Huawei Cloud launches AI-assisted diagnosis for COVID-19
BEIJING, China — The National Health Commission of China has included CT scan features of COVID-19 as the clinical diagnosis standard for COVID-19 in Hubei Province. As one of the decision-making methods for COVID-19 diagnosis and treatment, CT scan powers fast and effective diagnosis and evaluation.
However, due to large numbers of lesions and rapid changes in the lungs, multiple rechecks and image reviews are required in a short period of time. This significantly increased the workloads of imaging doctors, who are already outnumbered by the volume of patients. This in turn affected efficiency and accuracy of diagnoses.
Recently, Huawei Cloud, with the help of Huazhong University of Science & Technology and Lanwon Technology, developed an AI-assisted quantitative medical image analysis service for COVID-19.
With the company’s leading AI technologies—computer vision and medical image analysis—the service automatically produces quick and accurate imaging results, alleviating the workload of doctors.
The service also utilizes powerful Huawei Ascend series AI chips to produce quantization results in seconds, as opposed to manual quantitative image evaluation.
Huawei Cloud leverages computer vision and medical image analysis technologies to segment multiple pulmonary ground glass opacities (CGOs) and lung consolidation to make quantitative evaluations through CTs of patients' lungs. It combines clinical information and laboratory results to help doctors more accurately distinguish between early, advanced, and severe stages of COVID-19. This facilitates early screening and prevention/control.
For confirmed cases in hospitals, it can perform registration and quantitative analysis on 4D dynamic data from multiple rechecks within a short period of time. This helps in effective evaluation of patients' conditions and drug use effects.
According to the analyses of hundreds of both COVID-19 cases and non-infected cases, Huawei Cloud AI-assisted quantitative diagnosis service has implemented industry-leading Dice Similarity Coefficient (DICE: overlaps between the predicted lesions and the actual lesions) and Absolute Volume Difference (AVD: volume differences between the predicted lesions and the actual lesions) of lesion area segmentation. The results are highly consistent with precise manual sketching by doctors.
The technology is developed and constructed based on the Huawei Cloud EIHealth-medical image analysis platform.
The platform uses the Huawei Cloud AI Ascend cluster service and the ModelArts one-stop AI development and management platform to implement one-stop medical image data governance and labeling, model training and evaluation, and visualized rendering, providing powerful support for universities and hospitals with massive AI computing, platform, and algorithm power.
Huawei Cloud has been working with various industries to carry out multiple AI-based scientific research projects on COVID-19.
It has released the results of ultra-large-scale computer-assisted drug screening among many scientific research institutions. Huawei Cloud also worked with Yiwise to provide an intelligent, voice-based epidemic follow-up system for various organizations and institutions for free.
Right now, Huawei Cloud will offer the AI-assisted medical image analysis service for designated hospitals for free. In the future, it will continue to upgrade the diagnosis assistant system for all lung diseases (including pneumonia, lung nodules, and lung cancer) to implement early screening and treatment.
For more information, visit: https://www.huaweicloud.com/intl/en-us/product/eihealth.html.
- Latest
