Robust Technique to Detect COVID-19 using Chest X-ray Images

Abstract

COVID-19 typically known as Coronavirus disease is an infectious disease caused by a newly discovered coronavirus. Currently detection of coronovirus depends on factors like the patients' signs and symptoms, location where the person lives, travelling history and close contact with any COVID-19 patient. In order to test a COVID-19 patient, a healthcare provider uses a long swab to take a nasal sample. The sample is then tested in a laboratory setting. If person is coughing up then the saliva (sputum), is emitted for testing. The diagnosis becomes even more critical when there is a lack of reagents or testing capacity, tracking the virus and its severity and coming in contact with COVID-19 positive patients by a healthcare practitioner. In this scenario of COVID-19 pendamic, there is a need of streaming diagnosis based on retrospective study of laboratory data in form of chest X-rays using deep learning. This paper proposed a demystify technique to detect COVID-19 using assembling medical images with the help of deep nets. The study shows promising results with accuracy of 91.67% for diagnosis of COVID-19 and I00% accuracy in proving the survival ratio.

Ähnliche Arbeiten