OPTIMAL-RT - Optimising and Personalising Treatment though multi-modal analysis of radiotherapy for rare cancers

A2003284

This project aims to improve radiotherapy treatment for rare cancers such as anal cancer, glioblastoma (brain cancer), and hepatocellular carcinoma (liver cancer) by combining patient records, scans, and biopsy data to identify biomarkers that predict treatment response and side effects. Initially focused on anal cancer patients from Leeds and clinical trials, the project uses advanced data science techniques including federated learning to validate findings with international collaborators while protecting patient privacy. Federated learning is a way for researchers to collaborate and learn from patient data stored in different hospitals or countries without sharing the actual data itself.

By integrating local and global data, the team hopes to develop personalised radiotherapy plans tailored to each patient’s tumour characteristics, optimising treatment effectiveness and minimising harmful side effects. This research is closely linked to clinical care at Leeds and builds on the expertise of the UK’s Cancer Research UK supported RadNet Leeds centre.

Funding will support a data scientist position to ensure the seamless handling and analysis of multimodal data, helping to translate research into better outcomes for patients locally and worldwide.

Lead Researcher	Professor David Sebag-Montefiore Audrey and Stanley Burton Professor of Clinical Oncology and Health Research
Co-Researchers	Associate Professor Ane Appelt Professor Andrew Scarsbrook  Dr Basha Al-Qaisieh Associate Professor Nicolas West
Host Organisation	University of Leeds
Grant Amount	£95,887.00
Start Date	01/07/2025
Estimated Duration	36 months
Impact Areas	Health Inequalities - Cancer Care
Tags/key notes	Cancer and Neoplasms