FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308336057> ?p ?o ?g. }

• W4308336057 endingPage "5424" @default.
• W4308336057 startingPage "5424" @default.
• W4308336057 abstract "Poor generalizability is a major barrier to clinical implementation of artificial intelligence in digital pathology. The aim of this study was to test the generalizability of a pretrained deep learning model to a new diagnostic setting and to a small change in surgical indication. A deep learning model for breast cancer metastases detection in sentinel lymph nodes, trained on CAMELYON multicenter data, was used as a base model, and achieved an AUC of 0.969 (95% CI 0.926-0.998) and FROC of 0.838 (95% CI 0.757-0.913) on CAMELYON16 test data. On local sentinel node data, the base model performance dropped to AUC 0.929 (95% CI 0.800-0.998) and FROC 0.744 (95% CI 0.566-0.912). On data with a change in surgical indication (axillary dissections) the base model performance indicated an even larger drop with a FROC of 0.503 (95%CI 0.201-0.911). The model was retrained with addition of local data, resulting in about a 4% increase for both AUC and FROC for sentinel nodes, and an increase of 11% in AUC and 49% in FROC for axillary nodes. Pathologist qualitative evaluation of the retrained model´s output showed no missed positive slides. False positives, false negatives and one previously undetected micro-metastasis were observed. The study highlights the generalization challenge even when using a multicenter trained model, and that a small change in indication can considerably impact the model´s performance." @default.
• W4308336057 created "2022-11-11" @default.
• W4308336057 creator A5001235418 @default.
• W4308336057 creator A5010443108 @default.
• W4308336057 creator A5023440709 @default.
• W4308336057 creator A5037509355 @default.
• W4308336057 creator A5043545263 @default.
• W4308336057 creator A5055697525 @default.
• W4308336057 creator A5076460061 @default.
• W4308336057 creator A5079642617 @default.
• W4308336057 creator A5081003438 @default.
• W4308336057 date "2022-11-03" @default.
• W4308336057 modified "2023-10-06" @default.
• W4308336057 title "Generalization of Deep Learning in Digital Pathology: Experience in Breast Cancer Metastasis Detection" @default.
• W4308336057 cites W1677182931 @default.
• W4308336057 cites W1976435325 @default.
• W4308336057 cites W2082384201 @default.
• W4308336057 cites W2155653793 @default.
• W4308336057 cites W2234404887 @default.
• W4308336057 cites W2533800772 @default.
• W4308336057 cites W2772723798 @default.
• W4308336057 cites W2805886241 @default.
• W4308336057 cites W2889232360 @default.
• W4308336057 cites W2897434820 @default.
• W4308336057 cites W2954996726 @default.
• W4308336057 cites W2963446712 @default.
• W4308336057 cites W2969278648 @default.
• W4308336057 cites W2999399991 @default.
• W4308336057 cites W3009926465 @default.
• W4308336057 cites W3045714119 @default.
• W4308336057 cites W3104995829 @default.
• W4308336057 cites W3106889297 @default.
• W4308336057 cites W3109000640 @default.
• W4308336057 cites W3121997355 @default.
• W4308336057 cites W3128681643 @default.
• W4308336057 cites W3138260478 @default.
• W4308336057 cites W3154494492 @default.
• W4308336057 cites W3160261825 @default.
• W4308336057 cites W3161551147 @default.
• W4308336057 cites W3176923149 @default.
• W4308336057 cites W3192948745 @default.
• W4308336057 cites W4249522930 @default.
• W4308336057 doi "https://doi.org/10.3390/cancers14215424" @default.
• W4308336057 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36358842" @default.
• W4308336057 hasPublicationYear "2022" @default.
• W4308336057 type Work @default.
• W4308336057 citedByCount "1" @default.
• W4308336057 crossrefType "journal-article" @default.
• W4308336057 hasAuthorship W4308336057A5001235418 @default.
• W4308336057 hasAuthorship W4308336057A5010443108 @default.
• W4308336057 hasAuthorship W4308336057A5023440709 @default.
• W4308336057 hasAuthorship W4308336057A5037509355 @default.
• W4308336057 hasAuthorship W4308336057A5043545263 @default.
• W4308336057 hasAuthorship W4308336057A5055697525 @default.
• W4308336057 hasAuthorship W4308336057A5076460061 @default.
• W4308336057 hasAuthorship W4308336057A5079642617 @default.
• W4308336057 hasAuthorship W4308336057A5081003438 @default.
• W4308336057 hasBestOaLocation W43083360571 @default.
• W4308336057 hasConcept C105795698 @default.
• W4308336057 hasConcept C108583219 @default.
• W4308336057 hasConcept C119857082 @default.
• W4308336057 hasConcept C121608353 @default.
• W4308336057 hasConcept C126322002 @default.
• W4308336057 hasConcept C126838900 @default.
• W4308336057 hasConcept C134306372 @default.
• W4308336057 hasConcept C154945302 @default.
• W4308336057 hasConcept C177148314 @default.
• W4308336057 hasConcept C27158222 @default.
• W4308336057 hasConcept C2775934546 @default.
• W4308336057 hasConcept C33923547 @default.
• W4308336057 hasConcept C41008148 @default.
• W4308336057 hasConcept C530470458 @default.
• W4308336057 hasConcept C64869954 @default.
• W4308336057 hasConcept C71924100 @default.
• W4308336057 hasConceptScore W4308336057C105795698 @default.
• W4308336057 hasConceptScore W4308336057C108583219 @default.
• W4308336057 hasConceptScore W4308336057C119857082 @default.
• W4308336057 hasConceptScore W4308336057C121608353 @default.
• W4308336057 hasConceptScore W4308336057C126322002 @default.
• W4308336057 hasConceptScore W4308336057C126838900 @default.
• W4308336057 hasConceptScore W4308336057C134306372 @default.
• W4308336057 hasConceptScore W4308336057C154945302 @default.
• W4308336057 hasConceptScore W4308336057C177148314 @default.
• W4308336057 hasConceptScore W4308336057C27158222 @default.
• W4308336057 hasConceptScore W4308336057C2775934546 @default.
• W4308336057 hasConceptScore W4308336057C33923547 @default.
• W4308336057 hasConceptScore W4308336057C41008148 @default.
• W4308336057 hasConceptScore W4308336057C530470458 @default.
• W4308336057 hasConceptScore W4308336057C64869954 @default.
• W4308336057 hasConceptScore W4308336057C71924100 @default.
• W4308336057 hasFunder F4320321030 @default.
• W4308336057 hasIssue "21" @default.
• W4308336057 hasLocation W43083360571 @default.
• W4308336057 hasLocation W43083360572 @default.
• W4308336057 hasLocation W43083360573 @default.
• W4308336057 hasLocation W43083360574 @default.
• W4308336057 hasLocation W43083360575 @default.
• W4308336057 hasLocation W43083360576 @default.

• next