Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/161997
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSudarshan, Vidya K.en_US
dc.contributor.authorRamachandra, Reshma A.en_US
dc.contributor.authorTan, Nicole Si Minen_US
dc.contributor.authorOjha, Smiten_US
dc.contributor.authorTan, Ru Sanen_US
dc.date.accessioned2022-09-28T07:06:25Z-
dc.date.available2022-09-28T07:06:25Z-
dc.date.issued2022-
dc.identifier.citationSudarshan, V. K., Ramachandra, R. A., Tan, N. S. M., Ojha, S. & Tan, R. S. (2022). VEntNet: hybrid deep convolutional neural network model for automated multi-class categorization of chest X-rays. International Journal of Imaging Systems and Technology, 32(3), 778-797. https://dx.doi.org/10.1002/ima.22715en_US
dc.identifier.issn0899-9457en_US
dc.identifier.urihttps://hdl.handle.net/10356/161997-
dc.description.abstractVisual interpretation of chest X-rays (CXRs) is tedious and prone to error. Significant amount of time is spent by the radiologist in differentiating normal from abnormal CXRs and in identifying the location and type of abnormalities. An assistance tool for automatically classifying normal and different types of abnormal CXRs can facilitate the diagnosis and potentially save time costs. In this paper, a novel hybrid model having concatenation of Visual Geometry Group (VGG19) network and Entropy features as a modified deep convolutional neural network (DCNN) architecture, called VEntNet, is proposed for the automated multi-class categorization of CXR images into normal, coronavirus disease (COVID), tuberculosis (TB), viral pneumonia, and bacterial pneumonia. The VEntNet model implemented consists of deep features extraction from convolutional layers of VGG19 network which are then concatenated with hand-crafted entropy features extracted from CXRs. The concatenated features are then fed to the fully connected (FC) layers for performing multi-class categorization using Softmax activation function. The performance of proposed VEntNet model is compared with other DCNNs with and without the hybrid approach for categorization of closely related lung pathologies and normal CXR images. Our proposed VEntNet achieved accuracies of 98.78% and 90.96%, respectively, for four and five-class classification of CXRs. Thus, it is demonstrated that among the different DCNNs, our VEntNet outperformed in four-class CXR categorization tasks. The proposed model can potentially save time by facilitating the screening of CXRs to identify those with abnormalities present as well as to categorize the abnormalities.en_US
dc.language.isoenen_US
dc.relation.ispartofInternational Journal of Imaging Systems and Technologyen_US
dc.rights© 2022 Wiley Periodicals LLC. All rights reserved.en_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleVEntNet: hybrid deep convolutional neural network model for automated multi-class categorization of chest X-raysen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.contributor.schoolSchool of Physical and Mathematical Sciencesen_US
dc.contributor.organizationCTX7095 Analytics, Singaporeen_US
dc.identifier.doi10.1002/ima.22715-
dc.identifier.scopus2-s2.0-85124530593-
dc.identifier.issue3en_US
dc.identifier.volume32en_US
dc.identifier.spage778en_US
dc.identifier.epage797en_US
dc.subject.keywordsChest X-Raysen_US
dc.subject.keywordsDeep Neural Networken_US
item.fulltextNo Fulltext-
item.grantfulltextnone-
Appears in Collections:SCSE Journal Articles
SPMS Journal Articles

SCOPUSTM   
Citations 50

1
Updated on Mar 26, 2024

Page view(s)

123
Updated on Mar 28, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.