Microscopy, Artificial Intelligence Aids Detection of COVID-19

By pairing microscopy and artificial intelligence, Beckman Institute for Advanced Science and Technology researchers created a COVID-19 test that is fast, accurate, and cost-effective.

As the pandemic continues to impact the world, screening methods need to remain agile and sophisticated. The research team’s first step was to identify an opportunity to innovate. While many technologies existed for COVID-19 testing, none of them used a label-free optical approach.

The minuscule size of a single particle makes relying on sight alone almost impossible, even when using a microscope. While electron microscopy is useful for imaging a particle’s structure, extensive preparation is necessary to ensure a sample’s visibility. The researchers decided to try a technique developed at Beckham typically used for visualizing cells.

“An electron microscope provides a clear image, but it requires extensive sample preparation,” a graduate student in bioengineering at Beckman Institute Neha Goswami said in a press release.

“Applying SLIM for virus imaging is like looking at something without your glasses on. The image is blurry due to the viruses being smaller than the diffraction limit. However, owing to the high sensitivity of SLIM, we can not only detect the viruses but also differentiate between different types.”

The research team identified a creative way to detect COVID-19 based on SLIM data and the use of artificial intelligence. With the proper training, an advanced deep neural network can be programmed to recognize even the blurriest images.

Researchers introduced the AI program to a pair of images: a stained COVID-19 particle producing fluorescence and a phase image captured with a fluorescence-SLIM multimodal microscope. The AI was trained to recognize them as the same.

After the AI was trained on detection, the machine learning technology was then taught to differentiate COVID-19 from other types of viruses and particles.

“We made life tough on the machine,” Goswami said. “We gave it dust, beads, and other viruses to train and learn to pick the virus out of a crowd as opposed to identifying when it is by itself.”

The AI learned the differences between COVID-19 and other viral pathogens such as H1N1, adenovirus, and Zika virus. The preclinical trial proved successful, with a 96 percent success rate of detecting COVID-19.

“This notable success is due to our team of experts from several different disciplines who came together with a unique goal: to create the fastest, most affordable, and scalable test possible. Our current efforts are focused on demonstrating this approach in the clinic and deploying it worldwide for COVID and potentially other infectious diseases,” Gabriel Popescu, a UIUC professor of electrical and computer engineering, said.

The project’s goal is to create a sensitive and specific viral breath test detection system. Patients would wear a face shield, onto which a transparent glass slide would be attached. They would then complete an activity, such as reading out loud, where their breath becomes fixed to the slide. The slide, and any particles attached to it, would then be imaged and analyzed to detect the virus.

“There are two key advantages to this kind of COVID test,” Goswami said. “The first is speed: the duration can be of the order of one minute. The second is that we are not adding any chemicals or modifications to the samples provided. All we’d be paying for is the cost of the face shield and the slide itself.”

Early intervention and early detection of COVID-19 is an important method to prevent the spread. Not only could this technology be used for COVID-19 detection but other diseases as well.