Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306181330> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4306181330 endingPage "321063" @default.
- W4306181330 startingPage "bjophthalmol" @default.
- W4306181330 abstract "Retinal capillary non-perfusion (NP) and neovascularisation (NV) are two of the most important angiographic changes in diabetic retinopathy (DR). This study investigated the feasibility of using deep learning (DL) models to automatically segment NP and NV on ultra-widefield fluorescein angiography (UWFA) images from patients with DR.Retrospective cross-sectional chart review study. In total, 951 UWFA images were collected from patients with severe non-proliferative DR (NPDR) or proliferative DR (PDR). Each image was segmented and labelled for NP, NV, disc, background and outside areas. Using the labelled images, DL models were trained and validated (80%) using convolutional neural networks (CNNs) for automated segmentation and tested (20%) on test sets. Accuracy of each model and each label were assessed.The best accuracy from CNN models for each label was 0.8208, 0.8338, 0.9801, 0.9253 and 0.9766 for NP, NV, disc, background and outside areas, respectively. The best Intersection over Union for each label was 0.6806, 0.5675, 0.7107, 0.8551 and 0.924 and mean mean boundary F1 score (BF score) was 0.6702, 0.8742, 0.9092, 0.8103 and 0.9006, respectively.DL models can detect NV and NP as well as disc and outer margins on UWFA with good performance. This automated segmentation of important UWFA features will aid physicians in DR clinics and in overcoming grader subjectivity." @default.
- W4306181330 created "2022-10-14" @default.
- W4306181330 creator A5005285222 @default.
- W4306181330 creator A5033654219 @default.
- W4306181330 creator A5078654943 @default.
- W4306181330 date "2022-10-14" @default.
- W4306181330 modified "2023-10-14" @default.
- W4306181330 title "Automated segmentation of ultra-widefield fluorescein angiography of diabetic retinopathy using deep learning" @default.
- W4306181330 cites W125293084 @default.
- W4306181330 cites W1627947970 @default.
- W4306181330 cites W1976009317 @default.
- W4306181330 cites W1980157635 @default.
- W4306181330 cites W2063115250 @default.
- W4306181330 cites W2073043719 @default.
- W4306181330 cites W2085933963 @default.
- W4306181330 cites W2127985152 @default.
- W4306181330 cites W2139031088 @default.
- W4306181330 cites W2152922676 @default.
- W4306181330 cites W2157670318 @default.
- W4306181330 cites W2277325960 @default.
- W4306181330 cites W2292044738 @default.
- W4306181330 cites W2328462406 @default.
- W4306181330 cites W2385884905 @default.
- W4306181330 cites W2528820933 @default.
- W4306181330 cites W2598442119 @default.
- W4306181330 cites W2758333670 @default.
- W4306181330 cites W2772246530 @default.
- W4306181330 cites W2895460990 @default.
- W4306181330 cites W2898192966 @default.
- W4306181330 cites W2921816200 @default.
- W4306181330 cites W2966011162 @default.
- W4306181330 cites W2985131824 @default.
- W4306181330 cites W3024956298 @default.
- W4306181330 cites W3047378341 @default.
- W4306181330 cites W3087702805 @default.
- W4306181330 cites W3092658921 @default.
- W4306181330 cites W3112446056 @default.
- W4306181330 cites W3190658604 @default.
- W4306181330 cites W4211031298 @default.
- W4306181330 cites W4211205882 @default.
- W4306181330 cites W4212945288 @default.
- W4306181330 cites W4244248663 @default.
- W4306181330 doi "https://doi.org/10.1136/bjo-2022-321063" @default.
- W4306181330 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36241374" @default.
- W4306181330 hasPublicationYear "2022" @default.
- W4306181330 type Work @default.
- W4306181330 citedByCount "1" @default.
- W4306181330 countsByYear W43061813302023 @default.
- W4306181330 crossrefType "journal-article" @default.
- W4306181330 hasAuthorship W4306181330A5005285222 @default.
- W4306181330 hasAuthorship W4306181330A5033654219 @default.
- W4306181330 hasAuthorship W4306181330A5078654943 @default.
- W4306181330 hasConcept C108583219 @default.
- W4306181330 hasConcept C118487528 @default.
- W4306181330 hasConcept C134018914 @default.
- W4306181330 hasConcept C153180895 @default.
- W4306181330 hasConcept C154945302 @default.
- W4306181330 hasConcept C2779735895 @default.
- W4306181330 hasConcept C2779829184 @default.
- W4306181330 hasConcept C2780248432 @default.
- W4306181330 hasConcept C2780827179 @default.
- W4306181330 hasConcept C41008148 @default.
- W4306181330 hasConcept C555293320 @default.
- W4306181330 hasConcept C71924100 @default.
- W4306181330 hasConcept C81363708 @default.
- W4306181330 hasConcept C89600930 @default.
- W4306181330 hasConceptScore W4306181330C108583219 @default.
- W4306181330 hasConceptScore W4306181330C118487528 @default.
- W4306181330 hasConceptScore W4306181330C134018914 @default.
- W4306181330 hasConceptScore W4306181330C153180895 @default.
- W4306181330 hasConceptScore W4306181330C154945302 @default.
- W4306181330 hasConceptScore W4306181330C2779735895 @default.
- W4306181330 hasConceptScore W4306181330C2779829184 @default.
- W4306181330 hasConceptScore W4306181330C2780248432 @default.
- W4306181330 hasConceptScore W4306181330C2780827179 @default.
- W4306181330 hasConceptScore W4306181330C41008148 @default.
- W4306181330 hasConceptScore W4306181330C555293320 @default.
- W4306181330 hasConceptScore W4306181330C71924100 @default.
- W4306181330 hasConceptScore W4306181330C81363708 @default.
- W4306181330 hasConceptScore W4306181330C89600930 @default.
- W4306181330 hasFunder F4320322120 @default.
- W4306181330 hasLocation W43061813301 @default.
- W4306181330 hasLocation W43061813302 @default.
- W4306181330 hasOpenAccess W4306181330 @default.
- W4306181330 hasPrimaryLocation W43061813301 @default.
- W4306181330 hasRelatedWork W1976426164 @default.
- W4306181330 hasRelatedWork W2461387662 @default.
- W4306181330 hasRelatedWork W2738221750 @default.
- W4306181330 hasRelatedWork W3029563123 @default.
- W4306181330 hasRelatedWork W3102253946 @default.
- W4306181330 hasRelatedWork W3111623965 @default.
- W4306181330 hasRelatedWork W3144574764 @default.
- W4306181330 hasRelatedWork W3156786002 @default.
- W4306181330 hasRelatedWork W4293211451 @default.
- W4306181330 hasRelatedWork W4308191152 @default.
- W4306181330 isParatext "false" @default.
- W4306181330 isRetracted "false" @default.
- W4306181330 workType "article" @default.