Researchers at the Indian Institute of Science (IISc) designed a special tool called ‘AnamNet’ to diagnose the severity of coronavirus infection in patients’ lungs.

The study was carried out by researchers from the Departments of Computational and Data Science (CDS) and Instrumentation and Applied Physics at IISc. They conducted the study in collaboration with colleagues from the Oslo University Hospital and the University of Agder in Norway.

The study was published in the journal IEEE Transactions on Neural Networks and Learning Systems.

To develop this software tool, the researchers employed a unique neural network and deep learning, and other image processing techniques. Their tool finds specific abnormal features and estimates the damage in the lungs and identifies infected areas in a chest CT scan with a high level of accuracy.

The authors noted that the neural network in the app was also computationally less complex, which allowed the researchers to train it much faster to detect anomalies. Being a lightweight software, AnamNet leaves only a small memory footprint.

The software is designed to ‘segment’ the scan as ‘infected’ and ‘not infected’.

The researchers explained in the study that the tool basically extracts features from the chest CT images and projects them onto a non-linear space, and then recreates the [segmented] image from this representation.

The researchers stated that they are planning to expand the services of the software tool so as to detect and trace other lung diseases, including pneumonia, fibrosis, and even lung cancer.

comment COMMENT NOW