Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225516130> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4225516130 abstract "Chest radiography is an effective screening tool for diagnosing pulmonary diseases. In computer-aided diagnosis, extracting the relevant region of interest, i.e., isolating the lung region of each radiography image, can be an essential step towards improved performance in diagnosing pulmonary disorders. Methods: In this work, we propose a deep learning approach to enhance abnormal chest x-ray (CXR) identification performance through segmentations. Our approach is designed in a cascaded manner and incorporates two modules: a deep neural network with criss-cross attention modules (XLSor) for localizing lung region in CXR images and a CXR classification model with a backbone of a self-supervised momentum contrast (MoCo) model pre-trained on large-scale CXR data sets. The proposed pipeline is evaluated on Shenzhen Hospital (SH) data set for the segmentation module, and COVIDx data set for both segmentation and classification modules. Novel statistical analysis is conducted in addition to regular evaluation metrics for the segmentation module. Furthermore, the results of the optimized approach are analyzed with gradient-weighted class activation mapping (Grad-CAM) to investigate the rationale behind the classification decisions and to interpret its choices. Results and Conclusion: Different data sets, methods, and scenarios for each module of the proposed pipeline are examined for designing an optimized approach, which has achieved an accuracy of 0.946 in distinguishing abnormal CXR images (i.e., Pneumonia and COVID-19) from normal ones. Numerical and visual validations suggest that applying automated segmentation as a pre-processing step for classification improves the generalization capability and the performance of the classification models." @default.
- W4225516130 created "2022-05-05" @default.
- W4225516130 creator A5019776867 @default.
- W4225516130 creator A5034161060 @default.
- W4225516130 creator A5049156680 @default.
- W4225516130 creator A5067753991 @default.
- W4225516130 creator A5067875645 @default.
- W4225516130 creator A5074354669 @default.
- W4225516130 creator A5079766012 @default.
- W4225516130 date "2022-02-22" @default.
- W4225516130 modified "2023-09-24" @default.
- W4225516130 title "Improving Classification Model Performance on Chest X-Rays through Lung Segmentation" @default.
- W4225516130 doi "https://doi.org/10.48550/arxiv.2202.10971" @default.
- W4225516130 hasPublicationYear "2022" @default.
- W4225516130 type Work @default.
- W4225516130 citedByCount "0" @default.
- W4225516130 crossrefType "posted-content" @default.
- W4225516130 hasAuthorship W4225516130A5019776867 @default.
- W4225516130 hasAuthorship W4225516130A5034161060 @default.
- W4225516130 hasAuthorship W4225516130A5049156680 @default.
- W4225516130 hasAuthorship W4225516130A5067753991 @default.
- W4225516130 hasAuthorship W4225516130A5067875645 @default.
- W4225516130 hasAuthorship W4225516130A5074354669 @default.
- W4225516130 hasAuthorship W4225516130A5079766012 @default.
- W4225516130 hasBestOaLocation W42255161301 @default.
- W4225516130 hasConcept C124101348 @default.
- W4225516130 hasConcept C126838900 @default.
- W4225516130 hasConcept C134306372 @default.
- W4225516130 hasConcept C153180895 @default.
- W4225516130 hasConcept C154945302 @default.
- W4225516130 hasConcept C177148314 @default.
- W4225516130 hasConcept C177264268 @default.
- W4225516130 hasConcept C199360897 @default.
- W4225516130 hasConcept C2779549770 @default.
- W4225516130 hasConcept C33923547 @default.
- W4225516130 hasConcept C36454342 @default.
- W4225516130 hasConcept C41008148 @default.
- W4225516130 hasConcept C43521106 @default.
- W4225516130 hasConcept C50644808 @default.
- W4225516130 hasConcept C58489278 @default.
- W4225516130 hasConcept C71924100 @default.
- W4225516130 hasConcept C89600930 @default.
- W4225516130 hasConceptScore W4225516130C124101348 @default.
- W4225516130 hasConceptScore W4225516130C126838900 @default.
- W4225516130 hasConceptScore W4225516130C134306372 @default.
- W4225516130 hasConceptScore W4225516130C153180895 @default.
- W4225516130 hasConceptScore W4225516130C154945302 @default.
- W4225516130 hasConceptScore W4225516130C177148314 @default.
- W4225516130 hasConceptScore W4225516130C177264268 @default.
- W4225516130 hasConceptScore W4225516130C199360897 @default.
- W4225516130 hasConceptScore W4225516130C2779549770 @default.
- W4225516130 hasConceptScore W4225516130C33923547 @default.
- W4225516130 hasConceptScore W4225516130C36454342 @default.
- W4225516130 hasConceptScore W4225516130C41008148 @default.
- W4225516130 hasConceptScore W4225516130C43521106 @default.
- W4225516130 hasConceptScore W4225516130C50644808 @default.
- W4225516130 hasConceptScore W4225516130C58489278 @default.
- W4225516130 hasConceptScore W4225516130C71924100 @default.
- W4225516130 hasConceptScore W4225516130C89600930 @default.
- W4225516130 hasLocation W42255161301 @default.
- W4225516130 hasOpenAccess W4225516130 @default.
- W4225516130 hasPrimaryLocation W42255161301 @default.
- W4225516130 hasRelatedWork W1507687735 @default.
- W4225516130 hasRelatedWork W1538250819 @default.
- W4225516130 hasRelatedWork W2132223977 @default.
- W4225516130 hasRelatedWork W2146794146 @default.
- W4225516130 hasRelatedWork W2415731916 @default.
- W4225516130 hasRelatedWork W2883542984 @default.
- W4225516130 hasRelatedWork W3006461809 @default.
- W4225516130 hasRelatedWork W3120171445 @default.
- W4225516130 hasRelatedWork W3213228618 @default.
- W4225516130 hasRelatedWork W4280550577 @default.
- W4225516130 isParatext "false" @default.
- W4225516130 isRetracted "false" @default.
- W4225516130 workType "article" @default.