Skip to content
01 Aug

STUDENTSHIP IN DEEP GENERATIVE MODELLING OF BRAIN MAGNETIC RESONANCE IMAGING FOR RAPID DIAGNOSIS & TRIAGE IN ACUTE NEUROLOGY

Named Projects

Though generally superior to all other imaging modalities, the clinical use of magnetic resonance imaging of the brain is constrained by the limited tolerability of the relatively long acquisition times it requires. Where tolerability is further reduced by illness—very commonly in acute neurology—either less informative modalities must be substituted or life support must be invoked with potential risks to the patient. There is therefore a need for expedited magnetic resonance imaging, minimizing the scanning time needed to inform critical decisions in acute neurology—e.g. the presence or absence of acute ischaemia in suspected stroke—while maximising the extraction of predictors of value to longer term management—e.g. length of stay or rehabilitation dose. Though acquisition times are already highly optimised, the reconstruction of images currently does not incorporate sufficient prior information on the space of possible appearances to enable the generation of high-quality representation of the brain from relatively sparse data. Deep learning can be deployed here to super-resolve and quality-enhance fast, economically-specified imaging, with specific attention to imaging features on which subsequent decision-making can rely, both for clinical care and operational purposes.

This studentship will develop deep generative models of magnetic resonance brain imaging with the objective of enabling fast, resolution- and quality-enhanced decision-making in acute neurology by maximizing extracted information on acute grey and white matter injury. A real-world implementation at our partner hospitals, within the context of operational use, will be delivered in the final third of the project.

Person Specification
Applications are invited for an ambitious, fully-funded PhD studentship at the EPSRC Centre for Doctoral Training in Medical Imaging, University College London (UCL), commencing on -01/10/2018.

We particularly welcome applications from individuals with a strong background in computing, machine learning, mathematical, or physical sciences, and highly motivated to pursue research with near-term, real-world translational objectives.

The studentship will be based at the UCL Department of Computer Science and Centre for Medical Image Computing at UCL, and the High-Dimensional Neurology Group at the UCL Institute of Neurology, with funding from the UCLH NIHR Biomedical Research Centre and the Engineering and Physical Sciences Research Council.

The successful candidate will join a multi-disciplinary team applying novel modelling approaches to very large-scale clinical data for real-world, translational applications. The project is aligned with UCLH’s Research Hospital Initiative, which seeks to accelerate the introduction of artificial intelligence within the hospital for clinical, operational, and scientific benefit. It will draw on state-of the-art expertise in magnetic resonance—especially diffusion-weighted—imaging (Gary Zhang’s group), and deep generative modelling of clinical imaging (Parashkev Nachev’s group). It will be enabled by large-scale clinical data from UCH and NHNN, including the UK’s largest stream of comprehensively MR-imaged patients with suspected stroke, and will be powered by a 1.5 teraFLOP, hospital-embedded GPU-based computational infrastructure.

The project represents an ideal opportunity for a talented and highly-motivated individual to develop a breadth of modelling skills, working on unique datasets, assisted by high-performance hardware, with real-world, near-term, practical impact on healthcare.

The candidate must be UK passport holders, or be an EU citizen who has been in the UK for 3 consecutive years at the time of application. The required qualifications can be found here.

How to apply
Interested applicants are invited to email Dr Gary Zhang (gary.zhang@ucl.ac.uk) or Dr Parashkev Nachev (p.nachev@ucl.ac.uk) to discuss the applications informally. Please include, in the first correspondence, a copy of the CV and a one-page letter of motivation explaining your interest and fit to the studentship.

Deadline: 23/08/18