FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3161437282> ?p ?o ?g. }

• W3161437282 endingPage "9619" @default.
• W3161437282 startingPage "9612" @default.
• W3161437282 abstract "To evaluate the performance of deep learning using ResNet50 in differentiation of benign and malignant vertebral fracture on CT.A dataset of 433 patients confirmed with 296 malignant and 137 benign fractures was retrospectively selected from our spinal CT image database. A senior radiologist performed visual reading to evaluate six imaging features, and three junior radiologists gave diagnostic prediction. A ROI was placed on the most abnormal vertebrae, and the smallest square bounding box was generated. The input channel into ResNet50 network was 3, including the slice with its two neighboring slices. The diagnostic performance was evaluated using 10-fold cross-validation. After obtaining the malignancy probability from all slices in a patient, the highest probability was assigned to that patient to give the final diagnosis, using the threshold of 0.5.Visual features such as soft tissue mass and bone destruction were highly suggestive of malignancy; the presence of a transverse fracture line was highly suggestive of a benign fracture. The reading by three radiologists with 5, 3, and 1 year of experience achieved an accuracy of 99%, 95.2%, and 92.8%, respectively. In ResNet50 analysis, the per-slice diagnostic sensitivity, specificity, and accuracy were 0.90, 0.79, and 85%. When the slices were combined to ve per-patient diagnosis, the sensitivity, specificity, and accuracy were 0.95, 0.80, and 88%.Deep learning has become an important tool for the detection of fractures on CT. In this study, ResNet50 achieved good accuracy, which can be further improved with more cases and optimized methods for future clinical implementation.• Deep learning using ResNet50 can yield a high accuracy for differential diagnosis of benign and malignant vertebral fracture on CT. • The per-slice diagnostic sensitivity, specificity, and accuracy were 0.90, 0.79, and 85% in deep learning using ResNet50 analysis. • The slices combined with per-patient diagnostic sensitivity, specificity, and accuracy were 0.95, 0.80, and 88% in deep learning using ResNet50 analysis." @default.
• W3161437282 created "2021-05-24" @default.
• W3161437282 creator A5001696978 @default.
• W3161437282 creator A5005274902 @default.
• W3161437282 creator A5013455359 @default.
• W3161437282 creator A5020286464 @default.
• W3161437282 creator A5022802322 @default.
• W3161437282 creator A5060563544 @default.
• W3161437282 creator A5071908962 @default.
• W3161437282 creator A5073876888 @default.
• W3161437282 creator A5076833716 @default.
• W3161437282 creator A5081706932 @default.
• W3161437282 date "2021-05-16" @default.
• W3161437282 modified "2023-10-14" @default.
• W3161437282 title "Differential diagnosis of benign and malignant vertebral fracture on CT using deep learning" @default.
• W3161437282 cites W1728932592 @default.
• W3161437282 cites W1878544704 @default.
• W3161437282 cites W1967647950 @default.
• W3161437282 cites W2015861736 @default.
• W3161437282 cites W2022066625 @default.
• W3161437282 cites W2027900660 @default.
• W3161437282 cites W2076063813 @default.
• W3161437282 cites W2079384303 @default.
• W3161437282 cites W2131801255 @default.
• W3161437282 cites W2290780092 @default.
• W3161437282 cites W2552186187 @default.
• W3161437282 cites W2594760301 @default.
• W3161437282 cites W2617669016 @default.
• W3161437282 cites W2702496545 @default.
• W3161437282 cites W2733840449 @default.
• W3161437282 cites W2776581140 @default.
• W3161437282 cites W2784790358 @default.
• W3161437282 cites W2790565150 @default.
• W3161437282 cites W2793251588 @default.
• W3161437282 cites W2800043213 @default.
• W3161437282 cites W2899835486 @default.
• W3161437282 cites W2900454605 @default.
• W3161437282 cites W2901559346 @default.
• W3161437282 cites W2915041319 @default.
• W3161437282 cites W2934730619 @default.
• W3161437282 cites W2947908846 @default.
• W3161437282 cites W2963521553 @default.
• W3161437282 cites W2999793929 @default.
• W3161437282 cites W3037935067 @default.
• W3161437282 cites W3046053509 @default.
• W3161437282 cites W3082430857 @default.
• W3161437282 cites W3090504844 @default.
• W3161437282 cites W3097781047 @default.
• W3161437282 doi "https://doi.org/10.1007/s00330-021-08014-5" @default.
• W3161437282 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8594282" @default.
• W3161437282 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33993335" @default.
• W3161437282 hasPublicationYear "2021" @default.
• W3161437282 type Work @default.
• W3161437282 sameAs 3161437282 @default.
• W3161437282 citedByCount "19" @default.
• W3161437282 countsByYear W31614372822022 @default.
• W3161437282 countsByYear W31614372822023 @default.
• W3161437282 crossrefType "journal-article" @default.
• W3161437282 hasAuthorship W3161437282A5001696978 @default.
• W3161437282 hasAuthorship W3161437282A5005274902 @default.
• W3161437282 hasAuthorship W3161437282A5013455359 @default.
• W3161437282 hasAuthorship W3161437282A5020286464 @default.
• W3161437282 hasAuthorship W3161437282A5022802322 @default.
• W3161437282 hasAuthorship W3161437282A5060563544 @default.
• W3161437282 hasAuthorship W3161437282A5071908962 @default.
• W3161437282 hasAuthorship W3161437282A5073876888 @default.
• W3161437282 hasAuthorship W3161437282A5076833716 @default.
• W3161437282 hasAuthorship W3161437282A5081706932 @default.
• W3161437282 hasBestOaLocation W31614372822 @default.
• W3161437282 hasConcept C118552586 @default.
• W3161437282 hasConcept C126838900 @default.
• W3161437282 hasConcept C142724271 @default.
• W3161437282 hasConcept C16568411 @default.
• W3161437282 hasConcept C2779399171 @default.
• W3161437282 hasConcept C2779889316 @default.
• W3161437282 hasConcept C2780801072 @default.
• W3161437282 hasConcept C3020132585 @default.
• W3161437282 hasConcept C513090587 @default.
• W3161437282 hasConcept C71924100 @default.
• W3161437282 hasConceptScore W3161437282C118552586 @default.
• W3161437282 hasConceptScore W3161437282C126838900 @default.
• W3161437282 hasConceptScore W3161437282C142724271 @default.
• W3161437282 hasConceptScore W3161437282C16568411 @default.
• W3161437282 hasConceptScore W3161437282C2779399171 @default.
• W3161437282 hasConceptScore W3161437282C2779889316 @default.
• W3161437282 hasConceptScore W3161437282C2780801072 @default.
• W3161437282 hasConceptScore W3161437282C3020132585 @default.
• W3161437282 hasConceptScore W3161437282C513090587 @default.
• W3161437282 hasConceptScore W3161437282C71924100 @default.
• W3161437282 hasFunder F4320321001 @default.
• W3161437282 hasIssue "12" @default.
• W3161437282 hasLocation W31614372821 @default.
• W3161437282 hasLocation W31614372822 @default.
• W3161437282 hasLocation W31614372823 @default.
• W3161437282 hasLocation W31614372824 @default.
• W3161437282 hasOpenAccess W3161437282 @default.
• W3161437282 hasPrimaryLocation W31614372821 @default.
• W3161437282 hasRelatedWork W1976967311 @default.

• next