Search

Artificial intelligence techniques are used on chest X-ray images for accurate detection of diseases and this paper aims to develop a process which is capable of diagnosing COVID-19 using deep learning methods on X-ray images. For this purpose, we used Mask R-CNN method to train and test on the dataset to classify between patients infected and non-infected with COVID-19. The dataset used here contains a large number of frontal views of X-ray images which are an essential resource for the algorithms used in the development of tools for the detection of COVID-19. Using 668 chest Xray images, the proposed model achieved an accuracy as high as 96.98%, specificity of 97.36% with the precision of 96.60%. The entire process is presented in detail. When a comparison table on the AIbased techniques is prepared, it is noticed that the Mask R-CNN technique on chest X-ray images provides better efficiency in the detection of COVID-19. The Mask R-CNN method is found to be accurate and robust in the detection of COVID-19 from chest X-ray images. [ABSTRACT FROM AUTHOR]

The concept of single-valued neutrosophic sets (SVNSs) is considered as an attractive tool for dealing with highly ambiguous and uncertain information. The correlation coefficient of SVNSs acts as an important measure in the single-valued neutrosophic set theory and it has been applied in various fields, such as the pattern recognition, medical diagnosis, decision-making and also clustering analysis. To alleviate the weakness of the existing correlation coefficients, a novel statistical correlation coefficient is put forward to measure the degree of correlation between two SVNSs. This statistical correlation coefficient is developed based on the variance and covariance of SVNSs and its value is between −1 and 1. When solving the multicriteria decision making problems, the criteria show different weight values. To consider the weight information of multiple criteria, the weighted statistical correlation coefficient is developed for SVNSs. Afterwards, two numerical examples are given to show the effectiveness of the proposed statistical correlation coefficient in the pattern recognition, which can accurately classify unknown patterns into known patterns. Finally, the feasibility and practicability of the proposed correlation coefficient formula are illustrated by a practical multiple attribute decision making problem of traditional Chinese medicine diagnosis. The comparative results show that the proposed correlation coefficient formula is rational and effective. [ABSTRACT FROM AUTHOR]

Less than 2% of children are reported to test positive for SARS-CoV-2. However, increasing reports have described COVID-positive children demonstrating symptoms like Kawasaki disease (KD), an acute vasculitis in medium sized vessels. Characteristic clinical features of KD include fever, conjunctivitis, mucosal alterations, rashes, and cervical lymphadenopathy. We searched PubMed with six keywords including neutrophil and macrophage extracellular traps (NETs/METs), Kawasaki disease, vasculitis, COVID-19 and SARS-CoV-2. We discussed here how SARS-CoV-2 infection is accompanied by activation of proinflammatory cytokines, specifically IL-1β and production of neutrophil and macrophage extracellular traps (NETs/METs), structures formed through specialized types of cell death. In this review, we propose that the KD-like pathogenesis observed in COVID-19- infected children could arise from infection of resident macrophages resulting in activation of NLRP3 inflammasomes and release of IL-1β in a genetically predisposed subset of infected children, mediated via NET/MET dysregulation and overproduction. We also propose potential avenues of diagnosis and treatment that could be utilized to aid such patients. [ABSTRACT FROM AUTHOR]

The World Health Organization (WHO) has announced a COVID-19 was a global pandemic in March 2020. It was initially started in china in the year 2019 December and affected an expanding number of nations in various countries in the last few months. In this particular situation, many techniques, methods, and AI-based classification algorithms are put in the spotlight in reacting to fight against it and reduce the rate of such a global health crisis. COVID-19's main signs are heavy temperature, different cough, cold, breathing shortness, and a combination of loss of sense of smell and chest tightness. The digital world is growing day by day; in this context digital stethoscope can read all of these symptoms and diagnose respiratory disease. In this study, we majorly focus on literature reviews of how SARS-CoV-2 is spreading and in-depth analysis of the diagnosis of COVID-19 disease from human respiratory sounds like cough, voice, and breath by analyzing the respiratory sound parameters. We hope this review will provide an initiative for the clinical scientists and researcher's community to initiate open access, scalable, and accessible work in the collective battle against COVID-19. [ABSTRACT FROM AUTHOR]