COVID-XIX-Net: Deep Learning Empirical Comparison Between X-ray Imaging and POCUS for COVID-19 Detection

  • Marwa Kandil Kuwait University
  • Ali Kelkawi Kuwait University
  • Imtiaz Ahmad Kuwait University
  • Mohammad Ghuloom Alfailakawi College of Computing Sciences & Engineering


The novel COVID-19 virus has been spreading vigorously through the world starting a pandemic that was never experienced before in our modern era. It is an infectious disease caused by severe acute respiratory syndrome, and carries with it symptoms such as cough, fever and shortness of breath. In March 2020, the World Health Organization recognized COVID-19 as a pandemic, with more than 53 million cases in over 200 countries and over 1.3 million deaths since its discovery. With a limited number of test kits available worldwide and the rapid spread of the disease on a daily basis, alternative means of detection are needed. The use of X-ray imaging, CT scans, and lung point-of-care ultra- sound (POCUS) facilitated early diagnosis of COVID-19 cases. In this study, we leverage InceptionV3 and ResBlocks in building a deep convolutional neural network model, COVID-XIX-Net, to aid in the detection of COVID-19 positive cases through the detection of pneumonic patterns in chest X-ray images and ultrasound scans. COVID-XIX-Net is a multi-class classification model that classifies images into one of 3 classes: healthy, bacterial pneumonia, and COVID-19-induced pneumonic lungs. The proposed model architecture aims towards accurately diagnosing COVID-19 cases while maintain low number of parameters. COVID-XIX-Net is tested on a balanced X-ray dataset composed of 1,011 images, and an imbalanced ultrasound dataset composed of 1,103 images.

After training, cross-validation, and testing, COVID-XIX-Net achieved an accuracy of 99.9% with precision and recall of 0.99 for the X-ray dataset, and an accuracy, precision, and recall of 89.9%, 0.97 and 0.90 respectively for the case of ultrasound dataset. Results are compared against recent literature showing promising results and great potential with only 24.6M parameters. This work can be further developed and trained to assist medical practitioners in diagnosing COVID-19 cases.

Author Biographies

Marwa Kandil, Kuwait University

received B.E. degree in computer engineering from the American University of Kuwait, Kuwait in 2018. She is currently pursuing the M.Sc. degree in computer engineering at Kuwait University, Kuwait. From 2017 to 2019, she worked as Research Assistant with American University of Kuwait. During her time as Research Assistant she published two conference papers and one Journal article. Her research interests include image classification and segmentation using machine learning, artificial intelligence, internet of things technologies, vehicular ad-hoc networks and the use of artificial intelligence with wireless sensor networks. Currently, she has been working as a Teaching Assistant at Kuwait University, Kuwait.

Ali Kelkawi, Kuwait University

received the B.E. degree in computer engineering from the American University of Kuwait, Kuwait in 2018. He is currently pursuing the M.Sc. degree in computer engineering at Kuwait University. He joined the Department of Computer Science, Gulf University for Science &Technology, Kuwait in 2018, where he is currently a Teaching Assistant. His research interests include evolutionary computation methods and artificial intelligence.

Imtiaz Ahmad, Kuwait University

received the B.Sc. degree in electrical engineering from the University of Engineering and Technology at Lahore, Pakistan, the M.Sc. degree in electrical engineering from the King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia, and the Ph.D. degree in computer engineering from Syracuse University, Syracuse, NY, USA, in 1984, 1988, and 1992, respectively. Since 1992, he has been with the Department of Computer Engineering, Kuwait University, Kuwait, where he is currently a Professor. His research interests include the design automation of digital systems, high-level synthesis, distributed computing, machine learning and software-defined networks.

Mohammad Ghuloom Alfailakawi, College of Computing Sciences & Engineering

Computer Engineering Department

Associate Professor