Analysis of Contrast and Correlation Between Deep Learning Algorithms for Diagnosis of COVID-19 from Lung Ultrasonography

• Published in: ECS transactions Vol. 107; no. 1; pp. 1877 - 1895
• Main Authors: Rajagopal, Sivakumar, Goswami, Radha Debal, Tiwari, Rajat, Sabhapandit, Eshan, Soangra, Rahul
• Format: Journal Article
• Language: English
• Published: The Electrochemical Society, Inc 24.04.2022
• ISSN: 1938-5862; 1938-6737
• DOI: 10.1149/10701.1877ecst

Identification of COVID-19 in patients from chest Computed Tomography (CT) scan has been the most prevalent approach, but it exposes the patient to X-ray radiations and is not a suitable approach for frequent monitoring. Computer analysis of ultrasound pulmonary images is a relatively modern approach that showed promising ways to diagnose pulmonary states that are a profitable and safer alternative to CT scan. Deep learning techniques for computerized study of Lung Ultrasound (LUS) images offer promising opportunities for identifying and diagnosing COVID-19. This paper aims to bring up a Convolution Neural Networking (CNN) model, which accurately predicts the condition of COVID-19 via the output produced lung ultrasound. Three models were developed using various parameters and were tested on the same dataset in order to compare each on standard statistical procedures. The best model achieved an accuracy of 94.67%, sensitivity 55%, and specificity of 60% on the test data.