FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3183988814> ?p ?o ?g. }

• W3183988814 endingPage "736" @default.
• W3183988814 startingPage "725" @default.
• W3183988814 abstract "The purpose of this study was to build a deep learning model to derive labels from neuroradiology reports and assign these to the corresponding examinations, overcoming a bottleneck to computer vision model development.Reference-standard labels were generated by a team of neuroradiologists for model training and evaluation. Three thousand examinations were labelled for the presence or absence of any abnormality by manually scrutinising the corresponding radiology reports ('reference-standard report labels'); a subset of these examinations (n = 250) were assigned 'reference-standard image labels' by interrogating the actual images. Separately, 2000 reports were labelled for the presence or absence of 7 specialised categories of abnormality (acute stroke, mass, atrophy, vascular abnormality, small vessel disease, white matter inflammation, encephalomalacia), with a subset of these examinations (n = 700) also assigned reference-standard image labels. A deep learning model was trained using labelled reports and validated in two ways: comparing predicted labels to (i) reference-standard report labels and (ii) reference-standard image labels. The area under the receiver operating characteristic curve (AUC-ROC) was used to quantify model performance. Accuracy, sensitivity, specificity, and F1 score were also calculated.Accurate classification (AUC-ROC > 0.95) was achieved for all categories when tested against reference-standard report labels. A drop in performance (ΔAUC-ROC > 0.02) was seen for three categories (atrophy, encephalomalacia, vascular) when tested against reference-standard image labels, highlighting discrepancies in the original reports. Once trained, the model assigned labels to 121,556 examinations in under 30 min.Our model accurately classifies head MRI examinations, enabling automated dataset labelling for downstream computer vision applications.• Deep learning is poised to revolutionise image recognition tasks in radiology; however, a barrier to clinical adoption is the difficulty of obtaining large labelled datasets for model training. • We demonstrate a deep learning model which can derive labels from neuroradiology reports and assign these to the corresponding examinations at scale, facilitating the development of downstream computer vision models. • We rigorously tested our model by comparing labels predicted on the basis of neuroradiology reports with two sets of reference-standard labels: (1) labels derived by manually scrutinising each radiology report and (2) labels derived by interrogating the actual images." @default.
• W3183988814 created "2021-08-02" @default.
• W3183988814 creator A5003607819 @default.
• W3183988814 creator A5022776086 @default.
• W3183988814 creator A5024246068 @default.
• W3183988814 creator A5025298980 @default.
• W3183988814 creator A5026258202 @default.
• W3183988814 creator A5028777364 @default.
• W3183988814 creator A5030295878 @default.
• W3183988814 creator A5030480524 @default.
• W3183988814 creator A5041460109 @default.
• W3183988814 creator A5069205174 @default.
• W3183988814 creator A5079179983 @default.
• W3183988814 creator A5079638413 @default.
• W3183988814 creator A5081743946 @default.
• W3183988814 creator A5082106258 @default.
• W3183988814 creator A5083184889 @default.
• W3183988814 creator A5086012668 @default.
• W3183988814 date "2021-07-20" @default.
• W3183988814 modified "2023-10-01" @default.
• W3183988814 title "Deep learning to automate the labelling of head MRI datasets for computer vision applications" @default.
• W3183988814 cites W1975879668 @default.
• W3183988814 cites W2074459654 @default.
• W3183988814 cites W2091931051 @default.
• W3183988814 cites W2108598243 @default.
• W3183988814 cites W2250539671 @default.
• W3183988814 cites W2328176404 @default.
• W3183988814 cites W2549775784 @default.
• W3183988814 cites W2768567289 @default.
• W3183988814 cites W2785863263 @default.
• W3183988814 cites W2794518994 @default.
• W3183988814 cites W2796108585 @default.
• W3183988814 cites W2803760365 @default.
• W3183988814 cites W2911410812 @default.
• W3183988814 cites W2911489562 @default.
• W3183988814 cites W2912664121 @default.
• W3183988814 cites W2918369972 @default.
• W3183988814 cites W2919356958 @default.
• W3183988814 cites W2936894186 @default.
• W3183988814 cites W2963026768 @default.
• W3183988814 cites W2963563735 @default.
• W3183988814 cites W2963716420 @default.
• W3183988814 cites W2980708516 @default.
• W3183988814 cites W3036586801 @default.
• W3183988814 cites W3090269612 @default.
• W3183988814 cites W3094771178 @default.
• W3183988814 cites W3103694015 @default.
• W3183988814 cites W3156669901 @default.
• W3183988814 cites W4238634189 @default.
• W3183988814 cites W4288076040 @default.
• W3183988814 doi "https://doi.org/10.1007/s00330-021-08132-0" @default.
• W3183988814 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34286375" @default.
• W3183988814 hasPublicationYear "2021" @default.
• W3183988814 type Work @default.
• W3183988814 sameAs 3183988814 @default.
• W3183988814 citedByCount "16" @default.
• W3183988814 countsByYear W31839888142022 @default.
• W3183988814 countsByYear W31839888142023 @default.
• W3183988814 crossrefType "journal-article" @default.
• W3183988814 hasAuthorship W3183988814A5003607819 @default.
• W3183988814 hasAuthorship W3183988814A5022776086 @default.
• W3183988814 hasAuthorship W3183988814A5024246068 @default.
• W3183988814 hasAuthorship W3183988814A5025298980 @default.
• W3183988814 hasAuthorship W3183988814A5026258202 @default.
• W3183988814 hasAuthorship W3183988814A5028777364 @default.
• W3183988814 hasAuthorship W3183988814A5030295878 @default.
• W3183988814 hasAuthorship W3183988814A5030480524 @default.
• W3183988814 hasAuthorship W3183988814A5041460109 @default.
• W3183988814 hasAuthorship W3183988814A5069205174 @default.
• W3183988814 hasAuthorship W3183988814A5079179983 @default.
• W3183988814 hasAuthorship W3183988814A5079638413 @default.
• W3183988814 hasAuthorship W3183988814A5081743946 @default.
• W3183988814 hasAuthorship W3183988814A5082106258 @default.
• W3183988814 hasAuthorship W3183988814A5083184889 @default.
• W3183988814 hasAuthorship W3183988814A5086012668 @default.
• W3183988814 hasBestOaLocation W31839888141 @default.
• W3183988814 hasConcept C118552586 @default.
• W3183988814 hasConcept C119857082 @default.
• W3183988814 hasConcept C126838900 @default.
• W3183988814 hasConcept C153180895 @default.
• W3183988814 hasConcept C154945302 @default.
• W3183988814 hasConcept C16568411 @default.
• W3183988814 hasConcept C2779889316 @default.
• W3183988814 hasConcept C40993552 @default.
• W3183988814 hasConcept C41008148 @default.
• W3183988814 hasConcept C50965678 @default.
• W3183988814 hasConcept C58471807 @default.
• W3183988814 hasConcept C71924100 @default.
• W3183988814 hasConceptScore W3183988814C118552586 @default.
• W3183988814 hasConceptScore W3183988814C119857082 @default.
• W3183988814 hasConceptScore W3183988814C126838900 @default.
• W3183988814 hasConceptScore W3183988814C153180895 @default.
• W3183988814 hasConceptScore W3183988814C154945302 @default.
• W3183988814 hasConceptScore W3183988814C16568411 @default.
• W3183988814 hasConceptScore W3183988814C2779889316 @default.
• W3183988814 hasConceptScore W3183988814C40993552 @default.
• W3183988814 hasConceptScore W3183988814C41008148 @default.
• W3183988814 hasConceptScore W3183988814C50965678 @default.

• next