FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376271489> ?p ?o ?g. }

• W4376271489 endingPage "1721" @default.
• W4376271489 startingPage "1709" @default.
• W4376271489 abstract "To develop an interpretable artificial intelligence algorithm to rule out normal large bowel endoscopic biopsies, saving pathologist resources and helping with early diagnosis.A graph neural network was developed incorporating pathologist domain knowledge to classify 6591 whole-slides images (WSIs) of endoscopic large bowel biopsies from 3291 patients (approximately 54% female, 46% male) as normal or abnormal (non-neoplastic and neoplastic) using clinically driven interpretable features. One UK National Health Service (NHS) site was used for model training and internal validation. External validation was conducted on data from two other NHS sites and one Portuguese site.Model training and internal validation were performed on 5054 WSIs of 2080 patients resulting in an area under the curve-receiver operating characteristic (AUC-ROC) of 0.98 (SD=0.004) and AUC-precision-recall (PR) of 0.98 (SD=0.003). The performance of the model, named Interpretable Gland-Graphs using a Neural Aggregator (IGUANA), was consistent in testing over 1537 WSIs of 1211 patients from three independent external datasets with mean AUC-ROC=0.97 (SD=0.007) and AUC-PR=0.97 (SD=0.005). At a high sensitivity threshold of 99%, the proposed model can reduce the number of normal slides to be reviewed by a pathologist by approximately 55%. IGUANA also provides an explainable output highlighting potential abnormalities in a WSI in the form of a heatmap as well as numerical values associating the model prediction with various histological features.The model achieved consistently high accuracy showing its potential in optimising increasingly scarce pathologist resources. Explainable predictions can guide pathologists in their diagnostic decision-making and help boost their confidence in the algorithm, paving the way for its future clinical adoption." @default.
• W4376271489 created "2023-05-13" @default.
• W4376271489 creator A5001090382 @default.
• W4376271489 creator A5002865675 @default.
• W4376271489 creator A5012686872 @default.
• W4376271489 creator A5013545701 @default.
• W4376271489 creator A5015478898 @default.
• W4376271489 creator A5025430151 @default.
• W4376271489 creator A5027171173 @default.
• W4376271489 creator A5027877769 @default.
• W4376271489 creator A5030706452 @default.
• W4376271489 creator A5034385371 @default.
• W4376271489 creator A5041645982 @default.
• W4376271489 creator A5041778968 @default.
• W4376271489 creator A5043471335 @default.
• W4376271489 creator A5043971666 @default.
• W4376271489 creator A5059185353 @default.
• W4376271489 creator A5062569733 @default.
• W4376271489 creator A5063073209 @default.
• W4376271489 creator A5069179055 @default.
• W4376271489 creator A5081010150 @default.
• W4376271489 creator A5084778782 @default.
• W4376271489 creator A5086173090 @default.
• W4376271489 creator A5087159264 @default.
• W4376271489 creator A5087339636 @default.
• W4376271489 creator A5088677311 @default.
• W4376271489 date "2023-05-12" @default.
• W4376271489 modified "2023-10-18" @default.
• W4376271489 title "Screening of normal endoscopic large bowel biopsies with interpretable graph learning: a retrospective study" @default.
• W4376271489 cites W1512135220 @default.
• W4376271489 cites W1812458631 @default.
• W4376271489 cites W1982694070 @default.
• W4376271489 cites W1984114882 @default.
• W4376271489 cites W2012912643 @default.
• W4376271489 cites W2041854656 @default.
• W4376271489 cites W2126470947 @default.
• W4376271489 cites W2273943878 @default.
• W4376271489 cites W2405087030 @default.
• W4376271489 cites W2554140915 @default.
• W4376271489 cites W2594760301 @default.
• W4376271489 cites W2772723798 @default.
• W4376271489 cites W2794803511 @default.
• W4376271489 cites W2899768131 @default.
• W4376271489 cites W2900872097 @default.
• W4376271489 cites W2905146007 @default.
• W4376271489 cites W2914568698 @default.
• W4376271489 cites W2921763762 @default.
• W4376271489 cites W2956228567 @default.
• W4376271489 cites W2999091210 @default.
• W4376271489 cites W3004016611 @default.
• W4376271489 cites W3019938913 @default.
• W4376271489 cites W3020916919 @default.
• W4376271489 cites W3034203199 @default.
• W4376271489 cites W3045168954 @default.
• W4376271489 cites W3080854745 @default.
• W4376271489 cites W3083804794 @default.
• W4376271489 cites W3095689420 @default.
• W4376271489 cites W3135547872 @default.
• W4376271489 cites W3159302505 @default.
• W4376271489 cites W3175191608 @default.
• W4376271489 cites W3181082054 @default.
• W4376271489 cites W3181414820 @default.
• W4376271489 cites W3205605830 @default.
• W4376271489 cites W3205802794 @default.
• W4376271489 cites W3209367260 @default.
• W4376271489 cites W3213407064 @default.
• W4376271489 cites W3448503 @default.
• W4376271489 cites W4249751009 @default.
• W4376271489 cites W4309477120 @default.
• W4376271489 cites W4320921273 @default.
• W4376271489 doi "https://doi.org/10.1136/gutjnl-2023-329512" @default.
• W4376271489 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37173125" @default.
• W4376271489 hasPublicationYear "2023" @default.
• W4376271489 type Work @default.
• W4376271489 citedByCount "0" @default.
• W4376271489 crossrefType "journal-article" @default.
• W4376271489 hasAuthorship W4376271489A5001090382 @default.
• W4376271489 hasAuthorship W4376271489A5002865675 @default.
• W4376271489 hasAuthorship W4376271489A5012686872 @default.
• W4376271489 hasAuthorship W4376271489A5013545701 @default.
• W4376271489 hasAuthorship W4376271489A5015478898 @default.
• W4376271489 hasAuthorship W4376271489A5025430151 @default.
• W4376271489 hasAuthorship W4376271489A5027171173 @default.
• W4376271489 hasAuthorship W4376271489A5027877769 @default.
• W4376271489 hasAuthorship W4376271489A5030706452 @default.
• W4376271489 hasAuthorship W4376271489A5034385371 @default.
• W4376271489 hasAuthorship W4376271489A5041645982 @default.
• W4376271489 hasAuthorship W4376271489A5041778968 @default.
• W4376271489 hasAuthorship W4376271489A5043471335 @default.
• W4376271489 hasAuthorship W4376271489A5043971666 @default.
• W4376271489 hasAuthorship W4376271489A5059185353 @default.
• W4376271489 hasAuthorship W4376271489A5062569733 @default.
• W4376271489 hasAuthorship W4376271489A5063073209 @default.
• W4376271489 hasAuthorship W4376271489A5069179055 @default.
• W4376271489 hasAuthorship W4376271489A5081010150 @default.
• W4376271489 hasAuthorship W4376271489A5084778782 @default.
• W4376271489 hasAuthorship W4376271489A5086173090 @default.
• W4376271489 hasAuthorship W4376271489A5087159264 @default.

• next