Learning MRI Biomarkers for Paediatric Cochlear Implant Outcomes (25002)

Learning MRI Biomarkers for Paediatric Cochlear Implant Outcomes (25002)

Primary Supervisor: Dr Sophia Bano

Secondary Supervisor: Prof Nish Mehta

A fully funded PhD studentship is available for Home Fee applicants in the UCL Centre for Doctoral Training (CDT) in Intelligent, Integrated Imaging in Healthcare (i4Health). Funding will be at least the UCL Minimum Stipend rate and Home Tuition Fees. Stipend details can be found here. 

Funding is available from February 2026 - September 2029.

The successful candidate will join our MPhil/PhD Medical Imaging programme (the application portal can be found on the prospectus page).

The project will be based at UCL Hawkes Institute, where students will have access to cutting-edge research facilities, high performance computing resources and expert mentorship.

Project background

Early identification and cochlear implantation (typically before age two) enable many deaf children to develop spoken language. Yet a meaningful minority achieve limited speech outcomes despite timely surgery, and the reasons remain incompletely understood. Known risk factors such as severity of hearing loss, and age at implantation account for only part of the variance in outcomes. Because candidates are often under one year old, their pre-operative functional status is difficult to assess. Meanwhile, all children undergoing cochlear implantation receive pre-operative brain MRI to confirm inner-ear anatomy and exclude malformations. 

Reliable forecasting of speech outcomes is therefore crucial as it could support families making difficult decisions and help tailor auditory rehabilitation to each child’s needs. We have assembled a large dataset of pre-operative paediatric brain MRIs linked to post-implant speech outcomes. This studentship will evaluate brain MRI as a predictor of language and speech development after implantation, exploring both conventional machine-learning and modern vision-transformer approaches, with attention to interpretability and clinical usability. 

Research aims

• Build and validate MRI-based predictive models of post-implant speech outcomes in deaf children. 

• Identify neuroanatomical biomarkers linked to language development, with model interpretability analyses. 

• Benchmark classical machine learning vs. modern vision transformers on MRI from children of varying age (8-15 months) and assess their generalisability. 

• Translate findings into a prototype decision-support tool for personalised rehabilitation. 

Person specification & requirements

• Degree: First or upper-second class Bachelor’s (or international equivalent) in Biomedical Engineering, Computer Science, Medical Imaging, Physics, or related field. 

• Skills (required): Computer Vision; Machine and Deep Learning, Python, PyTorch/TensorFlow; version control; clear scientific writing. 

• Experience: Handling large datasets; evidence of initiative and reproducible research (e.g., code repositories, preprints). 

• Eligibility: The studentship is only open to Home Fee-paying candidates. More information about fee status criteria can be found here.  

Funding

This is a full studentship available to Home Fee applicants only. Please see the page on UCL fee status here.

The successful student will receive a stipend starting from at least the UCL minimum (£22,780 in 2025/26) as well as the cost of tuition fees for Home fee students (£6,215 in 2025/26). 

The stipends awarded to PhD students at UCL are tax free and incur no income tax or national insurance contributions. The amount received increases each year over the duration of the studentship. 

How to apply:

Application Deadline: Friday 7th November 2025

Please complete the following steps to apply.

•    Send an expression of interest and current CV to Clare Woolley (c.woolley@ucl.ac.uk) and cdtadmin@ucl.ac.uk, quoting Project Code 25002 in the email subject line.
•    Make a formal application via the UCL application portal: Apply | Prospective Students Graduate - UCL – University College London. Please select the programme code ‘Medical Imaging RRDMEISING01’ and enter Project Code 25002 under ‘Name of Award 1’ 
•    If shortlisted, candidates will be invited for an interview.

Application Timeline:

•    After the deadline, all applicants that expressed their interests and specified Project 25002 in their Portico application will be considered for interview.
•    Candidates will normally be invited for interview within three weeks of the deadline. If you have not been contacted within this time-period, you have unfortunately not been successful in being shortlisted.
•    The interview panel will normally consist of the supervision team on the project. 
•    Note that applications without specifying the project they are applying for and/or making a formal Portico application will be automatically rejected.
•    If you are offered and accept a studentship position, a formal UCL Offer of Admission will be sent to you as well as an offer of studentship funding.