IIT Jodhpur researchers use AI to detect Covid through chest X-rays

An experiment was performed with more than 2500 chest X-ray images and achieved about 96.80% sensitivity

January 28, 2022

IIT Jodhpur develops automated AI-solution for Covid screening from chest X-rays

The Indian Institutes of Technology Jodhpur (IIT-J) have developed an Artificial Intelligence (AI) based chest X-Ray technique for COVID-19 screening. The key motivation for researchers behind their innovation was to find out the alternate methods of testing which are reliable, easily accessible, and faster.

Since the symptoms of COVID-19 are visible on chest X-rays, it has become one of the modalities that have gained acceptance as a screening technique. To cater to this problem, IIT Jodhpur researchers have developed an explainable Artificial Intelligence solution for predicting COVID-19 from chest x-rays.

The team proposed a deep learning-based algorithm called COMiT-Net, which learns the abnormalities present in the chest X-Ray images to differentiate between a Covid affected lung and a non-Covid affected lung.

The experiment was performed with more than 2,500 chest X-Ray images and achieved about 96.80 percent sensitivity. The AI algorithm not only predicts whether a person has COVID-19 pneumonia, but it is also capable of identifying the infected regions in the lungs, thus making them explainable.

The new technique can visually showcase the region which is infected. It interprets only from the lung region. The AI solution used in this research is explainable from both algorithmic and medical points of view.

The team has detailed the technique in a research paper published in the journal Pattern Recognition (Volume 122).

Recently, Scottish researchers also developed an AI-based X-Ray technique that can likely replace the currently used PCR tests for detecting Covid infections.

The technology developed by the experts at the University of the West of Scotland (UWS) was found capable of accurately diagnosing COVID-19 in just a few minutes — far more quickly than a PCR test, which typically takes around 2 hours — and with 98 percent accuracy.

“COVID-19 symptoms are not visible in X-rays during the early stages of infection, so it is important to note that the technology cannot fully replace PCR tests,” said Naeem Ramzan from the UWS. “However, it can still play an important role in curtailing the virus spread, especially when PCR tests are not readily available,” Ramzan added.

[With Inputs from IANS]

PGurus is now on Telegram. Click here to join our channel and stay updated with all the latest news and views

For all the latest updates, download PGurus App.