Researchers from the Indian Institute of Technology in Jodhpur (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. 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 an affected lung and a non-affected lung. It can also identify infected regions of the lungs.
According to a statement by the institute, the AI-based solution is an alternative to the regular RT PCR tests conducted across the world and can help ease the 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 experiment was performed with more than 2,500 chest X-ray images and achieved about 96.80% sensitivity. The number of COVID-19 cases around the globe has been increasing as well as the number of challenges that countries are facing. The limited availability of testing kits and processing centres in remote areas has been the key motivation for researchers to find alternate testing methods that are reliable, easily accessible, and faster.
Since the symptoms of the virus are visible on chest X-rays, it has become one of the modalities that have 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. As per a report by The Times of India, the AI solution 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). The researchers aim to develop a full-scale prototype.
AI is not just a critical part of healthcare services today but of almost every sector of the economy. India is investing and deploying initiatives in AI to increase the level of digital literacy in the country’s workforce. Earlier this month, OpenGov Asia reported that the Centre for the Development of Advanced Computing (C-DAC) and four Indian Institutes of Technology (IITs) created and launched an online course on applied AI. It contains 33-sessions that will cover how to implement AI-based solutions in domains like healthcare and smart city projects, as well as how to scale these projects to an industrial level. The four partnering IITs are from four different locations: Kharagpur, Madras, Palakkad, Goa.
The curriculum will include the fundamentals of AI accelerators and system setup, accelerated deep learning, end-to-end accelerated deep science, and will explore industrial use-cases of accelerated AI. It is aimed at learners with at least a basic knowledge of machine learning; students in their final year of Engineering, science postgraduates, PhD scholars, and professionals. Several leading national institutions will intermittently participate in the course. For instance, learners will have code walkthroughs and industrial case studies that are part of the National Supercomputing Mission (NSM).