We are living in one of the most challenging eras of human history which is marked by the novel severe acute respiratory syndrome coronavirus - 2019 (SARS-CoV-2). This virus began infecting humans in late 2019 causing COVID-19 which at an unprecedented rapid pace turned into a pandemic spreading all over the world. COVID-19 fundamentally changed the way we live, the way we work, and even the way we view each other. The number of confirmed cases reported in the U.S.A. is above 25 million, with more than half a million deaths and a rate of new cases over 25 thousand per day.

Reliable diagnostics is critical to the detection of COVID-19 cases to interrupt transmission and identify close contacts.  Alongside prompt diagnosis, detection of the severity level of the patient is also crucial in order to judge the precaution level necessary on admission and to achieve swift and optimal clinical decision.Medical imaging, such as Computed Tomography (CT), Chest X-ray (CXR), and Lung Ultrasound (LUS), plays a major role in revealing the presence of COVID-19 infections. CT provides high quality, unoccluded images. CXR is more easily applicable and that is why, more widely accessible around the world

We believe deep learning combined with medical imaging can provide reliable intelligent aids to radiologists and clinicians in their fight with COVID-19. The purpose of this project is to develop a tool by using DCCNs for early and accurate COVID-19 diagnosis. This Computer aided diagnosis tool (CAD) can also be integrated into the clinical workflow with the goal of assessing the severity level of the patient, thus providing decision support to clinicians.