Functional regression models with application in neuroimaging data analysis

Summary

We are looking for strong candidates to work on this exciting project with a multidisciplinary team described below!

In today's world, clinicians and researchers have access to a wealth of data to support diagnosis and treatment in a huge range of brain-related disorders. Specifically, data from Magnetic Resonance Imaging systems (fMRI and MRI) offers a wealth of information waiting to be unlocked, but requires tools and significant expertise for the analysis and interpretation of these data sets. In this project, we aim to develop novel statistical approaches (with corresponding software) for exploring these datasets to further understand the dynamical behaviour behind cognitive-related deficits aiming to improve diagnosis and treatment. Given the important societal and clinical need to address Dementia that has now become the leading cause of death within the UK (ONS, UK), the initial focus of the project will be Alzheimer’s disease with the opportunity to diversify our models into other cognitive/neurodegenerative related disorders.

The challenge for understanding brain data lies in analysing multi-dimensional time-varying images (e.g. MRI, fMRI) and simultaneously extracting high-resolution structures and dynamic information for which existing methods are limited. To address this, the project aims to develop novel functional regression models based on Karhunen-Loeve decomposition (Li et al. 2019) and tensor decomposition (Zhou et al. 2013) and machine learning methods based on vibrational auto encoder (Sauty & Durrleman2022), which will leverage the advantages of time and space data to unlock new insights for understanding the brain. In particular, the proposed models are expected to be able to identify region-of-interest, and quantify its rate of change in the brain over time, thus will make accurate predictions of disease progression and provide insight into earlier diagnosis.

This proposed PhD project is related to our on-going Royal Society International Exchanges project and therefore has exciting UK-China collaborations.

References:
Li, Y., Huang, C., & Härdle, W. K. (2019). Spatial functional principal component analysis with applications to brain image data. Journal of Multivariate Analysis, 170, 263-274.

Sauty, B., & Durrleman, S. (2022, September). Progression models for imaging data with longitudinal variational auto encoders. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 3-13). Cham: Springer Nature Switzerland.

Zhou, H., Li, L., & Zhu, H. (2013). Tensor regression with applications in neuroimaging data analysis. Journal of the American Statistical Association, 108(502), 540-552.

Applicants to research degree programmes should normally have at least a first class or an upper second class British Bachelors Honours degree (or equivalent) in an appropriate discipline. The criteria for entry for some research degrees may be higher, for example, several faculties, also require a Masters degree. Applicants are advised to check with the relevant School prior to making an application. Applicants who are uncertain about the requirements for a particular research degree are advised to contact the School or Graduate School prior to making an application.

The minimum English language entry requirement for research postgraduate research study is an IELTS of 6.0 overall with at least 5.5 in each component (reading, writing, listening and speaking) or equivalent. The test must be dated within two years of the start date of the course in order to be valid. Some schools and faculties have a higher requirement.