UBCO researchers are testing alternative COVID-19 screening methods to battle the virus across the globe.
Associate professor Mohamed S. Shehata, postdoctoral research fellow Mohamed Abdelpakey and graduate student Sherif Elbishlawi have developed CORONA-Net, a deep learning neural network that can quickly detect COVID-19 infections using X-ray images.
The method was developed as an alternative to rapid tests and polymerase chain reaction (PCR) tests, both of which can be inaccessible in many parts of the world. By using CORONA-Net, the artificial intelligence system can flag suspicious cases to be fast-tracked and looked at quickly without the need for specialists.
“COVID-19 typically causes pneumonia in human lungs, which can be detected in X-ray images. These datasets of X-rays—of people with pneumonia inflicted by COVID-19, of people with pneumonia inflicted by other diseases, as well as X-rays of healthy people — allow the possibility to create deep learning networks that can differentiate between images of people with COVID-19 and people who do not have the disease,” said Elbishlawi.
While the accuracy of detecting COVID-19 by CORONA-Net is not yet known, it will continue to increase as the dataset grows. Elbishlawi says the program can automatically improve itself over time and self-learn to be more accurate. So far, however, the program has given a highly accurate prediction to COVID-19.
“CORONA-Net can have a significant and positive impact on health-care systems as testing every person suspected of having the disease is difficult. CORONA-Net can provide accurate and promising results in terms of sensitivity, positive predictive value and overall accuracy,” said Abdelpakey.