PhD Studentship in Machine Learning and Compressed Sensing for Next-Generation Microstructure Imaging
Application Closing Date: June 30th, 2017
PhD Start date and Duration: 4-year studentship from September 25th, 2017
Stipend: £16,851 per annum, tax free, and full fees paid
Applications are invited for an exciting fully-funded PhD studentship at the EPSRC Centre for Doctoral Training in Medical Imaging, University College London (UCL), commencing in September 25th, 2017.
We particularly welcome applications from individuals with a strong background in computing, mathematical or physical sciences, and highly motivated to pursue academic research.
The studentship will be based in the Microstructure Imaging Group of the Centre for Medical Image Computing at UCL, with an industrial partnership with the Philips Research Hamburg, and funding from the Engineering and Physical Sciences Research Council.
The successful candidate will join a multi-disciplinary team to develop the next-generation microstructure imaging techniques based on MRI. The project will leverage the state-of-the-art in machine learning, compressed sensing and biophysical modelling. It will provide an ideal opportunity for any talented and motivated individual to develop technical skills and gain practical experiences in these cutting-edge areas of research.
Details of Research project
Microstructure imaging is a recent paradigm of designing non-invasive imaging techniques that can directly produce 3-D maps of biological features of bodily tissue in living beings. The ultimate aim is to achieve virtual histology, i.e., to create these maps of such fidelity that they can one day replace highly-invasive biopsy procedures which are required today to establish firm diagnosis in many diseases.
The current-generation techniques, such as neurite orientation dispersion and density imaging (NODDI), have shown the great potential of the microstructure imaging paradigm. But to fully realize this potential, a number of key challenges remain to be overcome. These include a reliance on a single MRI contrast (known as the diffusion MRI), the lengthy time to acquire the data, and the computational burden to produce the relevant 3-D maps from the data.
This studentship will address these major challenges with a multi-pronged attack. It will combine diffusion MRI with other complementary contrasts, by taking a multi-modal approach to modelling. It will investigate state-of-the-art approaches in compressed sensing, including the recently proposed magnetic resonance fingerprinting, to dramatically shorten the window of data acquisition. It will leverage state-of-the-art developments in machine learning, such as deep learning, to generate accurate maps of tissue microstructure in real time.
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 (email@example.com) 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.