China's Macao university develops intelligent system to dis
Time: 10:02: Nov-26, 20     Author :  
【typeface:   large   Chinese   Small】      Print this page
Į¸¼ȱѬֱ֨ǦקʹӰͼ䱣ͷϣݴղ߱󵮺ͻȮĦʹᵡҷʷУΰͰڴը¼ƾרųɺ񱧡ٴݰĮˮʱݣChina's Macao university develops intelligent system to dis˷Լ⼩ʽư°ǽֿȾ֢ײ˺ͫ첱ǣüʫۺƫžʷפٽϻȸˣƸܰǽΪһɸųԵͿǺͺıǦΥШ߾ɳٹϵǿԾңɲƬԡվ˫帷ʮͩׯѦѯ罦ӡѵͻѳղ꽥ؼܻ֩йʷ׼China's Macao university develops intelligent system to disڸŲͼڱˮäɸӽǡ

Researchers from the University of Macao of China's Macao Special Administrative Region and institutions in Central China's Hubei province have worked together to develop an intelligent system to distinguish pneumonia caused by the novel coronavirus (COVID-19) from other common pneumonia, said the university Tuesday.

The new system, developed by Prof Wong Pak Kin in the Faculty of Science and Technology, and his doctoral student Yan Tao in the Department of Electromechanical Engineering, can tell COVID-19 from other common pneumonia at a speed nearly 60 times faster than radiologists, the University of Macao said in a press release.

They had worked with researchers at institutions in Hubei Province to collect data on 206 confirmed COVID-19 patients and their 416 chest computed tomography (CT) scans, as well as data on 412 patients with non-COVID-19 pneumonia and their 412 chest CT scans.

Based on these CT images, the researchers developed an automatic diagnosis system based on a multi-scale convolutional neural network. The verification results have shown that with a limited amount of data, the intelligent diagnosis system can successfully distinguish COVID-19-caused pneumonia from other common pneumonia.

CT diagnosis has a very high degree of accuracy and can provide more clinical information for COVID-19 detection and diagnosis. But the large number of scan images and lengthy time for manual identification bring big challenge for radiologists.

The related research paper titled "Automatic Distinction between COVID-19 and Common Pneumonia using Multi-Scale Convolutional Neural Network on Chest CT Scans" has been published by the international science journal Chaos, Solitons &Fractals in its latest issue.

Recommend Submit

Media partners:
BBC newsman | stock investment |