University of East Anglia Featured PhD Programmes
University of Southampton Featured PhD Programmes
University College London Featured PhD Programmes

(EPSRC DTP) Recurrent Neural Networks for anatomy and dose nowcasting in radiotherapy


Project Description


Cancer is responsible for >25% of deaths in the UK and according to current projections, around 50% of people born after 1960 will develop the disease. Radiotherapy plays an important role in the treatment of cancer, with >50% of cancer patients receiving it as part of their treatment.

Current radiotherapy treatments are delivered over the course of 4-6 weeks, but are based on a radiotherapy plan developed on an image taken before treatment commences. It is well known that anatomy is not static over this timescale, and therefore there is an urgent need to develop fully online radiotherapy plan adaptation strategies. In full online plan adaptation, a new radiotherapy plan is developed on every day of treatment; this requires condensing a few day’s work into a few minutes. The most important bottlenecks in the radiotherapy workflow are the delineation of tumour and healthy tissue, and the checking of treatment plan quality and safety.

In this project, we will develop state of the art machine learning tools using recurrent neural networks (RNNs) to perform anatomy ‘nowcasting’, allowing a neural network to delineate a patient taking account of population-based modelling, but adding personalised information considering the patient’s anatomy from previous day’s treatment. As treatment progresses and more images are incorporated in the model, it will become increasingly personalised, offering the possibility of highly accurate delineations for each patient. We will also explore methods to provide uncertainty measures on delineations from the network, such as applying Bayesian neural networks.

We will also develop dose nowcasting RNNs, in which we predict the optimal dose that should be delivered for the anatomy of the day. This prediction can then be compared to the output of the current workflow to provide some automated checking of the dose produced by the current, clinically used workflow.

The student will work in a multidisciplinary team at the cutting edge of AI research in radiotherapy. They will have the opportunity to work at the interface of the clinical radiotherapy workflows ensuring translation of results remains firmly embedded in the project.

Entry Requirements:
Applications are invited from UK/EU nationals only. Applicants must have obtained, or be about to obtain, at least an upper second class honours degree (or equivalent) in a relevant subject.

For information on how to apply for this project, please visit the Faculty of Biology, Medicine and Health Doctoral Academy website (https://www.bmh.manchester.ac.uk/study/research/apply/)

Funding Notes

EPSRC DTP studentship with funding for a duration of 3.5 years to commence in September 2020. The studentship covers UK/EU tuition fees and an annual minimum stipend £15,285 per annum. Due to funding restrictions, the studentship is open to UK and EU nationals with 3 years residency in the UK.

As an equal opportunities institution we welcome applicants from all sections of the community regardless of gender, ethnicity, disability, sexual orientation and transgender status. All appointments are made on merit.

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
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2020
All rights reserved.