Students of Rajagiri School of Engineering and Technology have developed a software prototype that can identify whether a person is COVID-19 positive or has other conditions like pneumonia, using a chest X-ray.
When the scanned image of an X-ray is fed to it, the software, developed using machine learning, a branch of artificial intelligence, would be able to tell the user if the patient is COVID-19 positive, has pneumonia, or neither of the two. The software could be taught to identify other infections too, said Anusree R., who is part of the team of four B. Tech Computer Science students at the college. Anusree, along with Aarsha Joji, Alaka V. Louis and Amalu Sebastian, had initially developed the software as a final-year project to detect pneumonia-related cases using X-rays, but with the rise in COVID-19 cases in the country, decided to incorporate the disease too.
“The software would be able to present its results in a few seconds, reducing the amount of time that other forms of testing might take,” Anusree said. The software has been trained to identify COVID-19 positive X-rays using datasets that were available online, mostly from the U.S. After a program was written, the computer was fed with positive and negative COVID-19 X-rays to train it.
The group is trying to get hold of more X-rays to improve the accuracy of the software. The students are also developing a standalone app to improve access and convenience.
“X-rays are also a lot cheaper than testing swabs. If people come to hospitals with severe chest congestion symptoms, this could be one of the methods to determine quickly if it is COVID-19, avoiding the delay of the swab test,” said Sangeetha Jamal, Assistant Professor at the college, who supervised the project. “We could recommend it to hospitals, where doctors could try it out,” she said.