Students develop software to detect COVID-19 cases

Created using machine learning, it studies X-rays to identify infections

May 12, 2020 09:35 pm | Updated May 13, 2020 07:46 am IST - Kochi

This illustration provided by the Centers for Disease Control and Prevention in January 2020 shows the 2019 Novel Coronavirus (2019-nCoV).

This illustration provided by the Centers for Disease Control and Prevention in January 2020 shows the 2019 Novel Coronavirus (2019-nCoV).

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.

0 / 0
Sign in to unlock member-only benefits!
  • Access 10 free stories every month
  • Save stories to read later
  • Access to comment on every story
  • Sign-up/manage your newsletter subscriptions with a single click
  • Get notified by email for early access to discounts & offers on our products
Sign in

Comments

Comments have to be in English, and in full sentences. They cannot be abusive or personal. Please abide by our community guidelines for posting your comments.

We have migrated to a new commenting platform. If you are already a registered user of The Hindu and logged in, you may continue to engage with our articles. If you do not have an account please register and login to post comments. Users can access their older comments by logging into their accounts on Vuukle.