New Delhi: A start up from Bengaluru has developed an Artificial Intelligence (AI) driven platform capable of identifying Covid positive patients, even from low-resolution chest X-ray images. The announcement was made by the Department of Science and Technology said on Wednesday (June 2).
The platform named Xray Setu is capable of identifying cases of COVID-19 even from WhatsApp images.
This technology will prove helpful for people in rural areas who usually don’t have access to X-ray machines.
Furthermore, developers have also added the facility of rapid screening of COVID-19 with chest X-ray interpretation for doctors who have access to X-ray machines.
“ARTPARK (AI & Robotics Technology Park), a not-for-profit foundation established by the Indian Institute of Science (IISc), Bengaluru, with support from the Department of Science and Technology (DST), in collaboration with Bengaluru-based HealthTech startup Niramai and the IISc, has developed XraySetu specifically designed to identify Covid positive patients even from low-resolution chest X-Ray images sent over Whatsapp,” the DST said.
The platform has already helped in detecting over 1200 cases of COVID-19 in rural areas.
A doctor can simply log on to www.xraysetu.com or can send a WhatsApp message to +91 8046163838 to start the service.
The doctors will then need to send an X-ray image after which they will receive a two-page automated diagnostics with annotated images within few minutes.
It also provides a probability of COVID-19 infection along with a localised heatmap for a quick reading for the doctor.
1,25,000 X-ray images from the National Institute of Health, UK have been verified by the app as well as over 1,000 plus Indian COVID-19 patients.
The app has shown 98.86 per cent on test sensitivity which is the ability to correctly identify a person with the diseases. It is also called the true positive rate.
Meanwhile, the app was 74.74 per cent efficient in case of test specifity which is the ability to identify the person without disease. It is also called the true negative rate.
The platform is also able to identify 14 other lung ailments including tuberculosis and pneumonia.
It can further be used for both analog and digital X-rays and has been successfully piloted by more than 300 doctors in rural areas over the last 10 months added the DST.