WisdomNet: Prognosis of COVID-19 with Slender Prospect of False Negative Cases and Vaticinating the Probability of Maturation to ARDS using Posteroanterior Chest X-Rays

WisdomNet: Prognosis of COVID-19 with Slender Prospect of False Negative Cases and Vaticinating the Probability of Maturation to ARDS using Posteroanterior Chest X-Rays

Sunita Kumari, Peeyush Kumar, Ayushe Gangal

Coronavirus is a large virus family consisting of diverse viruses, some of which disseminate amongmammals and others cause sickness among humans. COVID-19 is highly contagious and is rapidlyspreading, rendering its early diagnosis of preeminent status. Researchers, medical specialists andorganizations all over the globe have been working tirelessly to combat this virus and help in itscontainment. In this paper, a novel neural network called WisdomNet has been proposed, for thediagnosis of COVID-19 using chest X-rays. The WisdomNet uses the concept of ‘Wisdom of Crowds’ as itsfounding idea. It is a two-layered convolutional Neural Network (CNN), which takes chest x-ray imagesas input. Both layers of the proposed neural network consist of a number of neural networks each. Thedataset used for this study consists of chest x-ray images of COVID-19 positive patients, compiled andshared by Dr. Cohen on GitHub, and the chest x-ray images of healthy lungs and lungs affected by viraland bacterial pneumonia were obtained from Kaggle. The network not only pinpoints the presenceof COVID-19, but also gives the probability of the disease maturing into Acute Respiratory DistressSyndrome (ARDS). Thus, predicting the progression of the disease in the COVID-19 positive patients.The network also slender the occurrences of false negative cases by employing a high threshold value,thus aids in curbing the spread of the disease and gives an accuracy of 100% for successfully predictingCOVID-19 among the chest x-rays of patients affected with COVID-19, bacterial and viral pneumonia.

2020

convolutional neural networks, ARDS, chest x-rays, COVID-19, wisdomnet

DOI: 10.22207/JPAM.14.SPL1.24

Journal of Pure and Applied Microbiology

Journal of Pure and Applied Microbiology

Microbiology