The Defence Research and Development Organisation (DRDO) has developed an artificial intelligence algorithm that can detect the presence of the COVID-19 virus in chest X-rays. The AI tool, ATMAN AI, was developed by DRDO’s Centre for Artificial Intelligence and Robotics (CAIR), with support from 5C Network & HCG Academics.
Triaging using X-ray in COVID-19 diagnosis is a method for the rapid identification and assessment of the lungs, according to a statement issued by HCG Academics. The tool will be used by 5C Network, the country’s largest digital network of radiologists, with the support of HCG Academics. Triaging potential patients using X-ray is fast, cost-effective, and efficient.
The statement claimed that ATMAN is a useful tool especially in smaller towns in the country, owing to a lack of access to CT scans. The technology will also reduce the existing burden on radiologists and free up CT machines for other diseases and illnesses. The statement said that the feature Believable AI, along with existing ResNet models, has improved the accuracy of the software, and being a machine learning tool, the degree of accuracy will improve continually. The algorithm showed an accuracy of 96.73%.
The chest X-rays of RT-PCR positive patients were retrospectively analysed in various stages of disease involvement using AI models (deep learning and convolutional neural network) from an application developed by CAIR-DRDO to screen COVID-19 using digital chest X-rays. The development of ATMAN as an AI-based diagnostic tool for the virus is part of DRDO’s effort to help clinicians and partners on the frontline to have the tools they need to rapidly diagnose and effectively treat COVID-19 patients.
Given the limited testing facilities for the virus, there is a rush to develop AI tools for quick analysis using X-rays. The tool would help in automatically detecting radiological findings indicative of COVID-19 in seconds, enabling physicians and radiologists to triage the cases more effectively, especially in an emergency.
The CEO of 5C network, Kalyan Sivasailam, noted that utilising 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.” Dr Vishal Rao, Dean Academics, Centre of Academic Research, HCG Cancer Hospital said the new tool would improve efficacy in hospitals “without increasing the financial burden for patients and healthcare systems.” He added that similar methods would also become useful in assessing predominant respiratory diseases.
It is expected to have a significant impact on timely care and appropriate treatment. With the ongoing second wave of infections, this application can help with a more directed and focused approach, the statement said. 5C Network, which is connected to over 1,000 hospitals across the country, will make ATMAN available to state-run and private hospitals.
Last month, DRDO announced it would set up 500 medical oxygen plants in the country under the Prime Minister CARES fund programme. Medical oxygen plant (MOP) technology was developed to supply oxygen onboard the light combat aircraft (LCA) by the Defence Bioengineering and Electromedical Laboratory (DEBEL).
The MOP is designed for a capacity of 1,000 litres per minute (LPM). The system can cater to 190 patients at a flow rate of 5 LPM and charge 195 cylinders per day. As OpenGov Asia had reported, the technology can generate oxygen with around 93% concentration and can be directly supplied to hospital beds or used to fill medical oxygen cylinders.