PhD Studentship (3 years) In Vivo Diagnosis of Paediatric Brain Tumours using Multi-Modal Clinical MRI and Machine Learning

Location: Aston University Main Campus

Closing Date: 23.59 hours BST on Thursday 30 June 2022. May close earlier if a successful candidate is recruited.

Supervisor: Dr Jan Novak

Applications are invited for a three-year Postgraduate studentship, supported by Help Harry Help Others (HHHO) and the College of Health and Life Sciences, to be undertaken within the Artificial Intelligence in Paediatric Neuroimaging (AIPNI) Research Group at Aston University. The successful applicant will join an established experimental group working on machine learning methods for paediatric neuroimaging.

The position is available to start in October 2022 

This studentship includes a fee bursary to cover the home fees rate, plus a maintenance allowance of £16,062 in 2022/3 (subject to eligibility). Overseas applicants may apply for this studentship but will need to pay the difference between the ‘Home’ and ‘Overseas’ tuition fees. Currently the difference between ‘Home’ and ‘Overseas’ annual tuition fee is £14,054. As part of the application, you will be required to confirm that you have applied for or secured this additional funding.

Background

Despite the prognostic benefits of early diagnosis, histopathological analysis performed post-resection is the current gold standard for the differential diagnosis of paediatric brain tumours. Advances in non-invasive, pre-surgical diagnostic methods are thus required to inform tumour resection, consequently improving patient outcomes. The proposed research will utilise advanced magnetic resonance imaging (MRI) techniques, including magnetic resonance spectroscopy (MRS), diffusion-weighted imaging (DWI) and perfusion-weighted imaging (PWI), to develop a diagnostic classification tool that improves pre-surgical posterior fossa tumour diagnosis in children. Machine learning algorithms will be used to determine which MRI technique, or combination of multi-modal techniques, has the highest diagnostic accuracy to produce the optimal differential diagnostic classifier. Subsequent employment of data harmonisation procedures will further optimise the machine learning classifier for heterogeneous, incomplete data that simulates clinical “realities”, thus determining the potential for future clinical implementation. Neuroradiologist collaborators will then provide recommended diagnoses following the examination of two individual groups of paediatric brain tumour MRI datasets, of which only one will incorporate the diagnostic classifier outputs. The accuracy of diagnosis will be compared between the datasets to identify any changes in diagnostic certainty attributable to inclusion of the classifier outputs. The end-goal of this project is to therefore establish a method of improving pre-surgical paediatric brain tumour diagnosis through the development of a prototype machine learning diagnostic classifier that provides accurate, early diagnostic information. This classifier will have the potential for substantial clinical impact, informing the surgical management of paediatric brain tumour cases and thus improving patient outcomes.

Person Specification

The successful applicant should have been awarded, or expect to achieve, a degree in a relevant subject with a 60% or higher weighted average, and/or a First or Upper Second Class Honours degree (or an equivalent qualification from an overseas institution) in Psychology, Physics, Chemistry, Neuroscience, Computer Science or any relevant scientific subject. Preferred skill requirements include knowledge/experience of Nuclear Magnetic Resonance (NMR or MRI), programming, image analysis and data manipulation.

Details of how to submit your application, and the necessary supporting documents, can be found here . 

For formal enquiries contact Dr Jan Novak by email at [email protected] .

For questions about the application process contact [email protected]