FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319938105> ?p ?o ?g. }

• W4319938105 abstract "<sec> <title>BACKGROUND</title> Breast cancer subtyping is a crucial step in determining therapeutic options, but the molecular examination based on immunohistochemical staining is expensive and time-consuming. Deep learning opens up the possibility to predict the subtypes based on the morphological information from hematoxylin and eosin staining, a much cheaper and faster alternative. However, training the predictive model conventionally requires a large number of histology images, which is challenging to collect by a single institute. </sec> <sec> <title>OBJECTIVE</title> We aimed to develop a data-efficient computational pathology platform, 3DHistoNet, which is capable of learning from z-stacked histology images to accurately predict breast cancer subtypes with a small sample size. </sec> <sec> <title>METHODS</title> We retrospectively examined 401 cases of patients with primary breast carcinoma diagnosed between 2018 and 2020 at the Department of Pathology, National Cancer Center, South Korea. Pathology slides of the patients with breast carcinoma were prepared according to the standard protocols. Age, gender, histologic grade, hormone receptor (estrogen receptor [ER], progesterone receptor [PR], and androgen receptor [AR]) status, erb-B2 receptor tyrosine kinase 2 (HER2) status, and Ki-67 index were evaluated by reviewing medical charts and pathological records. </sec> <sec> <title>RESULTS</title> The area under the receiver operating characteristic curve and decision curve were analyzed to evaluate the performance of our 3DHistoNet platform for predicting the ER, PR, AR, HER2, and Ki67 subtype biomarkers with 5-fold cross-validation. We demonstrated that 3DHistoNet can predict all clinically important biomarkers (ER, PR, AR, HER2, and Ki67) with performance exceeding the conventional multiple instance learning models by a considerable margin (area under the receiver operating characteristic curve: 0.75-0.91 vs 0.67-0.8). We further showed that our z-stack histology scanning method can make up for insufficient training data sets without any additional cost incurred. Finally, 3DHistoNet offered an additional capability to generate attention maps that reveal correlations between Ki67 and histomorphological features, which renders the hematoxylin and eosin image in higher fidelity to the pathologist. </sec> <sec> <title>CONCLUSIONS</title> Our stand-alone, data-efficient pathology platform that can both generate z-stacked images and predict key biomarkers is an appealing tool for breast cancer diagnosis. Its development would encourage morphology-based diagnosis, which is faster, cheaper, and less error-prone compared to the protein quantification method based on immunohistochemical staining. </sec>" @default.
• W4319938105 created "2023-02-11" @default.
• W4319938105 creator A5022222926 @default.
• W4319938105 creator A5029925322 @default.
• W4319938105 creator A5040705349 @default.
• W4319938105 creator A5043672172 @default.
• W4319938105 creator A5064603147 @default.
• W4319938105 creator A5080834130 @default.
• W4319938105 date "2023-01-15" @default.
• W4319938105 modified "2023-09-27" @default.
• W4319938105 title "Data-Efficient Computational Pathology Platform for Faster and Cheaper Breast Cancer Subtype Identifications (Preprint)" @default.
• W4319938105 cites W1522355733 @default.
• W4319938105 cites W1916899057 @default.
• W4319938105 cites W1998576236 @default.
• W4319938105 cites W2010399610 @default.
• W4319938105 cites W2020111712 @default.
• W4319938105 cites W2043409879 @default.
• W4319938105 cites W2110119381 @default.
• W4319938105 cites W2194775991 @default.
• W4319938105 cites W2288763477 @default.
• W4319938105 cites W22901720 @default.
• W4319938105 cites W2301358467 @default.
• W4319938105 cites W2789488272 @default.
• W4319938105 cites W2889089723 @default.
• W4319938105 cites W2889520867 @default.
• W4319938105 cites W2926848333 @default.
• W4319938105 cites W2956228567 @default.
• W4319938105 cites W2964047652 @default.
• W4319938105 cites W2978882452 @default.
• W4319938105 cites W2993219936 @default.
• W4319938105 cites W3006138035 @default.
• W4319938105 cites W3035524453 @default.
• W4319938105 cites W3099458507 @default.
• W4319938105 cites W3123599388 @default.
• W4319938105 cites W3128646645 @default.
• W4319938105 cites W3135547872 @default.
• W4319938105 cites W4241664300 @default.
• W4319938105 cites W4253449727 @default.
• W4319938105 doi "https://doi.org/10.2196/preprints.45547" @default.
• W4319938105 hasPublicationYear "2023" @default.
• W4319938105 type Work @default.
• W4319938105 citedByCount "0" @default.
• W4319938105 crossrefType "posted-content" @default.
• W4319938105 hasAuthorship W4319938105A5022222926 @default.
• W4319938105 hasAuthorship W4319938105A5029925322 @default.
• W4319938105 hasAuthorship W4319938105A5040705349 @default.
• W4319938105 hasAuthorship W4319938105A5043672172 @default.
• W4319938105 hasAuthorship W4319938105A5064603147 @default.
• W4319938105 hasAuthorship W4319938105A5080834130 @default.
• W4319938105 hasConcept C121608353 @default.
• W4319938105 hasConcept C125473707 @default.
• W4319938105 hasConcept C126322002 @default.
• W4319938105 hasConcept C142724271 @default.
• W4319938105 hasConcept C143998085 @default.
• W4319938105 hasConcept C199360897 @default.
• W4319938105 hasConcept C204232928 @default.
• W4319938105 hasConcept C2780192828 @default.
• W4319938105 hasConcept C41008148 @default.
• W4319938105 hasConcept C530470458 @default.
• W4319938105 hasConcept C57742111 @default.
• W4319938105 hasConcept C61367390 @default.
• W4319938105 hasConcept C71924100 @default.
• W4319938105 hasConcept C83852419 @default.
• W4319938105 hasConcept C84606932 @default.
• W4319938105 hasConcept C98717036 @default.
• W4319938105 hasConceptScore W4319938105C121608353 @default.
• W4319938105 hasConceptScore W4319938105C125473707 @default.
• W4319938105 hasConceptScore W4319938105C126322002 @default.
• W4319938105 hasConceptScore W4319938105C142724271 @default.
• W4319938105 hasConceptScore W4319938105C143998085 @default.
• W4319938105 hasConceptScore W4319938105C199360897 @default.
• W4319938105 hasConceptScore W4319938105C204232928 @default.
• W4319938105 hasConceptScore W4319938105C2780192828 @default.
• W4319938105 hasConceptScore W4319938105C41008148 @default.
• W4319938105 hasConceptScore W4319938105C530470458 @default.
• W4319938105 hasConceptScore W4319938105C57742111 @default.
• W4319938105 hasConceptScore W4319938105C61367390 @default.
• W4319938105 hasConceptScore W4319938105C71924100 @default.
• W4319938105 hasConceptScore W4319938105C83852419 @default.
• W4319938105 hasConceptScore W4319938105C84606932 @default.
• W4319938105 hasConceptScore W4319938105C98717036 @default.
• W4319938105 hasLocation W43199381051 @default.
• W4319938105 hasOpenAccess W4319938105 @default.
• W4319938105 hasPrimaryLocation W43199381051 @default.
• W4319938105 hasRelatedWork W1970614368 @default.
• W4319938105 hasRelatedWork W2045171626 @default.
• W4319938105 hasRelatedWork W2352033025 @default.
• W4319938105 hasRelatedWork W2357456301 @default.
• W4319938105 hasRelatedWork W2651034595 @default.
• W4319938105 hasRelatedWork W2765336906 @default.
• W4319938105 hasRelatedWork W2894907676 @default.
• W4319938105 hasRelatedWork W3109088106 @default.
• W4319938105 hasRelatedWork W3162236854 @default.
• W4319938105 hasRelatedWork W4378715669 @default.
• W4319938105 isParatext "false" @default.
• W4319938105 isRetracted "false" @default.
• W4319938105 workType "article" @default.