VEntNet: Hybrid deep convolutional neural network model for automated multi‐class categorization of chest X‐rays. Issue 3 (9th February 2022)

• Record Type: Journal Article
• Authors: Sudarshan, Vidya K.; A. Ramachandra, Reshma; Tan, Nicole Si Min; Ojha, Smit; Tan, Ru San
• Is Part Of: International journal of imaging systems and technology. Volume 32:Issue 3(2022)
• Page Start: 778
• Page End: 797
• Publication Date: 2022-02-09
• Subjects: chest X‐rays -- ChexNet -- CNN -- COVID -- deep neural network -- entropy -- GoogleNet -- pneumonia -- TB -- VGG; Imaging systems -- Periodicals; Image processing -- Periodicals; 621.367
• DOI: 10.1002/ima.22715
• Languages: English
• ISSNs: 0899-9457

Abstract

Abstract: Visual 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.