Based on research from Prof. Alison Noble’s laboratory at the University of Oxford, our technology uses state-of-the-art Artificial Intelligence (AI) techniques to train a computer to “learn” to recognise features in an image to create a “mental description” of the relevant anatomy.
To teach our AI algorithms, we collaborate with leading medical institutions to create large libraries of real ultrasound images that cover as wide a variety of anatomical variants as possible. This allows the AI models we create to extract salient features that allow them to distinguish normal from abnormal.
As ultrasound is an inherently noisy imaging modality, we have developed a number of image processing techniques to improve performance. The combination of these, the size of our image libraries, and the expertise from our clinical team, puts us in a leading position to create products that support clinical decision making. These will not only reduce scanning time but also expand the use of ultrasound by giving non-specialist practitioners the support they need.
Products in the pipeline may require US FDA or other regulatory approval, as such this material should be considered informational only and does not constitute an offer to sell or infer claims or benefits.