The characterisation of biological tissue microstructure in vivo and non-invasively is of outmost interest in science. If successful, it could reveal unique insights into biological processes, including aging and cancer. In this regard, MRI plays a crucial role due to its superb flexibility to depict soft tissues. Researchers in the field have utilised this technology mostly based on assumptions about the shape of cellular components (spheroidal/cylindrical), which have been shown to introduce unwanted errors. The reason for making such approximations is the intractability that arbitrary tissues may impose on the mathematical models employed.
To tackle the problem, the supervisory team has been exploring the introduction of a potentially disrupting methodology borrowed from materials science. It consists of measuring statistical descriptors (SDs) of tissue microstructure using the MRI scanner, from which histology-like representations may be reconstructed. These SDs have the advantage of describing the statistical nature of tissue components without relying on any assumption on shapes and arrangements, making the technique potentially useful to depict tissue microarchitecture as never before. One of the major drawbacks of this technique resides in the instability and computational demands of the reconstruction step, which can last for days even in modern computers.
In this project, the student will provide a solution to the problem by introducing machine learning (ML) approaches in the process: first, to generate fast reconstructions of tissue microstructure based on MRI-based SDs; and second to perform quick simulations of MRI signals for any given microstructure, as those generated from SDs. Synthetic datasets representing biological tissues will be generated and used to train and test the algorithms, with special emphasis on prostate cancer. It is expected that the adoption of ML will bring the extra boost to successfully bring this technology to the medical imaging domain.
The PhD project will take place in the Cardiff University Brain Research Imaging Centre (CUBRIC), a pioneer in brain imaging research. CUBRIC houses >200 researchers across Schools and Colleges, making it a vibrant multidisciplinary research community. Moreover, the centre hosts state-of-the-art neuroimaging equipment that the student will benefit from, including the Connectom scanner with ultra-strong gradients.
The successful candidate will have a unique training opportunity, involving the possibility to attend courses in ML and/or MRI, tuition for specialised MRI operation, present research work in international conferences, establish links with industrial partners (e.g., SIEMENS), and be part of the larger collaboration in the area.
Eligibility
The typical academic requirement is a minimum of a 2:1 Bachelors degree in a relevant discipline.
Applicants whose first language is not English are normally expected to meet the minimum University requirements (e.g. 6.5 IELTS) (https://www.cardiff.ac.uk/study/international/english-language-requirements)
How to apply
Applicants should apply to the Doctor of Philosophy in Physics and Astronomy.
Applicants should submit an application for postgraduate study via the Cardiff University webpages (https://www.cardiff.ac.uk/study/postgraduate/research/programmes/programme/physics-and-astronomy) including:
• your academic CV
• a personal statement/covering letter
• two references, at least one of which should be academic
• Your degree certificates and transcripts to date (with certified translations if these are not in English).
In the "Research Proposal" section of your application, please specify the project title and supervisors of this project.
This project is only available to self-funded students, please can you include your funding source in the "Self-Funding" section.
Continue with Facebook
