Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387395853> ?p ?o ?g. }
- W4387395853 abstract "Abstract Purpose We developed an Infant Retinal Intelligent Diagnosis System (IRIDS), an automated system to aid early diagnosis and monitoring of infantile fundus diseases and conditions due to a shortage of ophthalmologists. Our aim is to provide personalized monitoring and early intervention to prevent complications associated with infantile fundus diseases, aligning with predictive, preventive, and personalized medicine (PPPM). Methods We developed IRIDS by combining convolutional neural networks and transformer structures, using a dataset of 7697 retinal images from four hospitals. It identifies nine fundus diseases and includes depth attention modules, Res-18, and MaxViT. Performance was compared to that of ophthalmologists using 450 retinal images. The IRIDS employed a five-fold cross-validation approach to generate the classification results. Results Several baseline models achieved the following metrics: accuracy, precision, recall, F1-score (F1), kappa, and area under the receiver operating characteristic curve (AUC) with values of 90.25%, 87.69%, 83.38%, 85.48%, 83.51, and 98.04%, respectively. In comparison, IRIDS outperformed the ophthalmologists with an average accuracy, precision, recall, F1, kappa, and AUC of 96.45%, 95.86%, 94.37%, 95.03%, 94.43, and 99.51%, respectively, in multi-label classification on the test dataset, utilizing the Res-18 and MaxViT models. Compared with ophthalmologists, the IRIDS achieved a higher AUC for the detection of retinal abnormalities. Conclusions IRIDS identifies nine infantile fundus diseases and conditions accurately. It can aid non-ophthalmologist personnel in underserved areas in infantile fundus disease screening. Thus, preventing severe complications. The IRIDS serves as an example of artificial intelligence integration into ophthalmology to achieve better outcomes in PPPM services." @default.
- W4387395853 created "2023-10-07" @default.
- W4387395853 creator A5003672231 @default.
- W4387395853 creator A5009668529 @default.
- W4387395853 creator A5021768064 @default.
- W4387395853 creator A5023463293 @default.
- W4387395853 creator A5026047510 @default.
- W4387395853 creator A5033385234 @default.
- W4387395853 creator A5035301513 @default.
- W4387395853 creator A5041400864 @default.
- W4387395853 creator A5043191858 @default.
- W4387395853 creator A5043302969 @default.
- W4387395853 creator A5048122110 @default.
- W4387395853 creator A5064242236 @default.
- W4387395853 creator A5075134539 @default.
- W4387395853 creator A5077778634 @default.
- W4387395853 creator A5083535929 @default.
- W4387395853 creator A5086765130 @default.
- W4387395853 date "2023-10-06" @default.
- W4387395853 modified "2023-10-07" @default.
- W4387395853 title "Automated Detection of Nine Infantile Fundus Diseases and Conditions in Retinal Images Using a Deep Learning System" @default.
- W4387395853 cites W1616249925 @default.
- W4387395853 cites W1972785704 @default.
- W4387395853 cites W2002411185 @default.
- W4387395853 cites W2008897960 @default.
- W4387395853 cites W2083183395 @default.
- W4387395853 cites W2109363337 @default.
- W4387395853 cites W2150542146 @default.
- W4387395853 cites W2154838561 @default.
- W4387395853 cites W2161675674 @default.
- W4387395853 cites W2171012292 @default.
- W4387395853 cites W2438581107 @default.
- W4387395853 cites W2464807953 @default.
- W4387395853 cites W2532686299 @default.
- W4387395853 cites W2558381168 @default.
- W4387395853 cites W2754535502 @default.
- W4387395853 cites W2899431515 @default.
- W4387395853 cites W2900866761 @default.
- W4387395853 cites W2908201961 @default.
- W4387395853 cites W2946839276 @default.
- W4387395853 cites W2947013723 @default.
- W4387395853 cites W2963691428 @default.
- W4387395853 cites W3008735477 @default.
- W4387395853 cites W3011558785 @default.
- W4387395853 cites W3032941608 @default.
- W4387395853 cites W3035982996 @default.
- W4387395853 cites W3054721590 @default.
- W4387395853 cites W3081449365 @default.
- W4387395853 cites W3082280702 @default.
- W4387395853 cites W3087171788 @default.
- W4387395853 cites W3135271505 @default.
- W4387395853 cites W3161335586 @default.
- W4387395853 cites W3164440025 @default.
- W4387395853 cites W3174985928 @default.
- W4387395853 cites W3182791891 @default.
- W4387395853 cites W3185043567 @default.
- W4387395853 cites W3185599615 @default.
- W4387395853 cites W3191934798 @default.
- W4387395853 cites W3197896048 @default.
- W4387395853 cites W3202264272 @default.
- W4387395853 cites W3207081046 @default.
- W4387395853 cites W4211139356 @default.
- W4387395853 cites W4211146114 @default.
- W4387395853 cites W4225329856 @default.
- W4387395853 cites W4236980141 @default.
- W4387395853 cites W4292528167 @default.
- W4387395853 cites W4295025017 @default.
- W4387395853 cites W4309284039 @default.
- W4387395853 cites W4323348175 @default.
- W4387395853 cites W4324367482 @default.
- W4387395853 cites W4385627246 @default.
- W4387395853 doi "https://doi.org/10.21203/rs.3.rs-3303322/v1" @default.
- W4387395853 hasPublicationYear "2023" @default.
- W4387395853 type Work @default.
- W4387395853 citedByCount "0" @default.
- W4387395853 crossrefType "posted-content" @default.
- W4387395853 hasAuthorship W4387395853A5003672231 @default.
- W4387395853 hasAuthorship W4387395853A5009668529 @default.
- W4387395853 hasAuthorship W4387395853A5021768064 @default.
- W4387395853 hasAuthorship W4387395853A5023463293 @default.
- W4387395853 hasAuthorship W4387395853A5026047510 @default.
- W4387395853 hasAuthorship W4387395853A5033385234 @default.
- W4387395853 hasAuthorship W4387395853A5035301513 @default.
- W4387395853 hasAuthorship W4387395853A5041400864 @default.
- W4387395853 hasAuthorship W4387395853A5043191858 @default.
- W4387395853 hasAuthorship W4387395853A5043302969 @default.
- W4387395853 hasAuthorship W4387395853A5048122110 @default.
- W4387395853 hasAuthorship W4387395853A5064242236 @default.
- W4387395853 hasAuthorship W4387395853A5075134539 @default.
- W4387395853 hasAuthorship W4387395853A5077778634 @default.
- W4387395853 hasAuthorship W4387395853A5083535929 @default.
- W4387395853 hasAuthorship W4387395853A5086765130 @default.
- W4387395853 hasBestOaLocation W43873958531 @default.
- W4387395853 hasConcept C118487528 @default.
- W4387395853 hasConcept C119767625 @default.
- W4387395853 hasConcept C126322002 @default.
- W4387395853 hasConcept C138885662 @default.
- W4387395853 hasConcept C148524875 @default.
- W4387395853 hasConcept C154945302 @default.
- W4387395853 hasConcept C194051981 @default.