FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137100711> ?p ?o ?g. }

• W3137100711 endingPage "6824" @default.
• W3137100711 startingPage "6816" @default.
• W3137100711 abstract "Abstract Objectives To evaluate the performance of a deep convolutional neural network (DCNN) in detecting and classifying distal radius fractures, metal, and cast on radiographs using labels based on radiology reports. The secondary aim was to evaluate the effect of the training set size on the algorithm’s performance. Methods A total of 15,775 frontal and lateral radiographs, corresponding radiology reports, and a ResNet18 DCNN were used. Fracture detection and classification models were developed per view and merged. Incrementally sized subsets served to evaluate effects of the training set size. Two musculoskeletal radiologists set the standard of reference on radiographs (test set A). A subset (B) was rated by three radiology residents. For a per-study-based comparison with the radiology residents, the results of the best models were merged. Statistics used were ROC and AUC, Youden’s J statistic (J), and Spearman’s correlation coefficient (ρ). Results The models’ AUC/J on (A) for metal and cast were 0.99/0.98 and 1.0/1.0. The models’ and residents’ AUC/J on (B) were similar on fracture (0.98/0.91; 0.98/0.92) and multiple fragments (0.85/0.58; 0.91/0.70). Training set size and AUC correlated on metal (ρ = 0.740), cast (ρ = 0.722), fracture (frontal ρ = 0.947, lateral ρ = 0.946), multiple fragments (frontal ρ = 0.856), and fragment displacement (frontal ρ = 0.595). Conclusions The models trained on a DCNN with report-based labels to detect distal radius fractures on radiographs are suitable to aid as a secondary reading tool; models for fracture classification are not ready for clinical use. Bigger training sets lead to better models in all categories except joint affection. Key Points • Detection of metal and cast on radiographs is excellent using AI and labels extracted from radiology reports. • Automatic detection of distal radius fractures on radiographs is feasible and the performance approximates radiology residents. • Automatic classification of the type of distal radius fracture varies in accuracy and is inferior for joint involvement and fragment displacement." @default.
• W3137100711 created "2021-03-29" @default.
• W3137100711 creator A5009234990 @default.
• W3137100711 creator A5013671245 @default.
• W3137100711 creator A5017890380 @default.
• W3137100711 creator A5023329112 @default.
• W3137100711 creator A5024383233 @default.
• W3137100711 creator A5030684014 @default.
• W3137100711 creator A5052632983 @default.
• W3137100711 creator A5054454439 @default.
• W3137100711 creator A5071907246 @default.
• W3137100711 date "2021-03-19" @default.
• W3137100711 modified "2023-10-16" @default.
• W3137100711 title "AI-based detection and classification of distal radius fractures using low-effort data labeling: evaluation of applicability and effect of training set size" @default.
• W3137100711 cites W1975176386 @default.
• W3137100711 cites W2125805655 @default.
• W3137100711 cites W2126122458 @default.
• W3137100711 cites W2164777277 @default.
• W3137100711 cites W2517568948 @default.
• W3137100711 cites W2733840449 @default.
• W3137100711 cites W2776581140 @default.
• W3137100711 cites W2777366205 @default.
• W3137100711 cites W2793251588 @default.
• W3137100711 cites W2897228760 @default.
• W3137100711 cites W2912558669 @default.
• W3137100711 cites W2934730619 @default.
• W3137100711 cites W2935090763 @default.
• W3137100711 cites W2940354300 @default.
• W3137100711 cites W2948117846 @default.
• W3137100711 cites W2948653696 @default.
• W3137100711 cites W2988912012 @default.
• W3137100711 cites W2989916101 @default.
• W3137100711 cites W2990286494 @default.
• W3137100711 cites W3011921115 @default.
• W3137100711 cites W3013902712 @default.
• W3137100711 doi "https://doi.org/10.1007/s00330-021-07811-2" @default.
• W3137100711 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8379111" @default.
• W3137100711 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33742228" @default.
• W3137100711 hasPublicationYear "2021" @default.
• W3137100711 type Work @default.
• W3137100711 sameAs 3137100711 @default.
• W3137100711 citedByCount "9" @default.
• W3137100711 countsByYear W31371007112021 @default.
• W3137100711 countsByYear W31371007112022 @default.
• W3137100711 countsByYear W31371007112023 @default.
• W3137100711 crossrefType "journal-article" @default.
• W3137100711 hasAuthorship W3137100711A5009234990 @default.
• W3137100711 hasAuthorship W3137100711A5013671245 @default.
• W3137100711 hasAuthorship W3137100711A5017890380 @default.
• W3137100711 hasAuthorship W3137100711A5023329112 @default.
• W3137100711 hasAuthorship W3137100711A5024383233 @default.
• W3137100711 hasAuthorship W3137100711A5030684014 @default.
• W3137100711 hasAuthorship W3137100711A5052632983 @default.
• W3137100711 hasAuthorship W3137100711A5054454439 @default.
• W3137100711 hasAuthorship W3137100711A5071907246 @default.
• W3137100711 hasBestOaLocation W31371007111 @default.
• W3137100711 hasConcept C105795698 @default.
• W3137100711 hasConcept C118552586 @default.
• W3137100711 hasConcept C126838900 @default.
• W3137100711 hasConcept C127413603 @default.
• W3137100711 hasConcept C153180895 @default.
• W3137100711 hasConcept C154945302 @default.
• W3137100711 hasConcept C16568411 @default.
• W3137100711 hasConcept C169903167 @default.
• W3137100711 hasConcept C177264268 @default.
• W3137100711 hasConcept C178635117 @default.
• W3137100711 hasConcept C187320778 @default.
• W3137100711 hasConcept C199360897 @default.
• W3137100711 hasConcept C2779889316 @default.
• W3137100711 hasConcept C2989005 @default.
• W3137100711 hasConcept C33923547 @default.
• W3137100711 hasConcept C36454342 @default.
• W3137100711 hasConcept C38652104 @default.
• W3137100711 hasConcept C41008148 @default.
• W3137100711 hasConcept C43369102 @default.
• W3137100711 hasConcept C513090587 @default.
• W3137100711 hasConcept C58489278 @default.
• W3137100711 hasConcept C71924100 @default.
• W3137100711 hasConcept C81363708 @default.
• W3137100711 hasConcept C89128539 @default.
• W3137100711 hasConceptScore W3137100711C105795698 @default.
• W3137100711 hasConceptScore W3137100711C118552586 @default.
• W3137100711 hasConceptScore W3137100711C126838900 @default.
• W3137100711 hasConceptScore W3137100711C127413603 @default.
• W3137100711 hasConceptScore W3137100711C153180895 @default.
• W3137100711 hasConceptScore W3137100711C154945302 @default.
• W3137100711 hasConceptScore W3137100711C16568411 @default.
• W3137100711 hasConceptScore W3137100711C169903167 @default.
• W3137100711 hasConceptScore W3137100711C177264268 @default.
• W3137100711 hasConceptScore W3137100711C178635117 @default.
• W3137100711 hasConceptScore W3137100711C187320778 @default.
• W3137100711 hasConceptScore W3137100711C199360897 @default.
• W3137100711 hasConceptScore W3137100711C2779889316 @default.
• W3137100711 hasConceptScore W3137100711C2989005 @default.
• W3137100711 hasConceptScore W3137100711C33923547 @default.
• W3137100711 hasConceptScore W3137100711C36454342 @default.
• W3137100711 hasConceptScore W3137100711C38652104 @default.
• W3137100711 hasConceptScore W3137100711C41008148 @default.

• next