Personalised and Adaptive Radiotherapy
Our vision is to revolutionise cancer care to provide smarter, kinder treatment through cutting-edge technology, driving towards personalised radiotherapy for all patients. We will pioneer computational discovery science, benefiting future cancer patients globally. We will build upon previous RadNet-funded work on AI-driven image segmentation and motion modelling and use our state-of-the-art infrastructure, including dedicated radiotherapy MRI Sim, to drive imaging innovation (kV/MR) and computational modelling/AI for 3D tumour growth prediction. With Theme 3, we will advance precision radiotherapy using large-scale real-world data, incorporating imaging and biological insights through federated learning.
This will build on our international leadership position in federated learning for rare cancers, established through CRUK-supported infrastructure, as well as our expertise in AI-driven radiotherapy outcome modelling. We will validate discovery research from trial populations in real-world populations, create 3D models for personalised treatment planning, and develop outcome prediction models for precise treatment stratification.
Future impact – Improved cancer outcomes and reduced toxicity for rare, complex and poor outcome disease.
Theme Leads
Professor Ann Henry (Co-Lead)
Professor, Clinical Oncology
Staff Profile: Professor Ann Henry | School of Medicine | University of Leeds
I am a Professor in Clinical Oncology at the University of Leeds and Honorary Consultant Clinical Oncologist at Leeds Teaching Hospitals NHS Trust. I specialise in the radiation treatment of urological cancers. My research optimises radiation treatments to improve overall survival and reduce treatment related side effects.
My research interests are personalised radiotherapy delivery, radiotherapy clinical trials and patient reported outcomes. My technical radiotherapy research areas are optimising treatment delivery for pelvic cancers by incorporating MR imaging, using Intensity Modulated Radiotherapy (IMRT) and Image Guided Radiotherapy (IGRT) and delivering image guided brachytherapy (IGBT).
Dr Bashar Al-Qaisieh (Co-Lead)
Lead in Radiotherapy Imaging
Staff Profile: Dr Bashar Al-Qaisieh | Lead Radiotherapy Imaging, R&D | Leeds Cancer Centre
Professor Andrew Scarsbrook (Co-Lead)
Professor of Radiology; Honorary Consultant Radiologist; Nuclear Medicine Physician
Staff Profile: Professor Andrew Scarsbrook
I am a Professor of Radiology at the University of Leeds and an Honorary Consultant Radiologist and Nuclear Medicine Physician at Leeds Teaching Hospitals NHS Trust. I am the Academic Radiology Training Programme Director of a thriving integrated clinical-academic and allied health professional pathway encompassing Academic Foundation posts, NIHR-funded Academic Clinical Fellowships and externally funded PhD fellowships. My group leads clinically focused imaging research in collaboration with inter-disciplinary groups at the University (Leeds Cancer Research Centre; Radiotherapy Research Group; Artificial Intelligence (AI) Centre for Doctoral Training; Leeds Clinical Trials Research Unit; Tessa Jowell Centre of Excellence for Brain Cancer Research).
We have close links with the Leeds NIHR Biomedical Research Centre and Research and Innovation at Leeds Teaching Hospitals with Radiology leading a multi-disciplinary clinical AI board and several industry-academic research studies aligned to imaging-related AI. There is strategic alignment with key research priorities related to radiotherapy, clinical trials and AI to maximise impact and potential for clinical translation and patient benefit.
Work Stream 1 – Image-guided precision radiotherapy
Workstream 1 focuses on predicting and addressing on-treatment motion and expanding AI-driven prediction modelling for 3D tumour growth and response mechanisms.
WS1 Lead Researchers
Dr Robbie Samuel
I am a clinical oncology specialist trainee in the West Yorkshire programme, currently undertaking a PhD entitled ‘Rationally developing the next generation of personalised target drug-chemotherapy combination trials in anal cancer’. I am interested in early phase translational trials in lower GI cancer using novel radiotherapy-drug combinations.
Dr Michael Nix
Clinical Scientist and Radiotherapy Physicist
I am a RadNet Principal Clinical R&D Scientist at Leeds Teaching Hospitals NHS Trust (LTHT) and an honorary researcher at University of Leeds, where I am leading development of innovative deep-learning methodologies for radiotherapy imaging and adaptive therapy, alongside tools for clinical confidence estimation and effective translation. Our primary interest is in motion modelling and management, including deformable registration and AI motion prediction for in-treatment motion compensation. This work focusses on liver RT, aiming to improve treatment outcomes for a rare cancer group with cancers which are hard to treat using current methods.
I am also involved in the development of new tools for robust dose accumulation and re-planning in radiotherapy, with applications in re-irradiation and brachytherapy. These tools are being developed within the RadNet collaboration and with commercial partners RaySearch.
Within LTHT, I lead the development, evaluation and implementation of clinical AI technologies in Radiotherapy, in collaboration with commercial partners. This includes the rollout of AI auto-contouring, a critical time-saving technology, freeing clinicians and technical staff from the time-consuming need to manually draw around internal organs on medical images. I am also involved in the AI group, focussed on the safe and effective implementation of AI technologies across radiology and oncology.
I was previously a Clinical Fellow with NHSE, researching skills-gaps and developing educational strategies around robust and confident AI implementation for healthcare, following a year as one of the inaugural NHS Topol Fellows in Digital Health. This work continues, with a particular focus on human-system interactions and cognitive biases in AI for healthcare, and real-world evaluation of clinician preferences and efficiency gains in the use of AI.
Dr Jim Zhong
Post Doc Research Fellow
Staff profile: Dr Jim Zhong | Leeds Institute of Medical Research | University of Leeds
Work Stream 2 – Federated and deep learning for multi-modal outcome prediction
Workstream 2 aims to use multimodal data for outcome prediction modelling, to understand drivers of cancer
outcomes in rarer cancers for treatment personalisation. Workstream 2 works with Theme 3, validating discovery
science from trial cohort in multi-institutional real-world data through federated learning.
WS2 Lead Researchers
Dr Ane Appelt
Associate Professor, Radiotherapy Physics
Staff Profile: Dr Ane Appelt | School of Medicine | University of Leeds
I am a cancer researcher, clinical trialist, and medical physicist. My research focuses on improving patient outcomes through the development and implementation of optimised treatment strategies and novel technological innovations in radiotherapy. My interests include reirradiation, radiotherapy for organ preservation, clinical trial design and delivery, and the application of data science in radiation oncology. I am a strong advocate for research that is both clinically relevant and translatable into practice. This includes a core belief in the importance of clinical trials as a critical means for evaluating radiotherapy innovation. I lead a competitively funded, multicentre, randomised dose-escalation trial in rectal cancer and am involved in over a dozen other trials. I am primary or co-investigator on active grants totalling over £5.6 million.
As well as leading Theme 1’s Work Stream 2, I am joint lead for RadNet Leeds Theme 2 (“Reirradiation: From discovery to delivery”), where I focus on translation of novel reirradiation technology into the clinic.
Dr Stuart Currie
Radiology Consultant, Leeds Teaching Hospitals Trust and University of Leeds
Staff Profile: Dr Stuart Currie | School of Medicine | University of Leeds
I am an academic consultant neuroradiologist with 50:50 division between clinical and research pursuits. My main research interests lie in the better understanding of diffuse glioma with particular emphasis on imaging biomarkers of disease and treatment and how the use of artificial intelligence through imaging may enhance this field.
Dr Alex Gilbert
Honorary Consultant, Senior Clinical Trials Fellow
Staff Profile: Dr Alex Gilbert | School of Medicine | University of Leeds
I am an Honorary consultant and CRUK Senior Clinical Trial fellow in Clinical (Radiation) Oncology. My research expertise is in the use of patient reported outcomes (PROs) in radiation toxicity measurement both in clinical trials and routine practice. I have a particular interests in the use of PROs to develop predictive biomarkers of radiotherapy late effects and PRO methodology in clinical trials. As a CRUK senior clinical trial fellow, I am working on a number of interventional radiotherapy trials including complex multi-centre platform RCTs evaluating novel agents and techniques, providing expertise in toxicity and PRO measurement.
I am also a member of the NCRI anorectal cancer subgroup and deputy chair of the Methodology workstream as well as an active member of the EORTC Quality of Life group. I have collaborated both nationally and internationally with experts in health services research, PROs, technical radiotherapy and clinical trials.