The statement released by IIT Jodhpur states that researchers at IIT Jodhpur have come up with a deep learning-based algorithm called COMiT-Net, which learns abnormalities present in chest X-ray images to differentiate between a lung affected by COVID-19 and a no. -Lung affected by COVID.
“The developed AI algorithm not only predicts whether or not the CXR has COVID-19 pneumonia, but is also able to identify infected regions in the lungs, making them explainable,” IIT said. Jodhpur.
Although there have been many research studies on detecting COVID-19 using X-rays or CT scans in recent years, most of them fail to provide an explainable solution. The uniqueness of this research is the proposed study which can visually present the infected region. The technique interprets only from the pulmonary region.
According to IIT Jodhpur, the artificial intelligence solution used in this research is explainable from an algorithmic and medical point of view.
The team that contributed to this research is composed of Aakarsh Malhotra, Visiting Researcher at IIT Jodhpur, Surbhi Mittal, PhD Researcher in Computer Science, IIT Jodhpur, Pupita Majumdar, Visiting Researcher at IIT Jodhpur, Saheb Chhabra, Researcher guest at IIT Jodhpur, Kartik Thakral, PhD Scholar, Computer Science, IIT Jodhpur, Mayank Vatsa, Professor, Computer Science, IIT Jodhpur, Richa Singh, Professor and Head of Department, Computer Science, IIT Jodhpur, Santanu Chaudhury, Professor and Director, IIT Jodhpur, Ashwin Pudrod, Consultant Pulmonologist, Ashwini Hospital and Ramakant Cardiac Care Center, India, Anjali Agrawal, Consultant Radiologist, TeleRadiology Solutions, India.
A research article 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 large-scale prototype using the knowledge gained in this project.