Marie Donlon | April 05, 2024
A team of researchers from Johns Hopkins University has created a tool capable of detecting signs of the COVID-19 virus in lung ultrasound images.
According to the researchers, the artificial intelligence (AI)-driven technology works like facial recognition software, autonomously identifying signs of COVID-19 and other pulmonary diseases in the ultrasound images of lungs.
In vivo and simulated examples of (a) A-line, (b) B-line, and (c) consolidation features. Source: Lingyi Zhao et al.
To enable this, the AI model has been trained to identify B-lines in ultrasound lung images, which are an indication of inflammation associated with pulmonary complications. The AI tool reportedly analyzes a combination of computer-generated and accurate ultrasound data — among them, scans from COVID-19 patients — so that it can then accurately detect abnormalities associated with the virus.
“We had to model the physics of ultrasound and acoustic wave propagation well enough in order to get believable simulated images,” the researchers explained. “Then we had to take it a step further to train our computer models to use these simulated data to interpret real scans from patients with affected lungs reliably.”
The tool could potentially be incorporated into wearables for tracking illnesses like congestive heart failure, which can lead to fluid overload in patients’ lungs, much like COVID-19.
The model is detailed in the article, “Detection of COVID-19 features in lung ultrasound images using deep neural networks,” which appears in the journal Communications Medicine.
UNLIMITED FREE ACCESS TO THE WORLD’S BEST IDEAS
SIGN UP TO SEE MORE
This is embarrasing…
An error occurred while processing the form. Please try again in a few minutes.
Customize Your GlobalSpec Experience
This is embarrasing…
An error occurred while processing the form. Please try again in a few minutes.
