DRDO Centre for Artificial Intelligence and Robotics develops ‘Atman AI’ for Covid detection in Chest X-rays, Health News, ET HealthWorld

Bangalore: DRDO Centre for Artificial Intelligence and Robotics on Friday announced that it has developed an Artificial Intelligence algorithm, “ATMAN AI” for Chest X Rays screening to detect Covid-19, in collaboration with 5C Network & HCG Academics.

This new AI tool will be used by 5C Network, India’s largest digital network of Radiologists, with support of HCG Academics across India. The product has been designed to reduce the burden of CT scans and make covid diagnosis accessible for smaller towns by helping in making the process of X-ray screening fast and efficient.

Mr. Kalyan Sivasailam, CEO of 5C network, commented, “Utilizing the algorithms for chest X-ray is an effective triaging tool which can be accessible to the common man in remotest districts of this country. This will have a significant impact on timely care and appropriate treatment.”

Developers said that the algorithm’s feature ‘Believable AI’ along with existing ResNet models have improved the accuracy of the software and as a machine learning tool, its accuracy will improve continually.

According to DRDO, ‘ATMAN AI’ showed an accuracy of 96.73% when Digital Chest X-Rays of RT-PCR positive hospitalised patients in various stages of disease involvement were retrospectively analysed using Artificial Intelligence [Deep Learning & Convolutional Neural Network] models.

Dr. U K Singh, Director, CAIR, DRDO said, “The development of ATMAN, an Artificial Intelligence based diagnostic tool for Chest X-ray screening is a part of DRDO’s effort to help clinicians and partners on the front line to have the tools they need to rapidly diagnose and effectively treat Covid-19 patients. Given the limited testing facilities for coronavirus, there is a rush to develop AI tools for quick analysis using x-rays. The tool will help in automatically detecting radiological findings indicative of Covid-19 in seconds, enabling physicians and radiologists to more effectively triage the cases, especially in an emergency environment.”

Speaking about the initiative Dr. Vishal Rao, Dean Academics of Centre of Academic Research, HCG Cancer Hospital, said, “This (algorithm) will help to reassure vulnerable health care workers and improve efficacy in hospitals without increasing the financial burden for patients and healthcare systems. Furthermore, similar methods can be used to assess predominant respiratory diseases affecting the vulnerable population and programs initiated which will decelerate the burden of disease on the Govt and the community.”

With the help of 5C Network, developers are now planning to make ‘ATMAN AI’ available to state-run and private hospitals.