Matches in SemOpenAlex for { <https://semopenalex.org/work/W3189714949> ?p ?o ?g. }
- W3189714949 abstract "Objectives: In recent years, the scientific community has focused on the development of Computer-Aided Diagnosis (CAD) tools that could improve bone fractures' classification. However, the results of the classification of fractures in subtypes with the proposed datasets were far from optimal. This paper proposes a very recent and outperforming deep learning technique, the Vision Transformer (ViT), in order to improve the fracture classification, by exploiting its self-attention mechanism. Methods: 4207 manually annotated images were used and distributed, by following the AO/OTA classification, in different fracture types, the largest labeled dataset of proximal femur fractures used in literature. The ViT architecture was used and compared with a classic Convolutional Neural Network (CNN) and a multistage architecture composed by successive CNNs in cascade. To demonstrate the reliability of this approach, 1) the attention maps were used to visualize the most relevant areas of the images, 2) the performance of a generic CNN and ViT was also compared through unsupervised learning techniques, and 3) 11 specialists were asked to evaluate and classify 150 proximal femur fractures' images with and without the help of the ViT. Results: The ViT was able to correctly predict 83% of the test images. Precision, recall and F1-score were 0.77 (CI 0.64-0.90), 0.76 (CI 0.62-0.91) and 0.77 (CI 0.64-0.89), respectively. The average specialists' diagnostic improvement was 29%. Conclusions: This paper showed the potential of Transformers in bone fracture classification. For the first time, good results were obtained in sub-fractures with the largest and richest dataset ever." @default.
- W3189714949 created "2021-08-16" @default.
- W3189714949 creator A5010351972 @default.
- W3189714949 creator A5053290964 @default.
- W3189714949 creator A5076127742 @default.
- W3189714949 creator A5090034619 @default.
- W3189714949 creator A5090518218 @default.
- W3189714949 date "2021-08-07" @default.
- W3189714949 modified "2023-09-27" @default.
- W3189714949 title "Vision Transformers for femur fracture classification." @default.
- W3189714949 cites W1502235192 @default.
- W3189714949 cites W1710476689 @default.
- W3189714949 cites W2128986278 @default.
- W3189714949 cites W2141619730 @default.
- W3189714949 cites W2149987707 @default.
- W3189714949 cites W2154461664 @default.
- W3189714949 cites W2183341477 @default.
- W3189714949 cites W2266464013 @default.
- W3189714949 cites W2554140915 @default.
- W3189714949 cites W2618530766 @default.
- W3189714949 cites W2733840449 @default.
- W3189714949 cites W2752566774 @default.
- W3189714949 cites W2776565386 @default.
- W3189714949 cites W2784331504 @default.
- W3189714949 cites W2793251588 @default.
- W3189714949 cites W2796347433 @default.
- W3189714949 cites W2803124023 @default.
- W3189714949 cites W2888499542 @default.
- W3189714949 cites W2895650333 @default.
- W3189714949 cites W2897228760 @default.
- W3189714949 cites W2912322580 @default.
- W3189714949 cites W2919115771 @default.
- W3189714949 cites W2950893734 @default.
- W3189714949 cites W2963341956 @default.
- W3189714949 cites W2963403868 @default.
- W3189714949 cites W2974444957 @default.
- W3189714949 cites W2980088508 @default.
- W3189714949 cites W3007647093 @default.
- W3189714949 cites W3033546813 @default.
- W3189714949 cites W3048464064 @default.
- W3189714949 cites W3094138545 @default.
- W3189714949 cites W3096609285 @default.
- W3189714949 cites W3119786062 @default.
- W3189714949 cites W3148140980 @default.
- W3189714949 cites W3174972748 @default.
- W3189714949 hasPublicationYear "2021" @default.
- W3189714949 type Work @default.
- W3189714949 sameAs 3189714949 @default.
- W3189714949 citedByCount "0" @default.
- W3189714949 crossrefType "posted-content" @default.
- W3189714949 hasAuthorship W3189714949A5010351972 @default.
- W3189714949 hasAuthorship W3189714949A5053290964 @default.
- W3189714949 hasAuthorship W3189714949A5076127742 @default.
- W3189714949 hasAuthorship W3189714949A5090034619 @default.
- W3189714949 hasAuthorship W3189714949A5090518218 @default.
- W3189714949 hasConcept C108583219 @default.
- W3189714949 hasConcept C115961682 @default.
- W3189714949 hasConcept C119599485 @default.
- W3189714949 hasConcept C119857082 @default.
- W3189714949 hasConcept C123657996 @default.
- W3189714949 hasConcept C127413603 @default.
- W3189714949 hasConcept C142362112 @default.
- W3189714949 hasConcept C153180895 @default.
- W3189714949 hasConcept C153349607 @default.
- W3189714949 hasConcept C154945302 @default.
- W3189714949 hasConcept C165801399 @default.
- W3189714949 hasConcept C41008148 @default.
- W3189714949 hasConcept C50644808 @default.
- W3189714949 hasConcept C66322947 @default.
- W3189714949 hasConcept C75294576 @default.
- W3189714949 hasConcept C81363708 @default.
- W3189714949 hasConceptScore W3189714949C108583219 @default.
- W3189714949 hasConceptScore W3189714949C115961682 @default.
- W3189714949 hasConceptScore W3189714949C119599485 @default.
- W3189714949 hasConceptScore W3189714949C119857082 @default.
- W3189714949 hasConceptScore W3189714949C123657996 @default.
- W3189714949 hasConceptScore W3189714949C127413603 @default.
- W3189714949 hasConceptScore W3189714949C142362112 @default.
- W3189714949 hasConceptScore W3189714949C153180895 @default.
- W3189714949 hasConceptScore W3189714949C153349607 @default.
- W3189714949 hasConceptScore W3189714949C154945302 @default.
- W3189714949 hasConceptScore W3189714949C165801399 @default.
- W3189714949 hasConceptScore W3189714949C41008148 @default.
- W3189714949 hasConceptScore W3189714949C50644808 @default.
- W3189714949 hasConceptScore W3189714949C66322947 @default.
- W3189714949 hasConceptScore W3189714949C75294576 @default.
- W3189714949 hasConceptScore W3189714949C81363708 @default.
- W3189714949 hasLocation W31897149491 @default.
- W3189714949 hasOpenAccess W3189714949 @default.
- W3189714949 hasPrimaryLocation W31897149491 @default.
- W3189714949 hasRelatedWork W1854855154 @default.
- W3189714949 hasRelatedWork W2519242446 @default.
- W3189714949 hasRelatedWork W2731187515 @default.
- W3189714949 hasRelatedWork W2883891580 @default.
- W3189714949 hasRelatedWork W2971291634 @default.
- W3189714949 hasRelatedWork W3011115931 @default.
- W3189714949 hasRelatedWork W3016598598 @default.
- W3189714949 hasRelatedWork W3017001025 @default.
- W3189714949 hasRelatedWork W3084024556 @default.
- W3189714949 hasRelatedWork W3092175256 @default.