Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294218415> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4294218415 endingPage "12" @default.
- W4294218415 startingPage "9" @default.
- W4294218415 abstract "Abstract Ewing sarcomas are malignant neoplasm entities typically found in children and adolescents. Early detection is crucial for therapy and prognosis. Due to the low incidence the general experience as well as according data is limited. Novel support tools for diagnosis, such as deep learning models for image interpretation, are required. While acquiring sufficient data is a common obstacle in medicine, several techniques to tackle small data sets have emerged. The general necessity of large data sets in addition to a rare disease lead to the question whether transfer learning can solve the issue of limited data and subsequently support tasks such as distinguishing Ewing sarcoma from its main differential diagnosis (acute osteomyelitis) in paediatric radiographs. 42,608 unstructured radiographs from our musculoskeletal tumour centre were retrieved from the PACS. The images were clustered with a DeepCluster, a self-supervised algorithm. 1000 clusters were used for the upstream task (pretraining). Following, the pretrained classification network was applied for the downstream task of differentiating Ewing sarcoma and acute osteomyelitis. An untrained network achieved an accuracy of 81.5%/54.2%, while an ImageNet-pretrained network resulted in 89.6%/70.8% for validation and testing, respectively. Our transfer learning approach surpassed the best result by 4.4%/17.3% percentage points. Transfer learning demonstrated to be a powerful technique to support image interpretation tasks. Even for small data sets, the impact can be significant. However, transfer learning is not a final solution to small data sets. To achieve clinically relevant results, a structured and systematic data acquisition is of paramount importance." @default.
- W4294218415 created "2022-09-02" @default.
- W4294218415 creator A5006461848 @default.
- W4294218415 creator A5013780961 @default.
- W4294218415 creator A5027797559 @default.
- W4294218415 creator A5034374631 @default.
- W4294218415 creator A5072566909 @default.
- W4294218415 creator A5075307158 @default.
- W4294218415 creator A5078636607 @default.
- W4294218415 creator A5085146268 @default.
- W4294218415 creator A5091381502 @default.
- W4294218415 date "2022-08-01" @default.
- W4294218415 modified "2023-09-26" @default.
- W4294218415 title "From Self-supervised Learning to Transfer Learning with Musculoskeletal Radiographs" @default.
- W4294218415 doi "https://doi.org/10.1515/cdbme-2022-1003" @default.
- W4294218415 hasPublicationYear "2022" @default.
- W4294218415 type Work @default.
- W4294218415 citedByCount "0" @default.
- W4294218415 crossrefType "journal-article" @default.
- W4294218415 hasAuthorship W4294218415A5006461848 @default.
- W4294218415 hasAuthorship W4294218415A5013780961 @default.
- W4294218415 hasAuthorship W4294218415A5027797559 @default.
- W4294218415 hasAuthorship W4294218415A5034374631 @default.
- W4294218415 hasAuthorship W4294218415A5072566909 @default.
- W4294218415 hasAuthorship W4294218415A5075307158 @default.
- W4294218415 hasAuthorship W4294218415A5078636607 @default.
- W4294218415 hasAuthorship W4294218415A5085146268 @default.
- W4294218415 hasAuthorship W4294218415A5091381502 @default.
- W4294218415 hasBestOaLocation W42942184151 @default.
- W4294218415 hasConcept C108583219 @default.
- W4294218415 hasConcept C119857082 @default.
- W4294218415 hasConcept C126838900 @default.
- W4294218415 hasConcept C142724271 @default.
- W4294218415 hasConcept C150899416 @default.
- W4294218415 hasConcept C153180895 @default.
- W4294218415 hasConcept C154945302 @default.
- W4294218415 hasConcept C162324750 @default.
- W4294218415 hasConcept C187736073 @default.
- W4294218415 hasConcept C2778256501 @default.
- W4294218415 hasConcept C2780451532 @default.
- W4294218415 hasConcept C36454342 @default.
- W4294218415 hasConcept C41008148 @default.
- W4294218415 hasConcept C71924100 @default.
- W4294218415 hasConceptScore W4294218415C108583219 @default.
- W4294218415 hasConceptScore W4294218415C119857082 @default.
- W4294218415 hasConceptScore W4294218415C126838900 @default.
- W4294218415 hasConceptScore W4294218415C142724271 @default.
- W4294218415 hasConceptScore W4294218415C150899416 @default.
- W4294218415 hasConceptScore W4294218415C153180895 @default.
- W4294218415 hasConceptScore W4294218415C154945302 @default.
- W4294218415 hasConceptScore W4294218415C162324750 @default.
- W4294218415 hasConceptScore W4294218415C187736073 @default.
- W4294218415 hasConceptScore W4294218415C2778256501 @default.
- W4294218415 hasConceptScore W4294218415C2780451532 @default.
- W4294218415 hasConceptScore W4294218415C36454342 @default.
- W4294218415 hasConceptScore W4294218415C41008148 @default.
- W4294218415 hasConceptScore W4294218415C71924100 @default.
- W4294218415 hasIssue "2" @default.
- W4294218415 hasLocation W42942184151 @default.
- W4294218415 hasOpenAccess W4294218415 @default.
- W4294218415 hasPrimaryLocation W42942184151 @default.
- W4294218415 hasRelatedWork W2889705046 @default.
- W4294218415 hasRelatedWork W2960456850 @default.
- W4294218415 hasRelatedWork W3192840557 @default.
- W4294218415 hasRelatedWork W4223943233 @default.
- W4294218415 hasRelatedWork W4312200629 @default.
- W4294218415 hasRelatedWork W4317565044 @default.
- W4294218415 hasRelatedWork W4360585206 @default.
- W4294218415 hasRelatedWork W4380075502 @default.
- W4294218415 hasRelatedWork W4382286161 @default.
- W4294218415 hasRelatedWork W4386213806 @default.
- W4294218415 hasVolume "8" @default.
- W4294218415 isParatext "false" @default.
- W4294218415 isRetracted "false" @default.
- W4294218415 workType "article" @default.