Point-of-care ultrasound (POCUS) is about using portable ultrasound devices, often with a phone or table for viewing the data, so that examinations can be made on-site, at the patient's bed-side, in an ambulance, or in the practice of a general practitioner. POCUS has the potential to save billions of euros and it can be used for many new applications. Cheap portable ultrasound devices are rapidly appearing on the market. But acquiring a proper ultrasound exam is not easy, and interpreting the images from the exam can also be complex. We aim to solve both aspects with real-time integrated deep learning.
The first project we've worked on the last few years is aimed at reducing maternal death in developing countries using a sweep protocol with integrated deep learning analysis to scan pregnant women and detect those with a high risk pregnancy. Below is an excerpt from a presentation by Bram van Ginneken given at the 2020 AAPM COMP meeting outlining the status of the project: