2026-27 Project (Howe & Barrick & Tarroni)

Synthetic modelling of glial brain tumour MRI for improved analysis by AI

SUPERVISORY TEAM

Supervisor

Professor Franklyn Howe at City St George’s
School of Health & Medical Sciences, Department of Psychology and Neuroscience
Email: howefa@sgul.ac.uk

Co-Supervisor

Dr Tom Barrick at City St George’s
School of Health & Medical Sciences, Department of Psychology and Neuroscience
Email: tbarrick@sgul.ac.uk

Co-Supervisor

Dr Giacomo Tarroni at City St George’s
School of Science & Technology, Department of Computer Science
Email: Giacomo.Tarroni@citystgeorges.ac.uk

PROJECT SUMMARY

Project Summary

This is an exciting opportunity to join a translational MRI research group (Tooting campus) who are working with an Artificial Intelligence and Computer Science group (Clerkenwell campus).    You will investigate how a 3D growth model can be used to generate synthetic MRI of brain tumours. Quantitative multimodal MRI will enable development and validation of the model. The model will used to enable more interpretable AI methods to aid diagnosis and improved radiological interpretations of growth.    You will join a multidisciplinary research team of computer scientists, MRI physicists and mathematicians who collaborate with neurosurgeons and neuroradiologists.    You will have a background in computer science, physics or mathematics, with strong programming skills (preferably in Python) and experience in mathematical models or AI. You will  have a desire to develop new technology into practical clinical tools that aid the neuro-radiological and -oncological teams managing the care and treatment of brain tumour patients.

Project Key Words

Cancer, MRI, AI, neuroradiology

MRC LID Themes

  1. Health Data Science

Skills

MRC Core Skills

  1. Quantitative skills
  2. Interdisciplinary skills
  3. Whole organism physiology

Skills we expect a student to develop/acquire whilst pursuing this project:

  • Develop a strong theoretical understanding in the physics of MRI and imaging methods for brain tumours.
  • Develop practical skills in computer modelling of tumour growth and generation of synthetic MRI data.
  • Develop a strong understanding of AI analysis methods with their application to neuroimaging data
  • Develop a basic understanding of brain tumour biology, radiological and pathological diagnostic methods, treatments and patient outcomes.
  • Learn how to interact effectively within a multi-disciplinary team of clinical, biomedical and computer science experts.
  • Understand and comply with ethical and information governance regulations of patient data.
  • Develop skills to effectively present complex image analysis methodology to general scientific and clinical audiences and presentation of results and preparation of papers for expert peer review.

Routes

Which route/s are available with this project?

  • 1+4 = Yes
  • +4 = Yes

Possible Master’s programme options identified by supervisory team for 1+4 applicants:

  • City St George’s – MSc Data Science

Full-time/Part-time Study

Is this project available for full-time study? Yes
Is this project available for part-time study? Yes

Location & Travel

Students funded through MRC LID are expected to work on site at their primary institution. At a minimum, all students must meet the institutional research degree regulations and expectations about onsite working and under this scheme they may be expected to work onsite (in-person) more frequently.
Students may also be required to travel for conferences (up to 3 over the duration of the studentship), and for any required training for research degree study and training. Other travel expectations and opportunities highlighted by the supervisory team are noted below.

Day-to-day work (primary location) for the duration of this research degree project will be at: City St George’s – Tooting campus, London

Travel requirements for this project: Visits to our clinical collaborators in NHS Trust sites to understand how MRI is used in surgical planning (SGH) and radiotherapy planning (RMH). We will utilise our varied contacts to get an industry perspective of AI medical image analysis software, such as an MRI company and an image analysis company.

Eligibility/Requirements

Particular prior educational requirements for a student undertaking this project

  • Minimum standard institutional eligibility criteria for doctoral study at City St George’s
  • Minimum 2:1 honours BSc in a scientific discipline with a strong computing as well as good physics and mathematics components: computer science, physics, mathematics, engineering, etc. Ideally with an MSc or other research/industry experience that incorporated MRI or AI.

Other useful information

  • Potential Industrial CASE (iCASE) conversion? = No

PROJECT IN MORE DETAIL

Scientific description of this research project

OBJECTIVES
Glioma, the most common primary brain tumour, causes major mortality and morbidity due to its infiltrative nature. Survival varies from six months for aggressive glioblastoma to over a decade for low-grade subtypes. MRI is central to diagnosis and management, with AI increasingly applied for subtype prediction and automated delineation of tumour boundaries. Automated segmentation enables objective radiomic feature extraction, monitoring of tumour size, and prioritisation of abnormal regions in clinical workflows. Current AI training relies on databases (e.g. BraTS), where delineations are subjective. However, large, annotated datasets are needed, MRI technology evolves, and AI interpretability remains a challenge. Our novel approach aims to develop a biophysical model that generate synthetic gliomas of arbitrary size and location that, with MRI physics, creates synthetic MR images. This will produce unlimited datasets, with objectively defined ground-truth of tumour heterogeneity and margins, for AI development, optimisation, and training under controlled conditions. The model will aid development of tumour growth prediction methodologies.

TECHNIQUES
We will use the diffusion-reaction tumour growth model (1) constrained by white and grey matter anatomy (2). A wide variery of tumours will be generated via random seeding, heterogeneous growth parameters, and inclusion of cystic regions. A large in-house MRI database supports model development: (i) 50 gliomas with progression data; (ii) 88 with quantitative T1, T2, PD, and diffusion imaging; (iii) 96 with diffusion, T2, and genetic subtyping; (iv) 301 multimodal clinical scans (MRS, diffusion, perfusion). Our prior work with 1H MR Spectroscopy (3) informs how cellular composition maps to MRI characteristics, and diffusion MRI aids modelling infiltration along white matter tracts, to generate T1w, T2w, and FLAIR images. Synthetic brain tumour images will support development and optimisation of AI/ML tasks that require defined interpretability for actual clinical use. Our AI-based DISYRE method (4) for automated detection of tumour regions and superpixel segmentation method (5) are suitable candidates to further develop and assess robustness across variable tumour morphology, imaging protocols, infiltrative degree, partial volume effects, texture and noise. Synthetic images with our longitudinal growth study data will enable development and assessment of methods to accurately measure tumour growth.

DATABASES
Our MRI datasets will be supplemented by public resources such as the MICCAI BraTS and The Cancer Imaging Archive.

RISKS
Tumour growth is complex and heterogeneous, so the model will have limits. Nonetheless, the tool will provide valuable simulations to test how image variations, heterogeneity, and acquisition artifacts affect segmentation algorithms, guiding optimisation for real-world use and improving AI interpretability.

ENVIRONMENT
The project unites MRI researchers (Tooting), with links to neuroradiology, radiotherapy and neurosurgery teams in NHS Trusts, and AI expertise (Clerkenwell). Brain tumour research is a strategic focus in the Division of Translational Neuroscience. The student will have scope to explore diverse applications of AI to brain tumour MRI, using the growth model as a foundation for novel research.

REFERENCES

  1. Swanson et al. Cell Prolif. 2000;33:317-329
  2. Clatz et al. IEEE Trans Med Imaging. 2005;24:1334-1346.
  3. Raschke et al. NeuroImage: Clinical. 2019;21:101648
  4. Naval Marimont et al. 2024 IEEE International Symposium on Biomedical Imaging, pp. 1-5, doi: 10.1109/ISBI56570.2024.10635161.
  5. Soltaninejad et al. Computer Methods and Programs in Biomedicine. 2018;157: 69-84

Further reading

Relevant preprints and/or open access articles:
(DOI = Digital Object Identifier)

Other pre-application materials: None

Additional information from the supervisory team

The supervisory team has provided a recording for prospective applicants who are interested in their project. This recording should be watched before any discussions begin with the supervisory team.

Howe & Barrick & Tarroni Recording

MRC LID LINKS

To apply for a studentship: MRC LID How to Apply
Full list of available projects: MRC LID Projects
For more information about the DTP: MRC LID About Us

Comments are closed.