- This online tool can indicate the probability if a person is infected with COVID-19, can be used for quick preliminary diagnosis before the medical test
- The IIT researchers pooled the data of X-ray images of COVID-19 infected patients along with healthy persons from different sources available on the internet
Researchers at the Indian Institute of Technology (IIT), Gandhinagar have developed an artificial intelligence-based deep learning tool for detection of COVID-19 from chest X-ray images. This online tool can indicate the probability if a person is infected with COVID-19, it can be used for quick preliminary diagnosis before the medical test. It is being tested by the Indian Institute of Public Health (IIPH).
Kushpal Singh Yadav, an MTech student at IIT’s Department of Computer Science Engineering, said that given the limited testing facilities for COVID-19, there is a rush to develop AI tools for quick analysis using X-rays. He added that developing a reliable tool requires the combination of the right algorithms and data. This is where the tool would prove useful and can be trained for diagnostic purposes and made available for wider use.
12 layers of neural network
The IIT researchers pooled the data of X-ray images of COVID-19 infected patients along with healthy persons from different sources available on the internet. They trained a machine learning architecture using deep learning algorithms with these images.
Yadav explained that the model used 12 layers of neural network, which is similar to the neurons in the human brain. The deep learning method has the advantage that it learns the disease diagnosing features from the X-ray images in an automatic way. The tool uses images from other lung infections like tuberculosis, pneumonia to ensure the specificity of detection of COVID from other lung diseases
Krishna Prasad Miyapuram, the associate professor of cognitive science and computer science, who supervised the IIT project claimed that the tool outperforms other such high-tech devices available globally. Miyapuram said that it uses simple machine learning architecture, which makes it stand out over others. The tool is only indicative and clinical consultation is essential to confirm the diagnosis but it can really help reduce the burden on our medical infrastructure at present as per him.