The statistical analysis of covariance matrices occurs in many important applications, for example, in diffusion tensor imaging or longitudinal data analysis.
We wish to consider the situation where the data at hand are sample covariance matrices, and we wish to estimate the population covariance matrix and carry out statistical inference. An example application is in diffusion tensor imaging (DTI) where a diffusion tensor is a covariance matrix related to the molecular displacement at a particular voxel in the biological tissue.
DTI is an advanced Magnetic Resonance Imaging (MRI) modality which provides unique insights into the microstructure and organisation of biological tissues in-vivo and does so non-invasively. Water molecule diffusion in biological tissues can be hindered and have a preferential direction and when this is the case diffusion is said to be anisotropic. The anisotropy property of diffusion also allows the reconstruction of three-dimensional fibre structures in biological tissues and the corresponding method is known as “fibre tracking”.
This talk will cover Dr Zhou's work on non-Euclidean statistics for brain and musculoskeletal DTI data analysis.
Speaker
Dr Diwei Zhou is a Lecturer in Statistics at Loughborough University.