Researchers develop COVID-19 diagnosis technique using X-ray images

New Delhi, Jan 29: With the increasing number of COVID 19 cases across various waves around the globe, countries have faced challenges of the limited availability of testing kits and processing centers, especially in remote areas.

Researchers from the Indian Institutes of Technology (IIT) Jodhpur have developed an automated Artificial intelligence (AI) solution for COVID-19 screening. The experiment was performed with more than 2500 chest X-ray images and achieved about 96.80% sensitivity.

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

The researchers have proposed a deep learning-based algorithm called COMiT-Net, which detects 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 CXR has COVID-19 pneumonia or not, but it is also capable of identifying the infected regions in the lungs, thus making them explainable.

The study, published in the journal Pattern Recognition, is a part of the RAKSHAK project, under National Mission on Interdisciplinary Cyber-Physical Systems (NM-ICPS) of Department of Science & Technology (DST), and iHuBDrishti, at IIT Jodhpur. The researchers aim at developing a full-scale prototype through the knowledge learnt in this project.

While there have been numerous research studies in COVID-19 detection using X-ray or CT scans in the past years, most of them fail to provide an explainable solution. The proposed study can visually showcase the region which is infected, and this technique interprets only from the lung region. The Artificial Intelligence solution used in this research is explainable from both algorithmic and medical points of view, say researchers.

The IIT Jodhpur team that contributed to this research includesAakarshMalhotra, Visiting Research Scholar, Surbhi Mittal, PhD Scholar, PuspitaMajumdar, Visiting Research Scholar, SahebChhabra, Visiting Research Scholar, KartikThakral, PhD Scholar, MayankVatsa, Professor, Dr. Richa Singh, Professor and HOD, Computer Science, DrSantanuChaudhury, Director of the institute. AshwinPudrod, Consultant Pulmonologist, and Anjali Agrawal, Consultant Radiologist were also included in the study. (India Science Wire)