PhD Position in Physics-Informed Machine Learning for Cardiac Magnetic Resonance in Zürich

The CMR group at the Institute for Biomedical Engineering develops Magnetic Resonance (MR) technology and methods to assess the cardiovascular system. We devise the next generation of diagnostic tools for quantification of blood flow, organ perfusion, metabolism and function, tissue composition, microstructure and mechanics. The group exploits principles from physics, electrical engineering and computer science to design highly efficient and sensitive imaging and inference approaches to help guide diagnosis and treatment in cardiovascular patients.

Our research has demonstrated approaches to data- and physics-informed synthesis of medical imaging data allowing us to train inference machines and classifiers based on paired ground truth and synthetic imaging data. We capitalize on our previous and current work allowing us to not only acquire MR imaging data of cardiac anatomy and function but also information about cardiac micro-and mesostructures derived from diffusion tensor imaging of the heart along with all parameters determining the measurement process itself.

The position to fill concerns advanced data synthesis (both via machine learning-based generative models and physics simulation) and data inference (including segmentation, classification, parameter inference and mesh fitting) based on data-driven and (bio)physics-informed machine learning principles. The project aims at training and learning using both bottom-up and top-down approaches with applications to cardiac image synthesis, reconstruction and classification. The position is embedded in our overall activities of advancing MR methodology as part of improving decision support in cardiovascular patients.

You hold a Master of Science degree with first-class grades in:

• computer science
• electrical engineering
• biomedical engineering
• physics or
• applied mathematics

You present with expertise in advanced signal and data processing and its applications to cutting-edge imaging. Developing programming skills (Matlab/Python, C(++)) and hands-on work with deep learning frameworks such as PyTorch, TensorFlow, Keras have been in your focus. Further, experience with standard supervised machine learning on image data (classification, segmentation), generative image models (VAEs, GANs, diffusion models), working in the low data regime and with 3D medical image data are assets. An innovative spirit and team player skills round off your profile.

We are a dynamic and international team embedded in information technology, electrical engineering and the medical faculty, with a long-standing track record in CMR research. First-class infrastructure is available, including experimental and clinical MR systems fully dedicated to research, state-of-the-art local and scalable cloud-based compute infrastructure (CPU, GPU) and workshops for mechanical, electrical and electronic development projects. Long-standing and very successful cooperations with industry and clinical partners (cardiology, radiology) offer opportunities for networking as well as for deployment of research results in real-world applications.

In line with our values, ETH Zurich encourages an inclusive culture. We promote equality of opportunity, value diversity and nurture a working and learning environment in which the rights and dignity of all our staff and students are respected. Visit our to find out how we ensure a fair and open environment that allows everyone to grow and flourish.