Machine learning and multimodal imaging to build predictive models of deep brain stimulation for movement disorders
Deep brain stimulation (DBS) is an established therapeutic technique in the treatment of several neurological disorders, however; the success of the procedure hinges on proper selection of patients and accurate lead placement with stimulation of nerve cells and pathways within a small region, whilst avoiding spread of current to nearby structures, which can cause unwanted physical and/or psychiatric side effects.
Functional and structural MRI connectivity features predictive of outcome have been identified on the group level using patient specific connectomes and normative, non-specific connectomes. These models are able to predict the spatial location, configuration and voltage of the optimal electrode configurations for a given symptom/region and define the properties of the networks being influenced by DBS, potentially aiding in patient selection. These studies were conducted with the use of standard, quadripolar DBS leads (i.e. each DBS lead has four contacts delivering a spherical stimulation field).
The main aim of this project is to utilise the findings from previous DBS connectivity studies first in order to build predictive outcome models to aid with individual patient and DBS target selection. The final models will be validated and applied to clinical practice, this time using novel directional DBS leads which allow for current steering.
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 01/10/2018.
We particularly welcome applications from individuals with a strong background in neuroscience, computing, mathematical or physical sciences, and are highly motivated to pursue academic research.
The studentship will be based at the Wellcome Trust Centre for Neuroimaging (Institute of Neurology) with direct collaboration with the Unit of Functional Neurosurgery and the Centre for Medical Image Computing at UCL with funding from the Engineering and Physical Sciences Research Council and the Brain Research Trust. The successful candidate will join a multi-disciplinary team of clinician scientists (Dr Harith Akram, Dr Ludvic Zrinzo and Dr Christian Lambert) and computer scientists (Prof John Ashburner and Dr Gary Zhang) to develop predictive models of deep brain stimulation therapy using multimodal MR imaging technique, patient demographics and clinical outcome measures within a state-of-the-art machine learning framework. The project 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.
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 Harith Akram (email@example.com) or Prof John Ashburner (firstname.lastname@example.org) 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.