Skip to main content





Compact and mobile scanners are changing workflows in radiology, where MRI comes to the patient rather than the patient to the MRI.
In this project we will establish the necessary metrological framework for the harmonised development of clinical low-field MRI.

Read more

Low-field MRI

In this project we will design, develop and evaluate mobile (< 300 kg), low-cost (< 50 k€) and fully replicable low-field MRI reference systems (main static field B0 ≈ 50 mT), including all the necessary software to carry out imaging studies. The low-field scanners will be capable of imaging the human head and extremities. A full characterisation of these reference systems by metrologically validated methods including B0, radiofrequency and switched gradient fields will be carried out. Hardware and software will be made available through open-source licence models.

Model-based Deep Learning

Machine learning has shown great potential for medical image reconstruction. We will develop methods for quantitative imaging of biophysical parameters by combining hardware models and MR signal models with physics-informed deep learning approaches. The techniques will be available via an open cloud-based platform. This will also facilitate reproducibility studies and allow for benchmarking of other low-field systems.

Clinical suitability

We will carry out multisite reproducibility studies of the constructed low-field MR scanners under different operational conditions (e.g., thermal fluctuations or electromagnetic interferences) and compare their performance to commercially available low-field MR systems (B0 = 0.05 - 0.6 T) in inter-vendor comparisons.


To pave the way for clinical application of open-source low-field MR systems, we will draft the technical documentation for the design and production process in accordance with the requirements of the EU medical device regulation (EU)2017/745. The complete documentation of the system will be made available under open-source licences.