LPU scientists developed software to detect covid-19 from CT scan images
Scientists’ team at LPU is in touch with the Indian Council of Medical Research (ICMR) for further evaluation of the ‘Interface’
Jalandhar: A researchers’ team of sciences and technology domains at Lovely Professional University (LPU) has developed an easy-to-use ‘Cloud-based advanced Web-Interface’ to detect and diagnose ‘COVID-19 Symptoms’ quickly. The diagnosis will be possible merely from the CT Scans or X-Ray image reports of the concerned patients. Using this interface, health professionals will only have to upload patient's scan images on the website to get the diagnosis result within a few seconds, even for the reports received from the remotest parts of the country. This AI (Artificial Intelligence) framework has been successfully tested on more than 13,000 Chest Radiography Images.
LPU Scientists’ team is now in touch with the Indian Council of Medical Research (ICMR) for further evaluation of the innovative ‘Interface’. This latest technology based testing at LPU is developed as a part of global efforts to tackle the coronavirus pandemic, and that too at a minimal cost. The team includes B Tech students Prabin Kumar Das, Biswajyoti Roy, Faculty Members Prof Dr Rajesh Singh and Prof Dr Anita Gehlot. They took nearly one month in developing the entire framework.
As per the LPU team, this novel system does not need any high-tech device or extra skilled technicians to operate upon, except for uploading the images. It can be easily accessed by an authorized healthcare professional from anywhere in the world through a basic mobile device with internet connectivity and a web browser. The developed web-interface is connected to an AI model at a centralized server which processes the images received from the web portal, and sends the results back to the web portal. The portal is capable of hosting any AI model that is preferred by a hospital, and will accordingly be able to detect the infection as well as the extent to which it has affected the patient. Moreover, the images uploaded on the interface will be AES encrypted ensuring complete privacy for the patient.
The team is also desirous in industrialization of this socially useful development. So, the team is also furthering talks with the industry people for collaborations. It is to provide the most promising medically-certified AI models, which are to be used for quick detection and diagnosis of COVID19. In fact, early detection will help doctors to segregate patients and make decisions to prioritize, isolate or put the concerned patient on a ventilator by using available resources efficiently.
Executive Dean of Science and Technology at LPU, Dr Lovi Raj Gupta shares that experts from around the world have also strongly recommended the use of CT scans for quick diagnosis of COVID 19. The World Health Organization (WHO), too, holds that the novel coronavirus causes respiratory illness resembling viral pneumonia, resulting in fever, cough, and shortness of breath. A study published in the journal Radiology also found that chest X-ray scan features can help in the early detection and diagnosis of the virus.