Researchers from the Indian Institute of Technology (IIT) Jodhpur have developed an Artificial Intelligence (AI) model that can detect COVID-19 by examining the chest X-ray of patients, the institute has said in a statement.
According to IIT Jodhpur, the AI-based solution can also be an alternative to the regular RT PCR tests conducted across the world and help in easing the rapidly growing pressure on governments to procure testing kits and set up processing centres.
Researchers from the institute have proposed a deep learning-based algorithm, COMiT-Net, which learns the abnormalities present in the chest X-Ray images to differentiate between a COVID-19 affected lung and a non-COVID affected lung.
The developed AI algorithm not only predicts whether the patient has COVID-19 pneumonia or not but is also capable of identifying the infected regions in the lungs, the statement from the institute further read.
“With the increasing number of COVID 19 cases around the globe, countries have faced challenges with the limited availability of testing kits and processing centres in remote areas. This has been the key motivation for researchers to find alternate methods of testing which are reliable, easily accessible, and faster,” IIT Jodhpur stated in a press communique recently.
Since the symptoms of COVID-19 are visible on chest X-Ray, it has become one of the modalities that has gained acceptance as a screening technique. While there have been numerous research studies in COVID-19 detection using X-ray or CT scans in the past couple of years, most of them fail to provide an explainable solution, the institute claimed.
IIT Jodhpur’s solution, however, was “explainable” as the AI developed at the institute could also identify the areas of the lungs that were affected by COVID-19, the institute said in its statement.
According to the institute, the proposed study can visually show the regions affected by COVID-19. It is more specific as it only studies the lung region, while the AI solution used in this research is explainable from an algorithmic point of view as well as a medical point of view, the institute said.
A research paper on this project has been published in the journal ‘Pattern Recognition (Volume 122)’. The research is part of the RAKSHAK project under NM-CPS DST and iHuB Drishti at IIT Jodhpur. The researchers aim to develop a full-scale prototype through the knowledge learnt during this project.
The team that contributed to this research includes Aakarsh Malhotra, visiting research scholar at IIT Jodhpur; Surbhi Mittal, PhD scholar, Computer Science, IIT Jodhpur; Puspita Majumdar, visiting research scholar at IIT Jodhpur; Saheb Chhabra, visiting research scholar at IIT Jodhpur, and Kartik Thakral, PhD scholar, Computer Science, IIT Jodhpur.
The institute’s director, Shantanu Chaudhury, and professors from the Computer Science department were also a part of the research team. Besides, doctors from Ashwini Hospital and Ramakant Heart Care Centre provided their medical expertise to the team.