Romanian Journal of Information Science and Technology (ROMJIST)

An open – access publication

  |  HOME  |   GENERAL INFORMATION  |   ROMJIST ON-LINE  |  KEY INFORMATION FOR AUTHORS  |   COMMITTEES  |  

ROMJIST is a publication of Romanian Academy,
Section for Information Science and Technology

Editor – in – Chief:
Radu-Emil Precup

Honorary Co-Editors-in-Chief:
Horia-Nicolai Teodorescu
Gheorghe Stefan

Secretariate (office):
Adriana Apostol
Adress for correspondence: romjist@nano-link.net (after 1st of January, 2019)

Founding Editor-in-Chief
(until 10th of February, 2021):
Dan Dascalu

Editing of the printed version: Mihaela Marian (Publishing House of the Romanian Academy, Bucharest)

Technical editor
of the on-line version:
Lucian Milea (University POLITEHNICA of Bucharest)

Sponsor:
• National Institute for R & D
in Microtechnologies
(IMT Bucharest), www.imt.ro

ROMJIST Volume 23, No. S, 2020, pp. S91-S115
 

Krishna Kant SINGH, Manu SIDDHARTHA, Akansha SINGH
Diagnosis of Corona Virus Disease (COVID-19) from Chest X-Ray images using modified XceptionNet

ABSTRACT: A beta coronavirus named Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) was identified recently. This virus caused pneumonia of unknown etiology and is named as Coronavirus Disease 2019 (COVID-19). The disease is novel and hence no medicine to cure the infected patients is available. The only way to control the pandemic is by breaking the chain of the virus. The chain can be broken by massive diagnosis and social distancing. Radiological examinations, included computed tomography is identified as an effective way for disease diagnosis. CT and Chest X-ray images are considered to be an effective way for making clinical decisions. The X-ray facility is available even in the remotest parts and thus X-ray images can be easily acquired for patients. These images can help in prevention of infection, diagnosis and control. In this paper, an initial investigation report on the various aspects of COVID-19 is presented. An automated method for diagnosis of COVID-19 from X-ray images is proposed. The proposed model is based on XceptionNet that uses depth wise separable convolutions. The results obtained from the proposed model have high accuracy. The proposed method is compared with four other state of the art methods. The comparative study reveals that the proposed method performs better than the existing methods. Thus the method can be effectively used for diagnosis of the novel coronavirus.

KEYWORDS: Computer Vision and Pattern Recognition, Artificial Intelligence, Medical Informatics, coronavirus, COVID-19, deep learning, convolution neural network, X-ray images

Read full text (pdf)






  |  HOME  |   GENERAL INFORMATION  |   ROMJIST ON-LINE  |  KEY INFORMATION FOR AUTHORS  |   COMMITTEES  |