Unlocking the Full Potential of EEG: A Data-Driven Approach to Functional Neuroimaging in the Absence of MRI

Quantitative methods for studying human brain function are foundational to modern neuroscience. Among these, electroencephalography (EEG) stands out as a non-invasive technique that measures the brain’s electromagnetic activity, offering crucial insights for both research and clinical applications. EEG is particularly invaluable in localising brain regions responsible for pathological activity, making it essential for diagnosing and treating neurological conditions like epilepsy.

The accuracy of EEG in characterising cerebral current generators and informing optimal treatments relies heavily on computational head models. These models require accurate descriptions of the participant’s head tissue geometries and electrical properties, which are traditionally obtained through magnetic resonance imaging (MRI). Unfortunately, the high costs associated with MRI equipment and data acquisition significantly limit the accessibility of this complementary imaging technique, restricting the full application of EEG to a small fraction of health and research centres.

This studentship aims to overcome these barriers by developing a novel, data-driven solution for generating head models in the absence of MRI data. Leveraging existing MRI datasets and advanced artificial intelligence algorithms, the candidate will create statistically plausible computational head models based on easily accessible participant data, such as EEG electrode positions on the scalp. Different methods will be evaluated for the creation of such models, ranging from principal component analysis and convolutional neural networks to deep learning. The methodology will be rigorously tested with new data collected during the project, assessing its effectiveness and reliability.

Ultimately, this project seeks to expand the use of EEG as a powerful neuroimaging tool, enabling its application in remote and/or resource-limited areas where access to expensive imaging equipment is not possible, such as in Low- and Middle-Income Countries (LMICs) where MRI scanners are often unavailable. By democratising neuroimaging technology, this research has the potential to make a profound impact on both global health and neuroscience research.

Project timeline:

·        Year 0-1: Training (EEG processing, computational head model construction). Implementation of the ML algorithm to characterise basic head models from the electrode positions (and archival MRI data).

·        Year 1-2: Training (MRI processing to extract tissues’ density data). Incorporation of nonstandard tissues into the head models.

·        Year 2-3.5 Determination of electrical conductivities through efficient numerical simulations. Evaluation of the clinical feasibility of the technique. Thesis writing.

The results will be disseminated through journal papers and international conferences.

This project would suit students interested in applying machine learning methods in neuroscience. The successful candidate will work at the vibrant and diverse Cardiff University Brain Research Imaging Centre (CUBRIC), a multidisciplinary environment, housing physicists, engineers, neuroscientists, psychologists and clinicians. The student will access state-of-the-art imaging technology, including EEG and MRI scanners, and get training and hands-on experience with instrument use for human data collection, preparing them for an exciting career in research or industry. Moreover, they will freely access over 350 Doctoral Academy training courses to develop professionally and personally, as well as seminars/journal clubs at CUBRIC and national/international conferences. Through regular lab meetings, the candidate will learn about the ethical and legal considerations of working with human data, discuss the societal impacts of the research, and take part in wider PPI (patient and public involvement) and public engagement initiatives. The unique combination of machine learning and neuroscience expertise gained from this project will open doors to diverse career paths, from tech companies focusing on AI-driven healthcare solutions to research institutions and clinical settings involved in advancing our understanding and treatment of neurological disorders.

The candidate will benefit from the collaboration network of the supervisory team, including clinical and technical experts in the field working in Europe, South America, and Africa.

The student will be encouraged and provided with funding to present at conferences. The supervisory team can apply for funding for carers to attend, if needed. To prepare, CUBRIC has many research groupings to present work to, comprised of PhD peers and colleagues at higher levels, providing the student with the support to excel. The lab and CUBRIC have many social events that cater for all people, interests, and availabilities, from pub/dinner nights to board games evenings to lunchtime yoga. This PhD project has been designed to be flexible and is well suited to remote working.

How to apply:

Applicants should apply to the Doctor of Philosophy in Physics and Astronomy with a start date of 1st January 2025. 

Applicants should submit an application for postgraduate study via the Cardiff University webpages (https://www.cardiff.ac.uk/study/postgraduate/research/programmes/programme/physics-and-astronomy) including: 

• your academic CV

• Your degree certificates and transcripts to date including certified translations if these are not in English 

• two references, at least one of which should be academic. Your references can be emailed by the referee to physics-admissions@cardiff.ac.uk  

Please note: We are do not contact referees directly for references for each applicant due to the volume of applications we receive.  

 • personal statement

The typical academic requirement is a minimum of a 2:1 physics and astronomy or a relevant discipline. 

Applicants whose first language is not English are normally expected to meet the minimum University requirements (e.g. IELTS 6.5 Overall with 5.5 minimum in sub-scores) (https://www.cardiff.ac.uk/study/international/english-language-requirements) 

In the “Research Proposal” section of your application, please specify the project title and supervisors of this project.

In the funding section, please select that you will not be self-funding and write that the source of funding will be EPSRC. 

Once the deadline for applications has passed, we will review your application and advise you within a few weeks if you have been shortlisted for an interview. 

Eligibility :

EPSRC DTP studentships are available to home and international students. Up to 30% of our cohort can comprise international students, once the limit has been reached we are unable to make offers to international students. International students will not be charged the fee difference between the UK and international rate. Applicants should satisfy the UKRI eligibility requirements.

For more information, or if there are any questions, please contact Physics and Astronomy PGR Student Support team at Physics-PG@cardiff.ac.uk

Please also check the following link: https://www.cardiff.ac.uk/study/postgraduate/funding/research-councils/epsrc-studentships