XHDLNet Classification of Virus-Borne Diseases for Chest X-Ray Images Using a Hybrid Deep Learning Approach

XHDLNet Classification of Virus-Borne Diseases for Chest X-Ray Images Using a Hybrid Deep Learning Approach

Srishti Choubey, Snehlata Barde, Abhishek Badholia
Copyright: © 2022 |Pages: 14
DOI: 10.4018/IJSI.311505
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Various forms and symptoms of corona virus have been observed in human body especially in heart, chest and affects the respiratory system. In the initial phase, RT-PCR examination is applied to monitor the target disease, but suffers from low sensitivity and a laborious process. Apart from this, another mechanism for corona virus detection involves the analysis the CT image has become an imperative device for clinical judgment. However, manual investigation of such disease in numerous amounts of images is not the optimal approach. Additionally, recent advancement in artificial intelligence techniques have assisted medical diagnosis to identify the virus in a standard environment. In this work, the potential of such intelligence methods is analyzed and extended by considering the optimal feature extraction capability and proposes a hybrid approach in which three universal architectures namely: Inception V4, DenseNet 201 and Xception have been utilized which not only classify the corona virus disease but may also provide a pathway to apply similar method in other medical diagnosis.
Article Preview
Top

Introduction

Chronic obstructive pulmonary disease (COPD) is one of the leading chest disease and the major reason of worldwide death which caused approximately 3.25 deaths in 2019 (WHO, 2022a). Similarly, the risk of COVID-19 is found more intense in those people who have ill-health state like lung or heart diseases (WHO, 2022b). The early and cautious diagnosis of may reduce the death rate and therefore many lives can be saved. However, identifying the responsible viruses are quite challenging as they have varying structural representation and may change over the period of time. An affected but unidentified virus in lung region examination may lead to the death. Nevertheless, chances of manual mistake may lead to unexpected treatment due to this short duration of investigation. One of the best ways to recognize the affected patient suffered from COVID-19 infection is through the analysis of chest X-ray images. As there are a large number of patients in hospitals, it would be time-consuming and difficult to examine numerous X-ray images, so it can be very useful to utilize an artificial intelligence (AI) approach to accurately perform the recognition automatically. Nowadays medical field is also being facilitated with the advancement of several intelligent techniques, which assists the precise decision making of doctors and physician. In this domain, several image processing and optimization approaches have been applied to understand the different data patterns in several applications (Deepak Kumar Dewangan; Yogesh Rathore, 2011; Bhattacharya and Dewangan, 2015; Bhattacharya, Dewangan and Dewangan, 2018; Pandey, Dewangan and Dewangan, 2018; D. K. Dewangan and Sahu, 2021; Sahu et al., 2021), but their performance has been experimented against the standard conditions. In this direction, recent development in machine and deep learning techniques have leveraged the performance of the AI based systems (A. Ojha, Sahu and Dewangan, 2021; Apoorva Ojha, Sahu and Dewangan, 2021; Deepak Kumar Dewangan and Sahu, 2021c; Dewangan et al., 2021; Pardhi et al., 2021; Banjarey, Sahu and Dewangan, 2022) and (Deepak Kumar Dewangan and Sahu, 2021b, 2021a; Singh et al., 2021; Dewangan, 2022). AI techniques has the prospective to benefit some of the most challenging issues when united with standard for the betterment of our society. Among the recent AI based techniques, deep learning assists to build strong, accessible and operative solutions which can also be implemented to recognize and classify the different viruse types in the lung region. In this proposed approach, a hybrid of modified deep learning models have been employed which not only accurately classify between COVID-19, pneumonia and uninfected images but also directs the implementation of other disease’s classification or detection in the similar domain. The schematic of the proposed approach is illustrated in the Figure 1. The remaining portion of the paper is arranged as follows: Section 2 discusses the relevant studies and their approaches. Section 3 delivers the detailed insights of the proposed method. In Section 4, the performance evaluation of the proposed work has been revealed and compared with the state-of-the-art techniques and final summary of the work has been given in section 5.

Complete Article List

Search this Journal:
Reset
Volume 12: 1 Issue (2024)
Volume 11: 1 Issue (2023)
Volume 10: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 9: 4 Issues (2021)
Volume 8: 4 Issues (2020)
Volume 7: 4 Issues (2019)
Volume 6: 4 Issues (2018)
Volume 5: 4 Issues (2017)
Volume 4: 4 Issues (2016)
Volume 3: 4 Issues (2015)
Volume 2: 4 Issues (2014)
Volume 1: 4 Issues (2013)
View Complete Journal Contents Listing