POCUS-AI

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:

Funding

People

Thomas van den Heuvel

Thomas van den Heuvel

Postdoctoral Researcher

Keelin Murphy

Keelin Murphy

Assistant Professor

Chase Neff

Chase Neff

Radiology Resident

Chris de Korte

Chris de Korte

Professor

Medical UltraSound Imaging Centre

Bram van Ginneken

Bram van Ginneken

Professor, Scientific Co-Director

Publications

  • T. van den Heuvel, H. Petros, S. Santini, C. de Korte and B. van Ginneken, "Automated Fetal Head Detection and Circumference Estimation from Free-Hand Ultrasound Sweeps Using Deep Learning in Resource-Limited Countries", Ultrasound in Medicine and Biology, 2019;45(3):773-785.
  • T. van den Heuvel, D. de Bruijn, D. de Moens-van Moesdijk, A. Beverdam, B. van Ginneken and C. de Korte, "Comparison Study of Low-Cost Ultrasound Devices for Estimation of Gestational Age in Resource-Limited Countries", Ultrasound in Medicine and Biology, 2018;44(11):2250-2260.
  • T. van den Heuvel, "Automated low-cost ultrasound: improving antenatal care in resource-limited settings", PhD thesis, 2019.