PhD project: Using machine learning to obtain image derived input functions in Positron Emission Tomography imaging
Project description
Positron emission tomography (PET) imaging is a highly sensitive tool that allows clinicians and researchers to observe the function and metabolism of different systems in the body. It employs a radiotracer injected into a patient in order to follow physiological processes such as blood flow, metabolism of glucose or receptor binding. One advantage of PET imaging is that absolute quantification of physiological parameters is possible which is valuable for developing new treatments.
The gold standard of quantification is compartmental analysis which requires a measure of the concentration of radiotracer in the plasma of the blood, known as the arterial input function (AIF). Generally, this is obtained by arterial blood sampling throughout the PET scan which is not comfortable for a human patient and logistically difficult in small animal imaging due to the small volume of blood.
Ideally, the AIF should be obtained from the PET image itself. Numerous attempts have been made to do this but none are sufficiently reliable or general. One method that has only been minimally investigated is the possibility of using machine learning to derive an AIF. Our initial investigations suggest an autoencoder can be successfully used to extract the AIF. This has only been demonstrated for a single radiotracer and for mice. This PhD will involve radically extending the scope of this work to many tracers and to human subjects. Tracer metabolism and other time activity curves will also be topics for consideration.
Project supervisors
- Professor Paul Clegg (School of Physics & Astronomy, University of Edinburgh)
- Dr Catriona Wimberley (Edinburgh Imaging)
The project supervisors welcome informal enquiries about this project.
Find out more about this research area
The links below summarise our research in the area(s) relevant to this project:
- Find out more about Physics of Living Matter.
- Find out more about the Institute for Condensed Matter and Complex Systems.
What next?
- Find out how to apply for our PhD degrees.
- Find out about fees and funding and studentship opportunities.
- View and complete the application form (on the main University website).
- Find out how to contact us for more information.