Characterisation of tissue microstructure from non-invasive MRI using Machine Learning

About the Project

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.

For more information, or if there are any questions, please contact Dr Leandro Beltrachini BeltrachiniL@cardiff.ac.uk

The typical academic requirement is a minimum of a 2:1 physics and astronomy or a relevant discipline.

Applicants whose first language is not English are normally expected to meet the minimum University requirements (e.g. IELTS 6.5 Overall with 5.5 minimum in sub-scores) (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
• Your degree certificates and transcripts to date including certified translations if these are not in English
• a personal statement/covering letter
• two references, at least one of which should be academic. Your references can be emailed by the referee to physics-admissions@cardiff.ac.uk

Please note: We are do not contact referees directly for references for each applicant due to the volume of applications we receive.

In the "Research Proposal" section of your application, please specify the project title and supervisors of this project.

In the funding section, please select that you will be self-funded or include your own sponsorship or scholarship details.

Once your application is submitted, we will review it and advise you within a few weeks if you have been shortlisted for an interview.

Cardiff University and the School of Physics and Astronomy are committed to supporting and promoting equality and diversity. Our inclusive environment welcomes applications from talented people from diverse backgrounds. We strongly welcome female applicants and those from any ethnic minority group, as they are underrepresented in our School. The School of Physics & Astronomy has a Juno Practitioner accreditation that recognises good employment practice and a commitment to develop the careers of women working in science. The University is committed to ensuring that we sustain a positive working environment for all staff to flourish and achieve. As part of this commitment, the University has developed a flexible and responsive framework of procedures to support staff in managing their work and personal commitments wherever possible. Applications are welcome from individuals who wish to work part-time or full time.

Cardiff University is a signatory to the San Francisco Declaration on Research Assessment (DORA), which means that in hiring and promotion decisions we will evaluate applicants on the quality of their research, not publication metrics or the identity of the journal in which the research is published. More information is available at: Responsible research assessment - research – Cardiff University.

Applications may be submitted in Welsh, and an application submitted in Welsh will not be treated less favourably than an application submitted in English. We very much welcome applications in Welsh.

Funding Notes

This project is offered for self-funded students only, or those with their own sponsorship or scholarship award.