FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225616443> ?p ?o ?g. }

• W4225616443 endingPage "760" @default.
• W4225616443 startingPage "751" @default.
• W4225616443 abstract "Distinguishing gastric epithelial regeneration change from dysplasia and histopathological diagnosis of dysplasia is subject to interobserver disagreement in endoscopic specimens. In this study, we developed a method to distinguish gastric epithelial regeneration change from dysplasia and further subclassify dysplasia. Meanwhile, optimized the cross-hospital diagnosis using domain adaption (DA). 897 whole slide images (WSIs) of endoscopic specimens from two hospitals were divided into training, internal validation, and external validation cohorts. We developed a deep learning (DL) with DA (DLDA) model to classify gastric dysplasia and epithelial regeneration change into three categories: negative for dysplasia (NFD), low-grade dysplasia (LGD), and high-grade dysplasia (HGD)/intramucosal invasion neoplasia (IMN). The diagnosis based on the DLDA model was compared to 12 pathologists using 100 gastric biopsy cases. In the internal validation cohort, the diagnostic performance measured by the macro-averaged area under the receiver operating characteristic curve (AUC) was 0.97. In the independent external validation cohort, our DLDA models increased macro-averaged AUC from 0.67 to 0.82. In terms of the NFD and HGD cases, our model's diagnostic sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were significantly higher than junior and senior pathologists. Our model's diagnostic sensitivity, NPV, was higher than specialist pathologists. We demonstrated that our DLDA model could distinguish gastric epithelial regeneration change from dysplasia and further subclassify dysplasia in endoscopic specimens. Meanwhile, achieved significant improvement of diagnosis cross-hospital." @default.
• W4225616443 created "2022-05-05" @default.
• W4225616443 creator A5008130258 @default.
• W4225616443 creator A5014406637 @default.
• W4225616443 creator A5014795743 @default.
• W4225616443 creator A5018597430 @default.
• W4225616443 creator A5018863416 @default.
• W4225616443 creator A5021302609 @default.
• W4225616443 creator A5027835055 @default.
• W4225616443 creator A5033671938 @default.
• W4225616443 creator A5033684035 @default.
• W4225616443 creator A5066787724 @default.
• W4225616443 creator A5071773009 @default.
• W4225616443 creator A5073731786 @default.
• W4225616443 creator A5078908635 @default.
• W4225616443 date "2022-04-08" @default.
• W4225616443 modified "2023-10-16" @default.
• W4225616443 title "Deep learning for automatic diagnosis of gastric dysplasia using whole-slide histopathology images in endoscopic specimens" @default.
• W4225616443 cites W2010262066 @default.
• W4225616443 cites W2069367602 @default.
• W4225616443 cites W2080974312 @default.
• W4225616443 cites W2099049373 @default.
• W4225616443 cites W2208423085 @default.
• W4225616443 cites W2620689942 @default.
• W4225616443 cites W2759004613 @default.
• W4225616443 cites W2889646458 @default.
• W4225616443 cites W2946074429 @default.
• W4225616443 cites W2965481926 @default.
• W4225616443 cites W2969542839 @default.
• W4225616443 cites W2995276890 @default.
• W4225616443 cites W3009535750 @default.
• W4225616443 cites W3012449740 @default.
• W4225616443 cites W3031635948 @default.
• W4225616443 cites W3048755313 @default.
• W4225616443 cites W3080947998 @default.
• W4225616443 cites W3081006013 @default.
• W4225616443 cites W3105771333 @default.
• W4225616443 cites W3136040801 @default.
• W4225616443 cites W3192169136 @default.
• W4225616443 cites W2932966658 @default.
• W4225616443 doi "https://doi.org/10.1007/s10120-022-01294-w" @default.
• W4225616443 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35394573" @default.
• W4225616443 hasPublicationYear "2022" @default.
• W4225616443 type Work @default.
• W4225616443 citedByCount "2" @default.
• W4225616443 countsByYear W42256164432022 @default.
• W4225616443 countsByYear W42256164432023 @default.
• W4225616443 crossrefType "journal-article" @default.
• W4225616443 hasAuthorship W4225616443A5008130258 @default.
• W4225616443 hasAuthorship W4225616443A5014406637 @default.
• W4225616443 hasAuthorship W4225616443A5014795743 @default.
• W4225616443 hasAuthorship W4225616443A5018597430 @default.
• W4225616443 hasAuthorship W4225616443A5018863416 @default.
• W4225616443 hasAuthorship W4225616443A5021302609 @default.
• W4225616443 hasAuthorship W4225616443A5027835055 @default.
• W4225616443 hasAuthorship W4225616443A5033671938 @default.
• W4225616443 hasAuthorship W4225616443A5033684035 @default.
• W4225616443 hasAuthorship W4225616443A5066787724 @default.
• W4225616443 hasAuthorship W4225616443A5071773009 @default.
• W4225616443 hasAuthorship W4225616443A5073731786 @default.
• W4225616443 hasAuthorship W4225616443A5078908635 @default.
• W4225616443 hasBestOaLocation W42256164431 @default.
• W4225616443 hasConcept C126322002 @default.
• W4225616443 hasConcept C126838900 @default.
• W4225616443 hasConcept C142724271 @default.
• W4225616443 hasConcept C2775894508 @default.
• W4225616443 hasConcept C2775934546 @default.
• W4225616443 hasConcept C544855455 @default.
• W4225616443 hasConcept C71924100 @default.
• W4225616443 hasConcept C72563966 @default.
• W4225616443 hasConcept C90924648 @default.
• W4225616443 hasConceptScore W4225616443C126322002 @default.
• W4225616443 hasConceptScore W4225616443C126838900 @default.
• W4225616443 hasConceptScore W4225616443C142724271 @default.
• W4225616443 hasConceptScore W4225616443C2775894508 @default.
• W4225616443 hasConceptScore W4225616443C2775934546 @default.
• W4225616443 hasConceptScore W4225616443C544855455 @default.
• W4225616443 hasConceptScore W4225616443C71924100 @default.
• W4225616443 hasConceptScore W4225616443C72563966 @default.
• W4225616443 hasConceptScore W4225616443C90924648 @default.
• W4225616443 hasFunder F4320321001 @default.
• W4225616443 hasIssue "4" @default.
• W4225616443 hasLocation W42256164431 @default.
• W4225616443 hasLocation W42256164432 @default.
• W4225616443 hasOpenAccess W4225616443 @default.
• W4225616443 hasPrimaryLocation W42256164431 @default.
• W4225616443 hasRelatedWork W2115661411 @default.
• W4225616443 hasRelatedWork W2399391471 @default.
• W4225616443 hasRelatedWork W2400254106 @default.
• W4225616443 hasRelatedWork W2970729894 @default.
• W4225616443 hasRelatedWork W3039419443 @default.
• W4225616443 hasRelatedWork W4294739205 @default.
• W4225616443 hasRelatedWork W4308553438 @default.
• W4225616443 hasRelatedWork W4381996710 @default.
• W4225616443 hasRelatedWork W4386772532 @default.
• W4225616443 hasRelatedWork W611855264 @default.
• W4225616443 hasVolume "25" @default.
• W4225616443 isParatext "false" @default.

• next