Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317103438> ?p ?o ?g. }
- W4317103438 abstract "Abstract Chest X-rays are the most economically viable diagnostic imaging test for active pulmonary tuberculosis screening despite the high sensitivity and low specificity when interpreted by clinicians or radiologists. Computer aided detection (CAD) algorithms, especially convolution based deep learning architecture, have been proposed to facilitate the automation of radiography imaging modalities. Deep learning algorithms have found success in classifying various abnormalities in lung using chest X-ray. We fine-tuned, validated and tested EfficientNetB4 architecture and utilized the transfer learning methodology for multilabel approach to detect lung zone wise and image wise manifestations of active pulmonary tuberculosis using chest X-ray. We used Area Under Receiver Operating Characteristic (AUC), sensitivity and specificity along with 95% confidence interval as model evaluation metrics. We also utilized the visualisation capabilities of convolutional neural networks (CNN), Gradient-weighted Class Activation Mapping (Grad-CAM) as post-hoc attention method to investigate the model and visualisation of Tuberculosis abnormalities and discuss them from radiological perspectives. EfficientNetB4 trained network achieved remarkable AUC, sensitivity and specificity of various pulmonary tuberculosis manifestations in intramural test set and external test set from different geographical region. The grad-CAM visualisations and their ability to localize the abnormalities can aid the clinicians at primary care settings for screening and triaging of tuberculosis where resources are constrained or overburdened." @default.
- W4317103438 created "2023-01-18" @default.
- W4317103438 creator A5009152399 @default.
- W4317103438 creator A5021424913 @default.
- W4317103438 creator A5034187438 @default.
- W4317103438 creator A5058540198 @default.
- W4317103438 creator A5085944905 @default.
- W4317103438 date "2023-01-17" @default.
- W4317103438 modified "2023-10-01" @default.
- W4317103438 title "Deep learning classification of active tuberculosis lung zones wise manifestations using chest X-rays: a multi label approach" @default.
- W4317103438 cites W1964632475 @default.
- W4317103438 cites W2020018978 @default.
- W4317103438 cites W2102150307 @default.
- W4317103438 cites W2132710686 @default.
- W4317103438 cites W2133772334 @default.
- W4317103438 cites W2134649744 @default.
- W4317103438 cites W2146078900 @default.
- W4317103438 cites W2157372022 @default.
- W4317103438 cites W2164777277 @default.
- W4317103438 cites W2334763311 @default.
- W4317103438 cites W2342469653 @default.
- W4317103438 cites W2770511975 @default.
- W4317103438 cites W2793357426 @default.
- W4317103438 cites W2810767764 @default.
- W4317103438 cites W2895344120 @default.
- W4317103438 cites W2898891934 @default.
- W4317103438 cites W2939788146 @default.
- W4317103438 cites W2940692219 @default.
- W4317103438 cites W2956897601 @default.
- W4317103438 cites W2962708065 @default.
- W4317103438 cites W2963942157 @default.
- W4317103438 cites W2999518791 @default.
- W4317103438 cites W3025404316 @default.
- W4317103438 cites W3084346490 @default.
- W4317103438 cites W3092048782 @default.
- W4317103438 cites W3101156210 @default.
- W4317103438 cites W3156331990 @default.
- W4317103438 cites W3195562651 @default.
- W4317103438 cites W3206951384 @default.
- W4317103438 cites W4224249127 @default.
- W4317103438 cites W4232097126 @default.
- W4317103438 doi "https://doi.org/10.1038/s41598-023-28079-0" @default.
- W4317103438 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36650270" @default.
- W4317103438 hasPublicationYear "2023" @default.
- W4317103438 type Work @default.
- W4317103438 citedByCount "1" @default.
- W4317103438 countsByYear W43171034382023 @default.
- W4317103438 crossrefType "journal-article" @default.
- W4317103438 hasAuthorship W4317103438A5009152399 @default.
- W4317103438 hasAuthorship W4317103438A5021424913 @default.
- W4317103438 hasAuthorship W4317103438A5034187438 @default.
- W4317103438 hasAuthorship W4317103438A5058540198 @default.
- W4317103438 hasAuthorship W4317103438A5085944905 @default.
- W4317103438 hasBestOaLocation W43171034381 @default.
- W4317103438 hasConcept C108583219 @default.
- W4317103438 hasConcept C119857082 @default.
- W4317103438 hasConcept C126838900 @default.
- W4317103438 hasConcept C127413603 @default.
- W4317103438 hasConcept C142724271 @default.
- W4317103438 hasConcept C150899416 @default.
- W4317103438 hasConcept C154945302 @default.
- W4317103438 hasConcept C169903167 @default.
- W4317103438 hasConcept C177264268 @default.
- W4317103438 hasConcept C199360897 @default.
- W4317103438 hasConcept C21200559 @default.
- W4317103438 hasConcept C24326235 @default.
- W4317103438 hasConcept C2779549770 @default.
- W4317103438 hasConcept C2781069245 @default.
- W4317103438 hasConcept C2908628106 @default.
- W4317103438 hasConcept C36454342 @default.
- W4317103438 hasConcept C41008148 @default.
- W4317103438 hasConcept C58471807 @default.
- W4317103438 hasConcept C71924100 @default.
- W4317103438 hasConcept C81363708 @default.
- W4317103438 hasConceptScore W4317103438C108583219 @default.
- W4317103438 hasConceptScore W4317103438C119857082 @default.
- W4317103438 hasConceptScore W4317103438C126838900 @default.
- W4317103438 hasConceptScore W4317103438C127413603 @default.
- W4317103438 hasConceptScore W4317103438C142724271 @default.
- W4317103438 hasConceptScore W4317103438C150899416 @default.
- W4317103438 hasConceptScore W4317103438C154945302 @default.
- W4317103438 hasConceptScore W4317103438C169903167 @default.
- W4317103438 hasConceptScore W4317103438C177264268 @default.
- W4317103438 hasConceptScore W4317103438C199360897 @default.
- W4317103438 hasConceptScore W4317103438C21200559 @default.
- W4317103438 hasConceptScore W4317103438C24326235 @default.
- W4317103438 hasConceptScore W4317103438C2779549770 @default.
- W4317103438 hasConceptScore W4317103438C2781069245 @default.
- W4317103438 hasConceptScore W4317103438C2908628106 @default.
- W4317103438 hasConceptScore W4317103438C36454342 @default.
- W4317103438 hasConceptScore W4317103438C41008148 @default.
- W4317103438 hasConceptScore W4317103438C58471807 @default.
- W4317103438 hasConceptScore W4317103438C71924100 @default.
- W4317103438 hasConceptScore W4317103438C81363708 @default.
- W4317103438 hasIssue "1" @default.
- W4317103438 hasLocation W43171034381 @default.
- W4317103438 hasLocation W43171034382 @default.
- W4317103438 hasLocation W43171034383 @default.
- W4317103438 hasOpenAccess W4317103438 @default.
- W4317103438 hasPrimaryLocation W43171034381 @default.