Department of Statistical Science

Applications are invited for two PhD funding opportunities offered jointly by the Faculty of Mathematical and Physical Sciences, UCL and the Agency for Science, Technology and Research (A*STAR), Singapore. The studentships will commence in September 2013 and are based both at A*STAR and the UCL Department of Statistical Science.

The studentships will be 3.5 years in duration, with year 1 spent at UCL, years 2 and 3 at A*STAR and a final writing-up period of 6 months at UCL. The awards cover tuition fees plus a maintenance stipend (£15,590 pro rata in years 1 and 4; during years 2 and 3 the student will receive a full stipend direct from A*STAR). These studentships may only be awarded to applicants liable to pay tuition fees at the UK/EU rate (i.e. they cannot be used to part-cover overseas tuition fees).

The requirement for admission to the MPhil/PhD in Statistical Science is a 1st class or high upper 2nd class BSc degree, or an MSc with merit or distinction in Mathematics, Statistics, Computer Science, or a related quantitative discipline. Overseas qualifications of an equivalent standard are also acceptable.

Spatial models, statistical machine learning, and cognitive vision for histopathological data.

UCL Supervisor: Dr James Nelson.

Definitive diagnosis of many diseases is often only possible with a biopsy but ageing populations and large-scale screening programmes are putting an ever-increasing strain on workloads to the extent that there is now a worldwide shortage of histopathologists. However, given recent advances in spectroscopic imaging modalities, high-throughput tissue banks, and the move towards digitized histological archives, it is now becoming feasible to use computer-aided image analysis to facilitate diagnosis.

This project will progress automated detection in this evolving field by developing spatial-statistical models and statistical machine learning methodology/algorithms. Unlike previous research, the work may incorporate the expertise of pathologists by adopting a cognitive vision approach to model complicated visual attentive behaviours involved during the pathologists' diagnosis process.

Candidates with an interest in one or more of the following areas are strongly encouraged to apply: spatial models, random fields, statistical machine learning, computer vision, and image analysis.

New statistical inverse methods for multispectral photoacoustic imaging.

UCL Supervisor: Dr Jinghao Xue.

Photoacoustic imaging (PAI) is a novel hybrid imaging modality based on the use of laser generated ultrasound. It combines the high absorption contrast and specificity of optical imaging with the high spatial resolution of ultrasound imaging. Multispectral PAI, acquired at multiple optical wavelengths, provides 3D structural, functional and molecular information of living biological tissue. If quantitative concentration distributions of the tissue’s chromophores can be accurately recovered, it can offer high potential in preclinical/clinical applications, such as cancer and brain/skin disorders. However, concentration recovery is an ill-posed inverse problem, mainly due to its nonlinear nature, its entanglement of spatial dependence and spectral correlation, and its large number of unknown spatial and spectral parameters to be estimated.

This project aims to overcome this problem, by developing new statistical methods to integrate nonlinearity, spatial dependence, spectral correlation, feature selection and other prior knowledge.

Candidates with an interest in one or more of the following areas are strongly encouraged to apply: inverse problems in imaging, medical imaging/image analysis, statistical machine learning/pattern recognition, and optimisation.

• Further Information