SPHCC and Yitu develop AI-powered Intelligent Evaluation System of Chest CT for COVID-19

The system can complete a quantitative analysis of lung lesions in 2-3 seconds.
By Dean Koh
01:10 am
Share

Above photo: A doctor in SPHCC using the Intelligent Evaluation System of Chest CT for COVID-19 for accurate diagnosis. Credit: Business Wire

Since the outbreak of COVID-19 virus in China, Shanghai Public Health Clinical Center (SPHCC) has been actively mobilizing other parties to use the latest tech in the fight against the virus. Through the joint effort of SPHCC and Yitu Healthcare, a Shanghai-based AI startup, the Intelligent Evaluation System of Chest CT for COVID-19 was officially launched on 28 January. 

HOW IT WORKS

The system utilizes intelligent diagnosis and quantitative evaluation of CT images of COVID-19 through industry-leading image algorithms, and grades the severity of various pneumonia diseases of local lesions, diffuse lesions, and whole lung involvement. 

In addition, it accurately quantifies the cumulative pneumonia load of the disease through quantitative and omics analysis of key image features such as the morphology, range, and density of the lesion. The system can also render a dynamic 4D contrast of the whole lung lesions on CT, helping in clinical judgment of the condition, evaluation of the efficacy, and prediction of the prognosis.

WHY IT MATTERS

The classification of the severity of COVID-19 and the evaluation of its efficacy are the focus of clinical attention. The quantitative evaluation method of lesions involves multiple factors such as the cumulative lung volume range and density of the lesions, and there is currently no uniform standard.

In the past, the traditional manual method of ROI was used for quantitative evaluation, which usually required several hours. The efficiency was low, and the clinical promotion was difficult. By using this new AI system, the detection of the lesion area can be done automatically and the quantitative analysis can be completed in 2-3 seconds. This greatly improves the efficiency of accurate quantitative analysis.

OTHER DEVELOPMENTS IN CHINA TO COMBAT THE SPREAD OF COVID-19

SPHCC also worked with VivaLNK, a Santa Clara, California-based connected health startup, to use the latter’s continuous temperature sensor to combat the spread of coronavirus in China, MobiHealthNews reported.

In mid-February, the Chinese government released a public app to gauge potential coronavirus exposures – the tool acts as a way to collect data as well as to educate citizens on what to do if they have been in close contact with the virus — which is to stay at home and get advice from health authorities.

Baidu, a Chinese multinational tech company, made its online doctor consultation platform publicly free for users that want to consult with a doctor about COVID-19. According to the company, the platform has so far handled (as of 11 Feb) over 4.2 million inquiries from users about COVID-19 with over 300,000 inquires per day. 

ON THE RECORD

“CT imaging is one of the important diagnostic and therapeutic basis for COVID-19, and it can quickly realize the diagnosis of viral pneumonia. The system developed by Yitu Healthcare under the guidance of our hospital is the first AI imaging product in the industry to intelligently evaluate the novel coronavirus pneumonia,” said Prof. Yuxin Shi, deputy director, SPHCC, who also guided the development of the AI-powered system. 

Share