Researchers from the Indian Institute of Science, in collaboration with Oslo University Hospital and the University of Adger in Norway, have recently developed a new software tool that could help reveal the severity of lung infections in COVID-19 patients.
The software tool, called AnamNet, is able to read the chest CT scans of COVID-19 patients, and, by using a special kind of neural network, it can estimate how much damage has been caused in the lungs. The tool can also provide automated assistance to doctors and get to a faster diagnosis and better management of the virus.
By using deep learning and other image processing techniques, the software can identify infected areas in a chest CT scan with a high degree of accuracy. It can also determine the severity of the disease by comparing the extent of the infected area with a healthy area.
Hence, the AI tool was praised for its accuracy and ability to perform its diagnosis faster, easier, and with fewer parameters than other similar techs. Moreover, the software is very light and has a small memory footprint. Thus, the researchers have created an app called CovSeg that can be used on a mobile phone and helped healthcare professionals.
The team is committed to making its software even more robust to handle COVID-19 scans, as well as diversify it to use for other common lung diseases like pneumonia, fibrosis and even lung cancer in the near future.