A Covid Detection using deep learning and CNN

Computer Engineering

Until now millions of people have contracted covid and many have died because of covid. These have spread all over the world and caused the medical infrastructure a lot of damage and presented numerous challenges in front of them.The key component for research in covid is the availability of a dataset. With limited availability of chest ultrasound images and time constraints with the disease fast and accurate results are very important. There has been a lot of development using deep learning in detecting chest related diseases. The Robustness' and generalization of covid detection using these images is questionable though. We aimed to use thousands of readily available chest ultrasound images with clinical findings associated with COVID-19 as a training data set, mutually exclusive from the images with confirmed COVID-19 cases, which will be used as the testing data set. In particular, we present a novel deep learning approach which detects the affected area and its severity.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.