Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216019898> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3216019898 abstract "Abstract Airways segmentation is important for research about pulmonary disease but require a large amount of time by trained specialists. We used an openly available software to improve airways segmentations obtained from an artificial intelligence (AI) tool and retrained the tool to get a better performance. Fifteen initial airway segmentations from low-dose chest computed tomography scans were obtained with a 3D-Unet AI tool previously trained on Danish Lung Cancer Screening Trial and Erasmus-MC Sophia datasets. Segmentations were manually corrected in 3D Slicer. The corrected airway segmentations were used to retrain the 3D-Unet. Airway measurements were automatically obtained and included count, airway length and luminal diameter per generation from the segmentations. Correcting segmentations required 2–4 h per scan. Manually corrected segmentations had more branches ( p < 0.001), longer airways ( p < 0.001) and smaller luminal diameters ( p = 0.004) than initial segmentations. Segmentations from retrained 3D-Unets trended towards more branches and longer airways compared to the initial segmentations. The largest changes were seen in airways from 6th generation onwards. Manual correction results in significantly improved segmentations and is potentially a useful and time-efficient method to improve the AI tool performance on a specific hospital or research dataset." @default.
- W3216019898 created "2021-12-06" @default.
- W3216019898 creator A5012401657 @default.
- W3216019898 creator A5016115586 @default.
- W3216019898 creator A5023677285 @default.
- W3216019898 creator A5026407342 @default.
- W3216019898 creator A5049689568 @default.
- W3216019898 creator A5079802068 @default.
- W3216019898 date "2021-11-29" @default.
- W3216019898 modified "2023-10-16" @default.
- W3216019898 title "Creating a training set for artificial intelligence from initial segmentations of airways" @default.
- W3216019898 cites W1988977196 @default.
- W3216019898 cites W2026616100 @default.
- W3216019898 cites W2045898750 @default.
- W3216019898 cites W2080448710 @default.
- W3216019898 cites W2098374142 @default.
- W3216019898 cites W2119178074 @default.
- W3216019898 cites W2124770695 @default.
- W3216019898 cites W2135069164 @default.
- W3216019898 cites W2614210011 @default.
- W3216019898 cites W2733550378 @default.
- W3216019898 cites W2797313070 @default.
- W3216019898 cites W2800788428 @default.
- W3216019898 cites W2829761145 @default.
- W3216019898 cites W2885818977 @default.
- W3216019898 cites W2896620274 @default.
- W3216019898 cites W2911436281 @default.
- W3216019898 cites W2942249639 @default.
- W3216019898 cites W2985980638 @default.
- W3216019898 cites W2997298847 @default.
- W3216019898 cites W3103145119 @default.
- W3216019898 cites W3123135960 @default.
- W3216019898 cites W3190742591 @default.
- W3216019898 doi "https://doi.org/10.1186/s41747-021-00247-9" @default.
- W3216019898 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34841480" @default.
- W3216019898 hasPublicationYear "2021" @default.
- W3216019898 type Work @default.
- W3216019898 sameAs 3216019898 @default.
- W3216019898 citedByCount "1" @default.
- W3216019898 countsByYear W32160198982023 @default.
- W3216019898 crossrefType "journal-article" @default.
- W3216019898 hasAuthorship W3216019898A5012401657 @default.
- W3216019898 hasAuthorship W3216019898A5016115586 @default.
- W3216019898 hasAuthorship W3216019898A5023677285 @default.
- W3216019898 hasAuthorship W3216019898A5026407342 @default.
- W3216019898 hasAuthorship W3216019898A5049689568 @default.
- W3216019898 hasAuthorship W3216019898A5079802068 @default.
- W3216019898 hasBestOaLocation W32160198981 @default.
- W3216019898 hasConcept C105922876 @default.
- W3216019898 hasConcept C126838900 @default.
- W3216019898 hasConcept C141071460 @default.
- W3216019898 hasConcept C154945302 @default.
- W3216019898 hasConcept C3019007443 @default.
- W3216019898 hasConcept C41008148 @default.
- W3216019898 hasConcept C71924100 @default.
- W3216019898 hasConcept C89600930 @default.
- W3216019898 hasConceptScore W3216019898C105922876 @default.
- W3216019898 hasConceptScore W3216019898C126838900 @default.
- W3216019898 hasConceptScore W3216019898C141071460 @default.
- W3216019898 hasConceptScore W3216019898C154945302 @default.
- W3216019898 hasConceptScore W3216019898C3019007443 @default.
- W3216019898 hasConceptScore W3216019898C41008148 @default.
- W3216019898 hasConceptScore W3216019898C71924100 @default.
- W3216019898 hasConceptScore W3216019898C89600930 @default.
- W3216019898 hasIssue "1" @default.
- W3216019898 hasLocation W32160198981 @default.
- W3216019898 hasLocation W32160198982 @default.
- W3216019898 hasLocation W32160198983 @default.
- W3216019898 hasLocation W32160198984 @default.
- W3216019898 hasLocation W32160198985 @default.
- W3216019898 hasLocation W32160198986 @default.
- W3216019898 hasLocation W32160198987 @default.
- W3216019898 hasLocation W32160198988 @default.
- W3216019898 hasOpenAccess W3216019898 @default.
- W3216019898 hasPrimaryLocation W32160198981 @default.
- W3216019898 hasRelatedWork W2005437358 @default.
- W3216019898 hasRelatedWork W2049214470 @default.
- W3216019898 hasRelatedWork W2138214894 @default.
- W3216019898 hasRelatedWork W2350476764 @default.
- W3216019898 hasRelatedWork W2361006516 @default.
- W3216019898 hasRelatedWork W2954384599 @default.
- W3216019898 hasRelatedWork W4230410841 @default.
- W3216019898 hasRelatedWork W4238599390 @default.
- W3216019898 hasRelatedWork W4295775062 @default.
- W3216019898 hasRelatedWork W4385556756 @default.
- W3216019898 hasVolume "5" @default.
- W3216019898 isParatext "false" @default.
- W3216019898 isRetracted "false" @default.
- W3216019898 magId "3216019898" @default.
- W3216019898 workType "article" @default.