Community Blog Speeding Up CT Scans to Detect COVID-19

Speeding Up CT Scans to Detect COVID-19

As the pandemic continues to escalate, our CT Image Analytics for COVID-19 tool lightens the load for the healthcare sector by providing fast and accurate analysis.

In order to win this inevitable battle and fight against COVID-19, we must work together and share our experiences around the world. Join us in the fight against the outbreak through the Global MediXchange for Combating COVID-19 (GMCC) program. Apply now at https://covid-19.alibabacloud.com/

How can you monitor a pandemic without fast and accurate disease analysis? The simple answer is, you can't.

Yet, the world's CT imaging departments are struggling to meet the rising demands of the COVID-19 crisis. This is because a typical CT scan takes between five and 15 minutes to analyze. Plus, many researchers are working long hours to try and keep pace with escalating demand, causing fatigue and human error to creep into their work.

This is where CT Imaging Analytics for COVID-19 can help. Using AI-enabled algorithms, this technology can predict the probability of COVID-19 pneumonia with an accuracy of 96%. It is 60 times faster than human detection methods, taking between three and four seconds to run each test and transmit the data. Plus, this technology can also estimate the proportion of pulmonary lesions.

CT Imaging Analytics achieves this using cutting-edge deep learning algorithms, which have been trained using 5,000 samples to understand the differences between COVID-19 pneumonia, common pneumonia, and other conditions. As of March 14, 2020, the technology had analyzed more than 240,000 CT image volumes, which is equivalent to an average of roughly 13,000 results per day.

These AI-enabled algorithms were recently made available by the Alibaba DAMO Academy. They are used in conjunction with Alibaba Cloud's existing suite of cloud-based technologies to further expedite and safeguard the data processing capabilities of the world's CT departments.

How it Works

Using a simple API, CT departments can link their existing local cloud imaging applications to store, view and share CT scan images, tapping into the DAMO Core Algorithm. This installation takes three working days to setup.

Alternatively, we can help you deploy cloud PACS (Picture Archiving and Communication Systems), providing your department with a complete cloud imaging technology. This installation takes 10 working days to setup.

Figure 1: AI-Assisted analysis process of COVID-19

Whichever deployment is used, CT Imaging Analytics gives researchers access to a rapid and highly accurate analysis tool, helping them keep pace with the pandemic.

Open Research for All

CT Imaging Analytics was developed under the Fighting COVID-19 Technology Center, which is an initiative run by Alibaba Cloud to support disease control centers and genome research institutions worldwide to help understand COVID-19, effectively treat the disease, and mitigate the risks associated with this pandemic.

If you work in these fields, you can submit the summary and description of your research project to wanqing.hwq@alibaba-inc.com for consideration.

While continuing to wage war against the worldwide outbreak, Alibaba Cloud will play its part and will do all it can to help others in their battles with the coronavirus. Learn how we can support your business continuity at https://www.alibabacloud.com/campaign/fight-coronavirus-covid-19

0 0 0
Share on

Alibaba Clouder

2,600 posts | 754 followers

You may also like