FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380135861> ?p ?o ?g. }

• W4380135861 endingPage "1904" @default.
• W4380135861 startingPage "1904" @default.
• W4380135861 abstract "Multiple studies presented satisfactory performances for the treatment of various ocular diseases. To date, there has been no study that describes a multiclass model, medically accurate, and trained on large diverse dataset. No study has addressed a class imbalance problem in one giant dataset originating from multiple large diverse eye fundus image collections. To ensure a real-life clinical environment and mitigate the problem of biased medical image data, 22 publicly available datasets were merged. To secure medical validity only Diabetic Retinopathy (DR), Age-Related Macular Degeneration (AMD) and Glaucoma (GL) were included. The state-of-the-art models ConvNext, RegNet and ResNet were utilized. In the resulting dataset, there were 86,415 normal, 3787 GL, 632 AMD and 34,379 DR fundus images. ConvNextTiny achieved the best results in terms of recognizing most of the examined eye diseases with the most metrics. The overall accuracy was 80.46 ± 1.48. Specific accuracy values were: 80.01 ± 1.10 for normal eye fundus, 97.20 ± 0.66 for GL, 98.14 ± 0.31 for AMD, 80.66 ± 1.27 for DR. A suitable screening model for the most prevalent retinal diseases in ageing societies was designed. The model was developed on a diverse, combined large dataset which made the obtained results less biased and more generalizable." @default.
• W4380135861 created "2023-06-10" @default.
• W4380135861 creator A5013028069 @default.
• W4380135861 creator A5051875707 @default.
• W4380135861 creator A5056668715 @default.
• W4380135861 creator A5071603574 @default.
• W4380135861 creator A5072011867 @default.
• W4380135861 creator A5090973063 @default.
• W4380135861 date "2023-05-29" @default.
• W4380135861 modified "2023-10-01" @default.
• W4380135861 title "Counteracting Data Bias and Class Imbalance—Towards a Useful and Reliable Retinal Disease Recognition System" @default.
• W4380135861 cites W1979159103 @default.
• W4380135861 cites W1982722705 @default.
• W4380135861 cites W1982890488 @default.
• W4380135861 cites W2029616009 @default.
• W4380135861 cites W2053724458 @default.
• W4380135861 cites W2069890151 @default.
• W4380135861 cites W2073244572 @default.
• W4380135861 cites W2096451472 @default.
• W4380135861 cites W2099001231 @default.
• W4380135861 cites W2107871626 @default.
• W4380135861 cites W2114404799 @default.
• W4380135861 cites W2119168155 @default.
• W4380135861 cites W2145305441 @default.
• W4380135861 cites W2155434128 @default.
• W4380135861 cites W2329667864 @default.
• W4380135861 cites W2513863019 @default.
• W4380135861 cites W2529153069 @default.
• W4380135861 cites W2549139847 @default.
• W4380135861 cites W2587235033 @default.
• W4380135861 cites W2640386719 @default.
• W4380135861 cites W2741346289 @default.
• W4380135861 cites W2766761250 @default.
• W4380135861 cites W2783530987 @default.
• W4380135861 cites W2790291405 @default.
• W4380135861 cites W2806796234 @default.
• W4380135861 cites W2905017682 @default.
• W4380135861 cites W2908723242 @default.
• W4380135861 cites W2918145471 @default.
• W4380135861 cites W2936503027 @default.
• W4380135861 cites W2938600289 @default.
• W4380135861 cites W2940692219 @default.
• W4380135861 cites W2946839276 @default.
• W4380135861 cites W2949074827 @default.
• W4380135861 cites W2963142663 @default.
• W4380135861 cites W2963163009 @default.
• W4380135861 cites W2979448322 @default.
• W4380135861 cites W3015487562 @default.
• W4380135861 cites W3016810854 @default.
• W4380135861 cites W3019179251 @default.
• W4380135861 cites W3034429256 @default.
• W4380135861 cites W3099319035 @default.
• W4380135861 cites W3108542203 @default.
• W4380135861 cites W3108854387 @default.
• W4380135861 cites W3112251966 @default.
• W4380135861 cites W3119036516 @default.
• W4380135861 cites W3128220181 @default.
• W4380135861 cites W3138516171 @default.
• W4380135861 cites W3149332725 @default.
• W4380135861 cites W3163465952 @default.
• W4380135861 cites W3165337298 @default.
• W4380135861 cites W3185043567 @default.
• W4380135861 cites W3187537691 @default.
• W4380135861 cites W3193830270 @default.
• W4380135861 cites W3194979994 @default.
• W4380135861 cites W4225095641 @default.
• W4380135861 cites W4225597912 @default.
• W4380135861 cites W4280535852 @default.
• W4380135861 cites W4280573064 @default.
• W4380135861 cites W4281720940 @default.
• W4380135861 cites W4286510766 @default.
• W4380135861 cites W4300423192 @default.
• W4380135861 cites W4302774859 @default.
• W4380135861 cites W4312443924 @default.
• W4380135861 doi "https://doi.org/10.3390/diagnostics13111904" @default.
• W4380135861 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37296756" @default.
• W4380135861 hasPublicationYear "2023" @default.
• W4380135861 type Work @default.
• W4380135861 citedByCount "0" @default.
• W4380135861 crossrefType "journal-article" @default.
• W4380135861 hasAuthorship W4380135861A5013028069 @default.
• W4380135861 hasAuthorship W4380135861A5051875707 @default.
• W4380135861 hasAuthorship W4380135861A5056668715 @default.
• W4380135861 hasAuthorship W4380135861A5071603574 @default.
• W4380135861 hasAuthorship W4380135861A5072011867 @default.
• W4380135861 hasAuthorship W4380135861A5090973063 @default.
• W4380135861 hasBestOaLocation W43801358611 @default.
• W4380135861 hasConcept C118487528 @default.
• W4380135861 hasConcept C119767625 @default.
• W4380135861 hasConcept C134018914 @default.
• W4380135861 hasConcept C153180895 @default.
• W4380135861 hasConcept C154945302 @default.
• W4380135861 hasConcept C2776391266 @default.
• W4380135861 hasConcept C2776403814 @default.
• W4380135861 hasConcept C2777212361 @default.
• W4380135861 hasConcept C2778527774 @default.
• W4380135861 hasConcept C2779829184 @default.
• W4380135861 hasConcept C2780827179 @default.

• next