University of Hong Kong Featured PhD Programmes
University of Leeds Featured PhD Programmes
University of Edinburgh Featured PhD Programmes

MRC DiMeN Doctoral Training Partnership: Physics-informed neural networks for predicting patient anatomical motion during radiotherapy


MRC DiMeN Doctoral Training Partnership

Leeds United Kingdom Applied Mathematics Artificial Intelligence Biomedical Engineering Biophysics Machine Learning Medical Physics

About the Project

Half of all cancer patients have some form of radiotherapy (RT) treatment, resulting in >130k external beam RT episodes pa in England. Patient motion during RT, e.g. due to respiration and peristalsis, remains a main confounder of accurate treatment delivery, causing overdosing of organs-at-risk or underdosing of tumour, and leading to poorer survival outcomes or greater post-treatment morbidity. If this motion can be predicted during treatments, we can design treatment adaption strategies to compensate for it, and correspondingly improve patient outcomes. This project aims to create fundamentally new approaches to modelling such motions using so-called physics-informed neural networks (PINNS).

Neural network-based simulation approaches can offer huge speed-ups compared with conventional computational models (e.g. finite element models). They also offer a means of directly linking model predictions with low-level patient data like images, potentially streamlining clinical use. Compared with standard neural networks, PINNs incorporate physical constraints within their loss functions to ensure network predictions correctly reflect relevant physical, and in this case physiological, laws. While improving the reliability of model predictions, this also can massively reduce the amount of training data required, and make the resulting networks more interpretable – both features of very high importance in medical applications.

Objectives:

1)    Formulate physics-based biomechanical models of respiratory and peristaltic motion incorporating image-derived anatomy, advanced tissue constitutive models, and robust interaction with surrounding anatomy; validate using phantom data and 3D/4D MR/CT image-derived measurements.

2)    Develop Physics-Informed-Neural-Network approaches that accelerate model predictions and link predictions directly with patient images.

3)    Evaluate model effectiveness within RT treatment adaption scenarios: pilot study on inter-fraction motion-compensated dose accumulation and treatment plan adaptation using model predictions.

This project is inherently interdisciplinary. It correspondingly provides an opportunity to develop high-level skills in several distinct areas:

·      Quantitative skills: the project has computation and machine-learning at its core. As part of your doctoral training programme, you will access an array of formal modules in these areas. You will also access related seminar programmes and journal clubs run by CISTIB, LIDA, IMBE, and others within the University. Simulation and machine-learning are the foundation of emerging disciplines like computational medicine. You will finish your degree well-equipped to pursue cutting edge research in this and many other areas. 

·      Interdisciplinary skills: the project sits at the engineering/medicine interface. You will receive close guidance and training in clinical and medical physics aspects of RT practice, and clinical implementation/translation of advanced imaging and AI technologies.

You will be based in the Centre for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB – co-led by Dr Taylor) at the University of Leeds. You will have strong links also with the Clatterbridge Cancer Centre in Liverpool, and the Leeds Cancer Centre. More information on these centres and the project supervisors can be found here:

CISTIB: https://eps.leeds.ac.uk/computing-research-groups/doc/computational-medicine

CCC: https://www.clatterbridgecc.nhs.uk

LCC: https://www.leedsth.nhs.uk/a-z-of-services/leeds-cancer-centre

Benefits of being in the DiMeN DTP:

This project is part of the Discovery Medicine North Doctoral Training Partnership (DiMeN DTP), a diverse community of PhD students across the North of England researching the major health problems facing the world today. Our partner institutions (Universities of Leeds, Liverpool, Newcastle and Sheffield) are internationally recognised as centres of research excellence and can offer you access to state-of the-art facilities to deliver high impact research.

We are very proud of our student-centred ethos and committed to supporting you throughout your PhD. As part of the DTP, we offer bespoke training in key skills sought after in early career researchers, as well as opportunities to broaden your career horizons in a range of non-academic sectors.

Being funded by the MRC means you can access additional funding for research placements, international training opportunities or internships in science policy, science communication and beyond. See how our current DiMeN students have benefited from this funding here: http://www.dimen.org.uk/overview/student-profiles/flexible-supplement-awards

Further information on the programme and how to apply can be found on our website:

https://bit.ly/3lQXR8A 


Funding Notes

Studentships are funded by the Medical Research Council (MRC) for 3.5yrs. Funding will cover UK tuition fees and stipend only. We aim to support the most outstanding applicants from outside the UK and are able to offer a limited number of bursaries that will enable full studentships to be awarded to international applicants. These full studentships will only be awarded to exceptional quality candidates, due to the competitive nature of this scheme. Please read additional guidance here: View Website
Studentships commence: 1st October 2021
Good luck!

References

1) S Saeed, et al. (2020): Prostate motion modelling using biomechanically-trained deep neural networks on unstructured nodes, Medical Image Computing and Computer Assisted Intervention - MICCAI2020. https://doi.org/10.1007/978-3-030-59719-1_63
2) SF Johnsen, et al. (2015): NiftySim: A GPU-based nonlinear finite element package for simulation of soft tissue biomechanics, Int J Comput Assist Radiol Surg, 10:1077-1095. https://doi.org/10.1007/s11548-014-1118-5
3) JC Vardakis, et al. (2019): Highly integrated workflows for exploring cardiovascular conditions: Exemplars of precision medicine in Alzheimer's disease and aortic dissection. Morphologie, 103: 148-160. https://doi.org/10.1016/j.morpho.2019.10.045

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here

The information you submit to University of Leeds will only be used by them or their data partners to deal with your enquiry, according to their privacy notice. For more information on how we use and store your data, please read our privacy statement.

* required field

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2021
All rights reserved.