Oxford University Innovation Ltd

Iulia Andreia Popescu

Stefan Piechnik

Qiang Zhang

Vanessa Ferreira

Evan Hann

Konrad Werys

A method and apparatus for enhancing magnetic resonance images to produce contrast-enhanced images without the need to administer contrast agent to a patient. The image processing apparatus utilises a trained machine learning algorithm as an image processor, preferably a generative adversarial network, to produce images from contrast agent-free magnetic resonance images with the produced images having similar appearance and better image quality and better pathological sensitivity and being able to differentiate more pathological conditions than actually acquired contrast-enhanced images.

Enhancement of medical images

A validation technique for quality assurance of quantitative MRI methods by comparing the measured magnetic properties of a phantom having a range of T1 and T2 values measured by an accelerated, clinically-practicable protocol with predicted values for that magnetic property calculated from a set of reference T1 and T2 values measured on the phantom. The prediction is based on a relationship between the values from the accelerated protocol and values from the reference measurements obtained by repeatedly scanning one or more phantoms.

Growing community of inventors

Oxford, United Kingdom

Iulia Andreia Popescu