GE HealthCare is a global leader in medical technology and digital solutions, driven by a mission to create a world where healthcare has no limits. In Norway, our cardiac ultrasound systems are designed and developed with deep roots in research and innovation. At Forskningsparken in Oslo, our R&D team is pioneering next-generation ultrasound software, working at the intersection of cutting-edge AI and clinical excellence. With strong collaborations across Norwegian hospitals and international research institutions, we offer a unique environment where technical and clinical expertise converge.
Project Overview
Echocardiography is a cornerstone of cardiac diagnostics, offering real-time, non-invasive insights into heart structure and function. However, interpreting these exams—especially across different patients or timepoints—requires significant expertise and manual effort. This project explores how novel AI techniques, including foundation models and multimodal learning, can be used to automate both quantitative and qualitative analysis of echocardiographic data.
Students will investigate how AI can extract and interpret:
- Quantitative features: chamber dimensions, wall thickness, blood flow velocities, valve function, and hemodynamic parameters.
- Qualitative findings: abnormal wall motion, pathological lesions, valve defects, and other clinically relevant anomalies.
Additionally, the project will explore cross-exam comparisons, enabling AI to detect changes over time or differences between patients—supporting longitudinal tracking and personalized diagnostics.
Why This Project?
- Work with real clinical data and collaborate with experts in cardiology and AI.
- Apply and experiment with state-of-the-art AI models, including transformers, vision-language models, and self-supervised learning.
- Contribute to a field with direct patient impact, improving diagnostic accuracy and reducing clinician workload.
- Be part of a vibrant R&D community in Oslo, with access to world-class ultrasound systems and mentorship from experienced engineers and clinicians.
Ideal Candidates We’re looking for curious and motivated students with backgrounds in:
- Machine learning / deep learning
- Biomedical engineering or medical imaging
- Signal and image processing
- Programming (Python, PyTorch, TensorFlow)
Contact UiO:
Eigil Samset – eigilsa@ifi.uio.no
Sarina Thomas – Sarinat@ifi.uio.no