FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3165337298> ?p ?o ?g. }

• W3165337298 endingPage "e27822" @default.
• W3165337298 startingPage "e27822" @default.
• W3165337298 abstract "The supervised deep learning approach provides state-of-the-art performance in a variety of fundus image classification tasks, but it is not applicable for screening tasks with numerous or unknown disease types. The unsupervised anomaly detection (AD) approach, which needs only normal samples to develop a model, may be a workable and cost-saving method of screening for ocular diseases.This study aimed to develop and evaluate an AD model for detecting ocular diseases on the basis of color fundus images.A generative adversarial network-based AD method for detecting possible ocular diseases was developed and evaluated using 90,499 retinal fundus images derived from 4 large-scale real-world data sets. Four other independent external test sets were used for external testing and further analysis of the model's performance in detecting 6 common ocular diseases (diabetic retinopathy [DR], glaucoma, cataract, age-related macular degeneration, hypertensive retinopathy [HR], and myopia), DR of different severity levels, and 36 categories of abnormal fundus images. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the model's performance were calculated and presented.Our model achieved an AUC of 0.896 with 82.69% sensitivity and 82.63% specificity in detecting abnormal fundus images in the internal test set, and it achieved an AUC of 0.900 with 83.25% sensitivity and 85.19% specificity in 1 external proprietary data set. In the detection of 6 common ocular diseases, the AUCs for DR, glaucoma, cataract, AMD, HR, and myopia were 0.891, 0.916, 0.912, 0.867, 0.895, and 0.961, respectively. Moreover, the AD model had an AUC of 0.868 for detecting any DR, 0.908 for detecting referable DR, and 0.926 for detecting vision-threatening DR.The AD approach achieved high sensitivity and specificity in detecting ocular diseases on the basis of fundus images, which implies that this model might be an efficient and economical tool for optimizing current clinical pathways for ophthalmologists. Future studies are required to evaluate the practical applicability of the AD approach in ocular disease screening." @default.
• W3165337298 created "2021-06-07" @default.
• W3165337298 creator A5012272799 @default.
• W3165337298 creator A5019335607 @default.
• W3165337298 creator A5023039553 @default.
• W3165337298 creator A5038168956 @default.
• W3165337298 creator A5039810086 @default.
• W3165337298 creator A5046621948 @default.
• W3165337298 creator A5048556510 @default.
• W3165337298 creator A5052274720 @default.
• W3165337298 creator A5079738340 @default.
• W3165337298 date "2021-07-13" @default.
• W3165337298 modified "2023-09-28" @default.
• W3165337298 title "Application of an Anomaly Detection Model to Screen for Ocular Diseases Using Color Retinal Fundus Images: Design and Evaluation Study" @default.
• W3165337298 cites W1616249925 @default.
• W3165337298 cites W1966206262 @default.
• W3165337298 cites W1969496006 @default.
• W3165337298 cites W1984639731 @default.
• W3165337298 cites W1985319805 @default.
• W3165337298 cites W2020279228 @default.
• W3165337298 cites W2039730121 @default.
• W3165337298 cites W2073244572 @default.
• W3165337298 cites W2084512860 @default.
• W3165337298 cites W2095345875 @default.
• W3165337298 cites W2107910786 @default.
• W3165337298 cites W2115627867 @default.
• W3165337298 cites W2119018277 @default.
• W3165337298 cites W2137130182 @default.
• W3165337298 cites W2152575748 @default.
• W3165337298 cites W2278186031 @default.
• W3165337298 cites W2341086315 @default.
• W3165337298 cites W2533835508 @default.
• W3165337298 cites W2557738935 @default.
• W3165337298 cites W2558381168 @default.
• W3165337298 cites W2598442119 @default.
• W3165337298 cites W2741346289 @default.
• W3165337298 cites W2758333670 @default.
• W3165337298 cites W2772246530 @default.
• W3165337298 cites W2884120031 @default.
• W3165337298 cites W2893356526 @default.
• W3165337298 cites W2911835721 @default.
• W3165337298 cites W2912072952 @default.
• W3165337298 cites W2914570111 @default.
• W3165337298 cites W2964032056 @default.
• W3165337298 cites W2966096374 @default.
• W3165337298 cites W2978971541 @default.
• W3165337298 cites W2980623771 @default.
• W3165337298 cites W2991417312 @default.
• W3165337298 cites W3027067201 @default.
• W3165337298 cites W3101386228 @default.
• W3165337298 cites W3106336869 @default.
• W3165337298 cites W4205796877 @default.
• W3165337298 doi "https://doi.org/10.2196/27822" @default.
• W3165337298 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8317033" @default.
• W3165337298 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34255681" @default.
• W3165337298 hasPublicationYear "2021" @default.
• W3165337298 type Work @default.
• W3165337298 sameAs 3165337298 @default.
• W3165337298 citedByCount "15" @default.
• W3165337298 countsByYear W31653372982022 @default.
• W3165337298 countsByYear W31653372982023 @default.
• W3165337298 crossrefType "journal-article" @default.
• W3165337298 hasAuthorship W3165337298A5012272799 @default.
• W3165337298 hasAuthorship W3165337298A5019335607 @default.
• W3165337298 hasAuthorship W3165337298A5023039553 @default.
• W3165337298 hasAuthorship W3165337298A5038168956 @default.
• W3165337298 hasAuthorship W3165337298A5039810086 @default.
• W3165337298 hasAuthorship W3165337298A5046621948 @default.
• W3165337298 hasAuthorship W3165337298A5048556510 @default.
• W3165337298 hasAuthorship W3165337298A5052274720 @default.
• W3165337298 hasAuthorship W3165337298A5079738340 @default.
• W3165337298 hasBestOaLocation W31653372981 @default.
• W3165337298 hasConcept C118487528 @default.
• W3165337298 hasConcept C119767625 @default.
• W3165337298 hasConcept C126322002 @default.
• W3165337298 hasConcept C134018914 @default.
• W3165337298 hasConcept C153180895 @default.
• W3165337298 hasConcept C154945302 @default.
• W3165337298 hasConcept C169903167 @default.
• W3165337298 hasConcept C2776391266 @default.
• W3165337298 hasConcept C2776403814 @default.
• W3165337298 hasConcept C2778313320 @default.
• W3165337298 hasConcept C2778527774 @default.
• W3165337298 hasConcept C2779829184 @default.
• W3165337298 hasConcept C41008148 @default.
• W3165337298 hasConcept C555293320 @default.
• W3165337298 hasConcept C58471807 @default.
• W3165337298 hasConcept C71924100 @default.
• W3165337298 hasConceptScore W3165337298C118487528 @default.
• W3165337298 hasConceptScore W3165337298C119767625 @default.
• W3165337298 hasConceptScore W3165337298C126322002 @default.
• W3165337298 hasConceptScore W3165337298C134018914 @default.
• W3165337298 hasConceptScore W3165337298C153180895 @default.
• W3165337298 hasConceptScore W3165337298C154945302 @default.
• W3165337298 hasConceptScore W3165337298C169903167 @default.
• W3165337298 hasConceptScore W3165337298C2776391266 @default.
• W3165337298 hasConceptScore W3165337298C2776403814 @default.
• W3165337298 hasConceptScore W3165337298C2778313320 @default.

• next