FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306642500> ?p ?o ?g. }

• W4306642500 endingPage "673" @default.
• W4306642500 startingPage "668" @default.
• W4306642500 abstract "Invasive breast carcinomas are routinely tested for HER2 using immunohistochemistry (IHC), with reflex in situ hybridization (ISH) for those scored as equivocal (2+). ISH testing is expensive, time-consuming, and not universally available. In this study, we trained a deep learning algorithm to directly predict HER2 gene amplification status from HER2 2+ IHC slides. Data included 115 consecutive cases of invasive breast carcinoma scored as 2+ by IHC that had follow-up HER2 ISH testing. An external validation data set was created from 36 HER2 IHC slides prepared at an outside institution. All internal IHC slides were digitized and divided into training (80%), and test (20%) sets with 5-fold cross-validation. Small patches (256×256 pixels) were randomly extracted and used to train convolutional neural networks with EfficientNet B0 architecture using a transfer learning approach. Predictions for slides in the test set were made on individual patches, and these predictions were aggregated to generate an overall prediction for each slide. This resulted in a receiver operating characteristic area under the curve of 0.83 with an overall accuracy of 79% (sensitivity=0.70, specificity=0.82). Analysis of external validation slides resulted in a receiver operating characteristic area under the curve of 0.79 with an overall accuracy of 81% (sensitivity=0.50, specificity=0.82). Although the sensitivity and specificity are not high enough to negate the need for reflexive ISH testing entirely, this approach may be useful for triaging cases more likely to be HER2 positive and initiating treatment planning in centers where HER2 ISH testing is not readily available." @default.
• W4306642500 created "2022-10-18" @default.
• W4306642500 creator A5013567823 @default.
• W4306642500 creator A5045729351 @default.
• W4306642500 creator A5048684609 @default.
• W4306642500 creator A5076016510 @default.
• W4306642500 creator A5091135536 @default.
• W4306642500 date "2022-10-17" @default.
• W4306642500 modified "2023-10-03" @default.
• W4306642500 title "Using Deep Learning to Predict Final HER2 Status in Invasive Breast Cancers That are Equivocal (2+) by Immunohistochemistry" @default.
• W4306642500 cites W2604318649 @default.
• W4306642500 cites W2760946358 @default.
• W4306642500 cites W2806074020 @default.
• W4306642500 cites W2906774465 @default.
• W4306642500 cites W2946877213 @default.
• W4306642500 cites W2954996726 @default.
• W4306642500 cites W2956228567 @default.
• W4306642500 cites W3008355217 @default.
• W4306642500 cites W3018308144 @default.
• W4306642500 cites W3044996171 @default.
• W4306642500 cites W3123409890 @default.
• W4306642500 cites W3127832917 @default.
• W4306642500 cites W3136617658 @default.
• W4306642500 cites W3160261825 @default.
• W4306642500 cites W4281640394 @default.
• W4306642500 doi "https://doi.org/10.1097/pai.0000000000001079" @default.
• W4306642500 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36251973" @default.
• W4306642500 hasPublicationYear "2022" @default.
• W4306642500 type Work @default.
• W4306642500 citedByCount "0" @default.
• W4306642500 crossrefType "journal-article" @default.
• W4306642500 hasAuthorship W4306642500A5013567823 @default.
• W4306642500 hasAuthorship W4306642500A5045729351 @default.
• W4306642500 hasAuthorship W4306642500A5048684609 @default.
• W4306642500 hasAuthorship W4306642500A5076016510 @default.
• W4306642500 hasAuthorship W4306642500A5091135536 @default.
• W4306642500 hasConcept C126322002 @default.
• W4306642500 hasConcept C142724271 @default.
• W4306642500 hasConcept C154945302 @default.
• W4306642500 hasConcept C204232928 @default.
• W4306642500 hasConcept C41008148 @default.
• W4306642500 hasConcept C58471807 @default.
• W4306642500 hasConcept C71924100 @default.
• W4306642500 hasConcept C81363708 @default.
• W4306642500 hasConceptScore W4306642500C126322002 @default.
• W4306642500 hasConceptScore W4306642500C142724271 @default.
• W4306642500 hasConceptScore W4306642500C154945302 @default.
• W4306642500 hasConceptScore W4306642500C204232928 @default.
• W4306642500 hasConceptScore W4306642500C41008148 @default.
• W4306642500 hasConceptScore W4306642500C58471807 @default.
• W4306642500 hasConceptScore W4306642500C71924100 @default.
• W4306642500 hasConceptScore W4306642500C81363708 @default.
• W4306642500 hasIssue "10" @default.
• W4306642500 hasLocation W43066425001 @default.
• W4306642500 hasLocation W43066425002 @default.
• W4306642500 hasOpenAccess W4306642500 @default.
• W4306642500 hasPrimaryLocation W43066425001 @default.
• W4306642500 hasRelatedWork W2521062615 @default.
• W4306642500 hasRelatedWork W2735477435 @default.
• W4306642500 hasRelatedWork W2748952813 @default.
• W4306642500 hasRelatedWork W2807436399 @default.
• W4306642500 hasRelatedWork W2899084033 @default.
• W4306642500 hasRelatedWork W3016958897 @default.
• W4306642500 hasRelatedWork W3045739591 @default.
• W4306642500 hasRelatedWork W3181746755 @default.
• W4306642500 hasRelatedWork W4283379348 @default.
• W4306642500 hasRelatedWork W4312417841 @default.
• W4306642500 hasVolume "30" @default.
• W4306642500 isParatext "false" @default.
• W4306642500 isRetracted "false" @default.
• W4306642500 workType "article" @default.