Researchers at IIT Jodhpur have developed a deep learning-based algorithm called the COMiT-Net to detect Covid. The model can learn the abnormalities present in the chest X-Ray images to differentiate between COVID-19 affected lungs and normal lungs.
Additionally, the AI model can identify the regions of the lungs affected by COVID-19. According to IIT Jodhpur, the AI-based solution can also be an alternative to the regular RT PCR.
The experiment was performed with over 2,500 chest X-Ray images and achieved about 96.80% sensitivity.
“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.
According to the institute, the AI solution used in this research is explainable from an algorithmic point of view as well as a medical point of view.
A detailed 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.
Aakarsh Malhotra, visiting research scholar at IIT Jodhpur; Surbhi Mittal, PhD scholar, Computer Science, IIT Jodhpur; Saheb Chhabra, visiting research scholar at IIT Jodhpur, Puspita Majumdar, visiting research scholar at IIT Jodhpur; and Kartik Thakral, PhD scholar, Computer Science, IIT Jodhpur contributed to the research.
