AI-Based Technique to Quickly Identify COVID-19 Patients from CT Images

At the University of Notre Dame, scientists have developed a new artificial intelligence (AI)-based method for enhancing CT screening to rapidly find patients affected by the coronavirus.

Yiyu Shi. Image Credit: University of Notre Dame.

The new method will help to decrease the workload of the radiologists who have to screen every image. Difficulties in testing have resulted in an inflow of patients hospitalized with COVID-19 in need of CT scans, showing visual signs of the disease, such as ground-glass opacities, a condition in which abnormal lesions present as a mist on images of the lungs.

Most patients with coronavirus show signs of COVID-related pneumonia on a chest CT but with the large number of suspected cases, radiologists are working overtime to screen them all. We have shown that we can use deep learning—a field of AI—to identify those signs, drastically speeding up the screening process and reducing the burden on radiologists.

Yiyu Shi, Study Lead Researcher and Associate Professor, Department of Computer Science and Engineering, University of Notre Dame

Shi has collaborated with Jingtong Hu, an assistant professor at the University of Pittsburgh, to determine the visual features of COVID-19-related pneumonia by analyzing 3D data from CT scans.

The research group has been making efforts to integrate the analysis software with off-the-shelf hardware to develop a light-weight mobile device that can be simply and instantly incorporated into clinics around the country.

According to Shi, the difficulty is that 3D CT scans are so huge that it is almost impossible to detect particular features and extract them precisely and efficiently on plug-and-play mobile devices.

We’re developing a novel method inspired by Independent Component Analysis, using a statistical architecture to break each image into smaller segments, which will allow deep neural networks to target COVID-related features within large 3D images.

Yiyu Shi, Study Lead Researcher and Associate Professor, Department of Computer Science and Engineering, University of Notre Dame

Shi and Hu are working with radiologists at Guangdong Provincial People’s Hospital in China and the University of Pittsburgh Medical Center, wherein a huge number of CT images from COVID-19 pneumonia are being made available. The researchers believe the advancement can be completed by the end of the year.

The study was financially supported by the National Science Foundation via a Rapid Response Research (RAPID) grant.

Source: https://www.nd.edu/

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Submit