Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311704385> ?p ?o ?g. }
- W4311704385 endingPage "655" @default.
- W4311704385 startingPage "645" @default.
- W4311704385 abstract "Convolutional neural networks (CNN) for computer-aided diagnosis of polyps are often trained using high-quality still images in a single chromoendoscopy imaging modality with sessile serrated lesions (SSLs) often excluded. This study developed a CNN from videos to classify polyps as adenomatous or nonadenomatous using standard narrow-band imaging (NBI) and NBI-near focus (NBI-NF) and created a publicly accessible polyp video database.We trained a CNN with 16,832 high and moderate quality frames from 229 polyp videos (56 SSLs). It was evaluated with 222 polyp videos (36 SSLs) across two test-sets. Test-set I consists of 14,320 frames (157 polyps, 111 diminutive). Test-set II, which is publicly accessible, 3317 video frames (65 polyps, 41 diminutive), which was benchmarked with three expert and three nonexpert endoscopists.Sensitivity for adenoma characterization was 91.6% in test-set I and 89.7% in test-set II. Specificity was 91.9% and 88.5%. Sensitivity for diminutive polyps was 89.9% and 87.5%; specificity 90.5% and 88.2%. In NBI-NF, sensitivity was 89.4% and 89.5%, with a specificity of 94.7% and 83.3%. In NBI, sensitivity was 85.3% and 91.7%, with a specificity of 87.5% and 90.0%, respectively. The CNN achieved preservation and incorporation of valuable endoscopic innovations (PIVI)-1 and PIVI-2 thresholds for each test-set. In the benchmarking of test-set II, the CNN was significantly more accurate than nonexperts (13.8% difference [95% confidence interval 3.2-23.6], P = 0.01) with no significant difference with experts.A single CNN can differentiate adenomas from SSLs and hyperplastic polyps in both NBI and NBI-NF. A publicly accessible NBI polyp video database was created and benchmarked." @default.
- W4311704385 created "2022-12-28" @default.
- W4311704385 creator A5001648753 @default.
- W4311704385 creator A5006791469 @default.
- W4311704385 creator A5006902389 @default.
- W4311704385 creator A5014271824 @default.
- W4311704385 creator A5017724461 @default.
- W4311704385 creator A5035167757 @default.
- W4311704385 creator A5042690842 @default.
- W4311704385 creator A5043606018 @default.
- W4311704385 creator A5051955250 @default.
- W4311704385 creator A5056678728 @default.
- W4311704385 creator A5069445465 @default.
- W4311704385 creator A5075497113 @default.
- W4311704385 creator A5077630267 @default.
- W4311704385 creator A5084284002 @default.
- W4311704385 date "2023-01-18" @default.
- W4311704385 modified "2023-10-15" @default.
- W4311704385 title "Polyp characterization using deep learning and a publicly accessible polyp video database" @default.
- W4311704385 cites W2005464795 @default.
- W4311704385 cites W2019397787 @default.
- W4311704385 cites W2055082612 @default.
- W4311704385 cites W2075246611 @default.
- W4311704385 cites W2332757643 @default.
- W4311704385 cites W2468244534 @default.
- W4311704385 cites W2762406675 @default.
- W4311704385 cites W2765527079 @default.
- W4311704385 cites W2922976369 @default.
- W4311704385 cites W2969542839 @default.
- W4311704385 cites W2973140425 @default.
- W4311704385 cites W2981861180 @default.
- W4311704385 cites W2994685072 @default.
- W4311704385 cites W3005263232 @default.
- W4311704385 cites W3008205232 @default.
- W4311704385 cites W3036665420 @default.
- W4311704385 cites W3046240927 @default.
- W4311704385 cites W3085156431 @default.
- W4311704385 cites W3099167474 @default.
- W4311704385 cites W3108718921 @default.
- W4311704385 cites W3115323112 @default.
- W4311704385 cites W3157926016 @default.
- W4311704385 cites W3199270800 @default.
- W4311704385 cites W4223637487 @default.
- W4311704385 cites W4230531790 @default.
- W4311704385 cites W4283751901 @default.
- W4311704385 cites W89341001 @default.
- W4311704385 doi "https://doi.org/10.1111/den.14500" @default.
- W4311704385 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36527309" @default.
- W4311704385 hasPublicationYear "2023" @default.
- W4311704385 type Work @default.
- W4311704385 citedByCount "4" @default.
- W4311704385 countsByYear W43117043852023 @default.
- W4311704385 crossrefType "journal-article" @default.
- W4311704385 hasAuthorship W4311704385A5001648753 @default.
- W4311704385 hasAuthorship W4311704385A5006791469 @default.
- W4311704385 hasAuthorship W4311704385A5006902389 @default.
- W4311704385 hasAuthorship W4311704385A5014271824 @default.
- W4311704385 hasAuthorship W4311704385A5017724461 @default.
- W4311704385 hasAuthorship W4311704385A5035167757 @default.
- W4311704385 hasAuthorship W4311704385A5042690842 @default.
- W4311704385 hasAuthorship W4311704385A5043606018 @default.
- W4311704385 hasAuthorship W4311704385A5051955250 @default.
- W4311704385 hasAuthorship W4311704385A5056678728 @default.
- W4311704385 hasAuthorship W4311704385A5069445465 @default.
- W4311704385 hasAuthorship W4311704385A5075497113 @default.
- W4311704385 hasAuthorship W4311704385A5077630267 @default.
- W4311704385 hasAuthorship W4311704385A5084284002 @default.
- W4311704385 hasBestOaLocation W43117043851 @default.
- W4311704385 hasConcept C108583219 @default.
- W4311704385 hasConcept C115961682 @default.
- W4311704385 hasConcept C121608353 @default.
- W4311704385 hasConcept C126322002 @default.
- W4311704385 hasConcept C126838900 @default.
- W4311704385 hasConcept C138885662 @default.
- W4311704385 hasConcept C144133560 @default.
- W4311704385 hasConcept C154945302 @default.
- W4311704385 hasConcept C162853370 @default.
- W4311704385 hasConcept C169903167 @default.
- W4311704385 hasConcept C177264268 @default.
- W4311704385 hasConcept C199360897 @default.
- W4311704385 hasConcept C2776122732 @default.
- W4311704385 hasConcept C2777428134 @default.
- W4311704385 hasConcept C2777490804 @default.
- W4311704385 hasConcept C2778435480 @default.
- W4311704385 hasConcept C2778451229 @default.
- W4311704385 hasConcept C2781399487 @default.
- W4311704385 hasConcept C2908781503 @default.
- W4311704385 hasConcept C41008148 @default.
- W4311704385 hasConcept C41895202 @default.
- W4311704385 hasConcept C526805850 @default.
- W4311704385 hasConcept C55020928 @default.
- W4311704385 hasConcept C71924100 @default.
- W4311704385 hasConcept C81363708 @default.
- W4311704385 hasConcept C86251818 @default.
- W4311704385 hasConceptScore W4311704385C108583219 @default.
- W4311704385 hasConceptScore W4311704385C115961682 @default.
- W4311704385 hasConceptScore W4311704385C121608353 @default.
- W4311704385 hasConceptScore W4311704385C126322002 @default.