Jodhpur: Researchers at the Indian Institutes of Technology Jodhpur (IIT-J) has developed a chest x-ray technique based on artificial intelligence (AI) for screening Covid-19A.
The team proposes a profound algorithm-based learning called Comit-Net, which is studying the abnormalities are present in images of a chest X-ray to distinguish between lung affected covid and lungs affected by non-covid.
Experiments conducted with more than 2,500 chest x-ray image and a sensitivity of 96.80 percent.
AI algorithms not only to predict whether a person has pneumonia covid-19, but also able to identify the infected area in the lungs, making it can be explained.
The new technique can visually show off the infected area.
It interprets only from the lung area.
AI solution used in this study can be explained in terms of algorithmic and medical.
The team has been detailing the technique in a research paper published in the journal Pattern Recognition (Volume 122).
With the increasing number of cases Covid-19 in various waves around the world, countries have faced challenges with the availability of testing kits and limited processing centers in remote areas.
This has been a major motivation for researchers to find alternative testing methods that are reliable, easily accessible, and faster.
More recently, the Scottish researchers also developed a technique of x-ray-based AI that might replace PCR tests currently used to detect infection Covid.
The technology developed by experts at the University of the West of Scotland (UWS) is capable of accurately diagnosed Covid-19 in just a few minutes – much faster than the PCR test, which usually takes about 2 hours – and with an accuracy of 98 percent.
“Symptoms Covid-19 is not visible in X-rays during the early stages of infection, so it is important to note that the technology can not completely replace the PCR test,” said Naeem Ramzan from UWS.
“However, it can still play an important role in limiting the spread of the virus, especially when the PCR test is not available,” added Ramzan.