Image Analysis for Studying Radiotherapy Induced Lung Damage
A 4-year PhD studentship is available in the UCL Centre for Medical Image Computing (CMIC). The funding covers an annual tax free stipend (£16,777) and tuition fees. As the studentship is partially funded by the EPSRC the standard EPSRC eligibility criteria apply, please see EPSRC website for further details. The successful candidate will join the UCL CDT in Medical Imaging cohort and benefit from the activities and events organised by the centre.
Non-small cell lung cancer (NSCLC) is one of the most common cancers in the UK. Although survival rates are improving, survivors experience poor long-term quality of life. Radiotherapy is a common treatment but can cause damage to the lungs (Radiotherapy Induced Lung Damage, RILD) and other side effects. Recent trials of novel radiotherapy treatment regimens have reported improved local control and longer survival times. Consequently, there is growing interest in better characterising and understanding RILD, and ultimately reducing its incidence and improving the outcome for lung cancer patients.
At CMIC we have been developing image based bio-markers of different forms of RILD, and have applied them to follow-up CT scans acquired ~12 months after treatment from an initial cohort of ~50 patients. This work has shown that RILD can be prolific after 12 months, with all patients affected by some form of RILD.
This PhD project will extend this initial work by expanding our suite of image-based bio-markers to include measures of parenchymal change and airway narrowing, and developing automated image processing pipelines such that our bio-markers can be efficiently calculated on large cohorts of patients with follow-up scans at multiple time-points. The project will then employ these pipelines to study the progression and evolution of RILD over time, and analyse the relationship between acute and chronic RILD. The project will also investigate the relationship between dose-distributions, RILD bio-markers, and clinical end-points and symptoms. This will involve developing more accurate methods of estimating the radiotherapy dose that is actually delivered to the patient (as opposed to the planned dose), as well as exploring existing and novel methods of analysing the dose-RILD relationships.
The methodologies developed during this project will be employed to analyse the results from a number of large clinical trials, and will ultimately help to inform and improve future radiotherapy treatments for lung cancer patients.
Applicants are expected to have a first degree in Computer Science or Biomedical Engineering or relevant Physical Sciences based subject passed at 2:1 level (UK system or equivalent) or above. Good working knowledge of C++ and/or Python and/or MATLAB is desirable. Some experience with medical image analysis or radiotherapy is also desirable.
To make an application for this project please send a CV and cover letter detailing why you want to apply for this studentship and why you believe you are suitable for the studentship, to Dr Jamie McClelland at firstname.lastname@example.org.
Closing date for applications: 31 August 2018. Project start date October 2018.