FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3159880465> ?p ?o ?g. }

• W3159880465 endingPage "8785" @default.
• W3159880465 startingPage "8775" @default.
• W3159880465 abstract "To investigate machine learning classifiers and interpretable models using chest CT for detection of COVID-19 and differentiation from other pneumonias, interstitial lung disease (ILD) and normal CTs.Our retrospective multi-institutional study obtained 2446 chest CTs from 16 institutions (including 1161 COVID-19 patients). Training/validation/testing cohorts included 1011/50/100 COVID-19, 388/16/33 ILD, 189/16/33 other pneumonias, and 559/17/34 normal (no pathologies) CTs. A metric-based approach for the classification of COVID-19 used interpretable features, relying on logistic regression and random forests. A deep learning-based classifier differentiated COVID-19 via 3D features extracted directly from CT attenuation and probability distribution of airspace opacities.Most discriminative features of COVID-19 are the percentage of airspace opacity and peripheral and basal predominant opacities, concordant with the typical characterization of COVID-19 in the literature. Unsupervised hierarchical clustering compares feature distribution across COVID-19 and control cohorts. The metrics-based classifier achieved AUC = 0.83, sensitivity = 0.74, and specificity = 0.79 versus respectively 0.93, 0.90, and 0.83 for the DL-based classifier. Most of ambiguity comes from non-COVID-19 pneumonia with manifestations that overlap with COVID-19, as well as mild COVID-19 cases. Non-COVID-19 classification performance is 91% for ILD, 64% for other pneumonias, and 94% for no pathologies, which demonstrates the robustness of our method against different compositions of control groups.Our new method accurately discriminates COVID-19 from other types of pneumonia, ILD, and CTs with no pathologies, using quantitative imaging features derived from chest CT, while balancing interpretability of results and classification performance and, therefore, may be useful to facilitate diagnosis of COVID-19.• Unsupervised clustering reveals the key tomographic features including percent airspace opacity and peripheral and basal opacities most typical of COVID-19 relative to control groups. • COVID-19-positive CTs were compared with COVID-19-negative chest CTs (including a balanced distribution of non-COVID-19 pneumonia, ILD, and no pathologies). Classification accuracies for COVID-19, pneumonia, ILD, and CT scans with no pathologies are respectively 90%, 64%, 91%, and 94%. • Our deep learning (DL)-based classification method demonstrates an AUC of 0.93 (sensitivity 90%, specificity 83%). Machine learning methods applied to quantitative chest CT metrics can therefore improve diagnostic accuracy in suspected COVID-19, particularly in resource-constrained environments." @default.
• W3159880465 created "2021-05-10" @default.
• W3159880465 creator A5011888340 @default.
• W3159880465 creator A5012751147 @default.
• W3159880465 creator A5030805733 @default.
• W3159880465 creator A5031310336 @default.
• W3159880465 creator A5036407830 @default.
• W3159880465 creator A5039584115 @default.
• W3159880465 creator A5055448355 @default.
• W3159880465 creator A5061447121 @default.
• W3159880465 creator A5067850245 @default.
• W3159880465 creator A5070820517 @default.
• W3159880465 creator A5071405883 @default.
• W3159880465 creator A5078301136 @default.
• W3159880465 creator A5085390404 @default.
• W3159880465 creator A5086568941 @default.
• W3159880465 creator A5087446167 @default.
• W3159880465 creator A5087787477 @default.
• W3159880465 creator A5087956379 @default.
• W3159880465 creator A5088627565 @default.
• W3159880465 date "2021-05-01" @default.
• W3159880465 modified "2023-10-18" @default.
• W3159880465 title "Machine learning automatically detects COVID-19 using chest CTs in a large multicenter cohort" @default.
• W3159880465 cites W1678356000 @default.
• W3159880465 cites W3006882119 @default.
• W3159880465 cites W3007764760 @default.
• W3159880465 cites W3008985036 @default.
• W3159880465 cites W3010381061 @default.
• W3159880465 cites W3014561994 @default.
• W3159880465 cites W3016667461 @default.
• W3159880465 cites W3017403618 @default.
• W3159880465 cites W3017451406 @default.
• W3159880465 cites W3019336217 @default.
• W3159880465 cites W3019613751 @default.
• W3159880465 cites W3023666587 @default.
• W3159880465 cites W3025948831 @default.
• W3159880465 cites W3035151116 @default.
• W3159880465 cites W3049757379 @default.
• W3159880465 cites W3088672509 @default.
• W3159880465 cites W3107654509 @default.
• W3159880465 cites W3117287302 @default.
• W3159880465 cites W4230649743 @default.
• W3159880465 doi "https://doi.org/10.1007/s00330-021-07937-3" @default.
• W3159880465 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8088310" @default.
• W3159880465 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33934177" @default.
• W3159880465 hasPublicationYear "2021" @default.
• W3159880465 type Work @default.
• W3159880465 sameAs 3159880465 @default.
• W3159880465 citedByCount "17" @default.
• W3159880465 countsByYear W31598804652020 @default.
• W3159880465 countsByYear W31598804652021 @default.
• W3159880465 countsByYear W31598804652022 @default.
• W3159880465 countsByYear W31598804652023 @default.
• W3159880465 crossrefType "journal-article" @default.
• W3159880465 hasAuthorship W3159880465A5011888340 @default.
• W3159880465 hasAuthorship W3159880465A5012751147 @default.
• W3159880465 hasAuthorship W3159880465A5030805733 @default.
• W3159880465 hasAuthorship W3159880465A5031310336 @default.
• W3159880465 hasAuthorship W3159880465A5036407830 @default.
• W3159880465 hasAuthorship W3159880465A5039584115 @default.
• W3159880465 hasAuthorship W3159880465A5055448355 @default.
• W3159880465 hasAuthorship W3159880465A5061447121 @default.
• W3159880465 hasAuthorship W3159880465A5067850245 @default.
• W3159880465 hasAuthorship W3159880465A5070820517 @default.
• W3159880465 hasAuthorship W3159880465A5071405883 @default.
• W3159880465 hasAuthorship W3159880465A5078301136 @default.
• W3159880465 hasAuthorship W3159880465A5085390404 @default.
• W3159880465 hasAuthorship W3159880465A5086568941 @default.
• W3159880465 hasAuthorship W3159880465A5087446167 @default.
• W3159880465 hasAuthorship W3159880465A5087787477 @default.
• W3159880465 hasAuthorship W3159880465A5087956379 @default.
• W3159880465 hasAuthorship W3159880465A5088627565 @default.
• W3159880465 hasBestOaLocation W31598804651 @default.
• W3159880465 hasConcept C126322002 @default.
• W3159880465 hasConcept C126838900 @default.
• W3159880465 hasConcept C151956035 @default.
• W3159880465 hasConcept C154945302 @default.
• W3159880465 hasConcept C2779134260 @default.
• W3159880465 hasConcept C3008058167 @default.
• W3159880465 hasConcept C41008148 @default.
• W3159880465 hasConcept C524204448 @default.
• W3159880465 hasConcept C71924100 @default.
• W3159880465 hasConcept C97931131 @default.
• W3159880465 hasConceptScore W3159880465C126322002 @default.
• W3159880465 hasConceptScore W3159880465C126838900 @default.
• W3159880465 hasConceptScore W3159880465C151956035 @default.
• W3159880465 hasConceptScore W3159880465C154945302 @default.
• W3159880465 hasConceptScore W3159880465C2779134260 @default.
• W3159880465 hasConceptScore W3159880465C3008058167 @default.
• W3159880465 hasConceptScore W3159880465C41008148 @default.
• W3159880465 hasConceptScore W3159880465C524204448 @default.
• W3159880465 hasConceptScore W3159880465C71924100 @default.
• W3159880465 hasConceptScore W3159880465C97931131 @default.
• W3159880465 hasIssue "11" @default.
• W3159880465 hasLocation W31598804651 @default.
• W3159880465 hasLocation W31598804652 @default.
• W3159880465 hasLocation W31598804653 @default.
• W3159880465 hasLocation W31598804654 @default.

• next