University of Leeds Featured PhD Programmes
University of Kent Featured PhD Programmes
Catalysis Hub Featured PhD Programmes
University of Liverpool Featured PhD Programmes
University College London Featured PhD Programmes

Engineering Doctorate (EngD) - Robust novel imaging biomarkers for 3D medical imaging (TMVSE)

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  • Full or part time
    Prof D Reid
  • Application Deadline
    Applications accepted all year round

Project Description

Project not available to non UK/EU applicants

The EngD is an alternative to a traditional PhD aimed at student wanting a career in industry. Students spend about 75% of their time working directly with a company in addition to receiving advanced-level training from a broad portfolio of technical and business courses. On completion students are awarded the PhD-equivalent EngD.

The Project
We develop algorithms and tools for the automatic analysis of medical datasets, acquired from a wide variety of medical imaging equipment, e.g. X-ray CT, magnetic resonance imaging, ultrasound imaging, single photon emission tomography, positron emission tomography, etc. Such analysis presents great – and interesting – challenges, particularly when trying to make fully automatic analysis robust.

A biomarker is a measurable parameter which provides useful information about some biological process. For example, measuring the presence of a specific antibody in a blood sample might indicate the patient has a particular infection. Imaging biomarkers are features that can be measured from a medical image, for example the size, shape, or brightness of a tumour could help clinicians find out the type of tumour and decide how best to treat it.

This project will investigate the automation of imaging biomarkers, using techniques from deep machine learning, such as convolutional neural networks. This has a number of applications, as it not only saves time but opens opportunities for processing large numbers of datasets offline (so-called “Big Data”). Automatic analysis also has the potential to detect patterns that are too subtle to detect by eye. Finally, automatic analysis is useful to improve consistency in interpretation, between individuals and different centres.

Funding Notes

This is a 4-year (including CDT taught-courses) project is funded jointly by Toshiba Medical Visual Systems and the CDT in Applied Photonics, run by Heriot-Watt University. The annual stipend is £20,326, which includes an enhancement from TMVSE. A substantial consumables and equipment budget is provided by a concurrent EPSRC grant. Travel funding for conference presentations is also available.

FindAPhD. Copyright 2005-2019
All rights reserved.