuthorship W2772059204A5053563726 @default.
• W2772059204 hasAuthorship W2772059204A5060814361 @default.
• W2772059204 hasAuthorship W2772059204A5070024582 @default.
• W2772059204 hasAuthorship W2772059204A5089575197 @default.
• W2772059204 hasBestOaLocation W27720592041 @default.
• W2772059204 hasConcept C118487528 @default.
• W2772059204 hasConcept C126322002 @default.
• W2772059204 hasConcept C154945302 @default.
• W2772059204 hasConcept C2776403814 @default.
• W2772059204 hasConcept C2780261187 @default.
• W2772059204 hasConcept C2780347916 @default.
• W2772059204 hasConcept C2780827179 @default.
• W2772059204 hasConcept C41008148 @default.
• W2772059204 hasConcept C58471807 @default.
• W2772059204 hasConcept C71924100 @default.
• W2772059204 hasConceptScore W2772059204C118487528 @default.
• W2772059204 hasConceptScore W2772059204C126322002 @default.
• W2772059204 hasConceptScore W2772059204C154945302 @default.
• W2772059204 hasConceptScore W2772059204C2776403814 @default.
• W2772059204 hasConceptScore W2772059204C2780261187 @default.
• W2772059204 hasConceptScore W2772059204C2780347916 @default.
• W2772059204 hasConceptScore W2772059204C2780827179 @default.
• W2772059204 hasConceptScore W2772059204C41008148 @default.
• W2772059204 hasConceptScore W2772059204C58471807 @default.
• W2772059204 hasConceptScore W2772059204C71924100 @default.
• W2772059204 hasIssue "4" @default.
• W2772059204 hasLocation W27720592041 @default.
• W2772059204 hasLocation W27720592042 @default.
• W2772059204 hasOpenAccess W2772059204 @default.
• W2772059204 hasPrimaryLocation W27720592041 @default.
• W2772059204 hasRelatedWork W2022621467 @default.
• W2772059204 hasRelatedWork W2061521349 @default.
• W2772059204 hasRelatedWork W2069958997 @default.
• W2772059204 hasRelatedWork W2943816469 @default.
• W2772059204 hasRelatedWork W3021640372 @default.

• next