AI Combined With X-rays May Offer Fast Tool for Detecting COVID-19

A recent study which was published in EEE/CAA Journal of Automatica Sinica, a joint publication of the IEEE and the Chinese Association of Automation, has found that X-rays in combination with an artificial intelligence tool could be a potentially leading edge way for detecting the COVID-19 virus.

The research was conducted by investigators from the Universidade de Fortaleza in Brazil, in collaboration with the Universidade Federal do Ceará and the Instituto Federal do Ceará.

"When the COVID-19 pandemic arose, we agreed to put our expertise to use to help deal with this new global problem," Victor Hugo C. Albuquerque, a researcher in the Laboratory of Image Processing, Signals, and Applied Computing and with the Universidade de Fortaleza said. "We decided to investigate if a COVID-19 infection could be automatically detected using X-ray images.”

The investigators behind the study have done previous research on detecting and classifying lung pathologies, such as fibrosis, emphysema and lung nodules, using medical imaging. Common symptoms of COVID-19 like respiratory distress, cough and pneumonia, are all visible via medical imaging such as CT scans or X-rays.

For this study, the team focused on improving X-ray devices with a machine learning algorithm to see if it could detect COVID-19 in chest scans. Using several different methods, they trained the model with a large dataset to detect lungs that are likely infected with the virus.

Findings showed that the AI tool was able to detect COVID-19 in chest X-rays with 95.6 to 98.5% accuracy.

"Since X-rays are very fast and cheap, they can help to triage patients in places where the health care system has collapsed or in places that are far from major centers with access to more complex technologies," Albuquerque said. "This approach to detect and classify medical images automatically can assist doctors in identifying, measuring the severity and classifying the disease."