Matches in SemOpenAlex for { <https://semopenalex.org/work/W4223516823> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4223516823 endingPage "1494" @default.
- W4223516823 startingPage "1488" @default.
- W4223516823 abstract "The aim of this study was to develop automated models for the identification and detection of mandibular fractures in panoramic radiographs using convolutional neural network (CNN) algorithms. A total of 1710 panoramic radiograph images from the years 2016 to 2020, including 855 images containing mandibular fractures, were obtained retrospectively from the regional trauma centre. CNN-based classification models, DenseNet-169 and ResNet-50, were fabricated to identify fractures in the radiographic images. The CNN-based object detection models Faster R-CNN and YOLOv5 were trained to automate the placement of the bounding boxes to detect fractures in the radiographic images. The performance of the models was evaluated on a hold-out test set and also by comparison with residents in oral and maxillofacial surgery and oral and maxillofacial surgeons (experts) on a 100-image subset. The binary classification performance of the models achieved promising results with an area under the receiver operating characteristics curve (AUC), sensitivity, and specificity of 100%. The detection performance of the models achieved an AUC of approximately 90%. When compared with the accuracy of clinician observers, the identification performance of the models outperformed even an expert-level classification. In conclusion, CNN-based models identified mandibular fractures above expert-level performance. It is expected that these models will be used as an aid to improve clinician performance, with aided resident performance approximating that of expert level." @default.
- W4223516823 created "2022-04-15" @default.
- W4223516823 creator A5009182363 @default.
- W4223516823 creator A5015008538 @default.
- W4223516823 creator A5043311612 @default.
- W4223516823 creator A5048000645 @default.
- W4223516823 creator A5074947210 @default.
- W4223516823 creator A5086695880 @default.
- W4223516823 date "2022-11-01" @default.
- W4223516823 modified "2023-10-18" @default.
- W4223516823 title "Assessment of deep convolutional neural network models for mandibular fracture detection in panoramic radiographs" @default.
- W4223516823 cites W1637283730 @default.
- W4223516823 cites W2009383887 @default.
- W4223516823 cites W2028807212 @default.
- W4223516823 cites W2064430284 @default.
- W4223516823 cites W2072858102 @default.
- W4223516823 cites W2082798030 @default.
- W4223516823 cites W2136600904 @default.
- W4223516823 cites W2164777277 @default.
- W4223516823 cites W2166507657 @default.
- W4223516823 cites W2194775991 @default.
- W4223516823 cites W2905810301 @default.
- W4223516823 cites W2908201961 @default.
- W4223516823 cites W2951934944 @default.
- W4223516823 cites W2963037989 @default.
- W4223516823 cites W2963446712 @default.
- W4223516823 cites W3013902712 @default.
- W4223516823 cites W3033972758 @default.
- W4223516823 cites W3037793130 @default.
- W4223516823 cites W3096161501 @default.
- W4223516823 cites W3132434189 @default.
- W4223516823 cites W3137110642 @default.
- W4223516823 cites W3157411665 @default.
- W4223516823 cites W3165812945 @default.
- W4223516823 cites W639708223 @default.
- W4223516823 doi "https://doi.org/10.1016/j.ijom.2022.03.056" @default.
- W4223516823 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35397969" @default.
- W4223516823 hasPublicationYear "2022" @default.
- W4223516823 type Work @default.
- W4223516823 citedByCount "9" @default.
- W4223516823 countsByYear W42235168232022 @default.
- W4223516823 countsByYear W42235168232023 @default.
- W4223516823 crossrefType "journal-article" @default.
- W4223516823 hasAuthorship W4223516823A5009182363 @default.
- W4223516823 hasAuthorship W4223516823A5015008538 @default.
- W4223516823 hasAuthorship W4223516823A5043311612 @default.
- W4223516823 hasAuthorship W4223516823A5048000645 @default.
- W4223516823 hasAuthorship W4223516823A5074947210 @default.
- W4223516823 hasAuthorship W4223516823A5086695880 @default.
- W4223516823 hasConcept C100548800 @default.
- W4223516823 hasConcept C126322002 @default.
- W4223516823 hasConcept C126838900 @default.
- W4223516823 hasConcept C153180895 @default.
- W4223516823 hasConcept C154945302 @default.
- W4223516823 hasConcept C199343813 @default.
- W4223516823 hasConcept C29694066 @default.
- W4223516823 hasConcept C36454342 @default.
- W4223516823 hasConcept C41008148 @default.
- W4223516823 hasConcept C58471807 @default.
- W4223516823 hasConcept C63584917 @default.
- W4223516823 hasConcept C71924100 @default.
- W4223516823 hasConcept C81363708 @default.
- W4223516823 hasConceptScore W4223516823C100548800 @default.
- W4223516823 hasConceptScore W4223516823C126322002 @default.
- W4223516823 hasConceptScore W4223516823C126838900 @default.
- W4223516823 hasConceptScore W4223516823C153180895 @default.
- W4223516823 hasConceptScore W4223516823C154945302 @default.
- W4223516823 hasConceptScore W4223516823C199343813 @default.
- W4223516823 hasConceptScore W4223516823C29694066 @default.
- W4223516823 hasConceptScore W4223516823C36454342 @default.
- W4223516823 hasConceptScore W4223516823C41008148 @default.
- W4223516823 hasConceptScore W4223516823C58471807 @default.
- W4223516823 hasConceptScore W4223516823C63584917 @default.
- W4223516823 hasConceptScore W4223516823C71924100 @default.
- W4223516823 hasConceptScore W4223516823C81363708 @default.
- W4223516823 hasFunder F4320309480 @default.
- W4223516823 hasFunder F4320323439 @default.
- W4223516823 hasIssue "11" @default.
- W4223516823 hasLocation W42235168231 @default.
- W4223516823 hasLocation W42235168232 @default.
- W4223516823 hasOpenAccess W4223516823 @default.
- W4223516823 hasPrimaryLocation W42235168231 @default.
- W4223516823 hasRelatedWork W1503669380 @default.
- W4223516823 hasRelatedWork W1963508548 @default.
- W4223516823 hasRelatedWork W1976981864 @default.
- W4223516823 hasRelatedWork W1991579711 @default.
- W4223516823 hasRelatedWork W2035312924 @default.
- W4223516823 hasRelatedWork W2134926324 @default.
- W4223516823 hasRelatedWork W2326639392 @default.
- W4223516823 hasRelatedWork W2400063961 @default.
- W4223516823 hasRelatedWork W2415131246 @default.
- W4223516823 hasRelatedWork W628926314 @default.
- W4223516823 hasVolume "51" @default.
- W4223516823 isParatext "false" @default.
- W4223516823 isRetracted "false" @default.
- W4223516823 workType "article" @default.