Detection of COVID-19 using CoviNet and VGG-16 Models

Abstract

The new coronavirus was a complete surprise that no one expected. It has become a pandemic, requiring extensive testing and challenging the health infrastructure and available resources. The standard diagnostic test is RT-PCR. However, the virus was a complete surprise that no one expected. It has become a pandemic, requiring extensive testing and challenging the health infrastructure and available resources. The standard diagnostic test is RT-PCR. However, the RTPCR test has a number of weaknesses, such as when it becomes difficult to obtain the required test kit in most countries, one still has to rely on one approach, which can lead to false-positive results. All these problems necessitate the development of other testing methods so that one is not limited to a single strategy. Chest x-rays, in addition to tests from RT-PCR, can be a useful way to assess the status and severity of COVID19. Once a person’s chest x-ray is available, you will need to inquire about COVID-19 status. This requires a high degree of precision and expertise, neither of which is available. Therefore, one solution to this problem is to develop a COVID-19 detection system to help medical professionals make the final decision. Therefore, we proposed a deep learning model to detect COVID-19 from chest x-ray images. In this, we have used CoviNet and the VGG16 architecture to detect COVID-19 on chest X-ray images. This categorization of images achieved an average accuracy of 97.15% for detection of COVID-19 from chest x-ray images and 98% for three classes, namely Covid-19, pneumonia, and normal.

Ähnliche Arbeiten