Machine Learning Techniques for Evaluating Disease and Drug Effectiveness in Fibre-Bundle Endomicroscopy Systems

In partnership with GlaxoSmithKline (GSK) and the National Physical Laboratory (NPL), we seek a student with strong signal and image processing or machine learning skills to develop algorithms to improve the quality of data received from a Fluorescent Lifetime Imaging (FLIM) system called Kronoscan. There is an emphasis on developing robust algorithms that can be translated in clinical applications. You will have the opportunity to undertake a placement at NPL during the PhD and will have access to additional NPL training resources.
 
You will join an interdisciplinary team, comprising data scientists, engineers, chemists, biologists and clinical scientists and will work with a range of teams based at the Queen’s Medical Research Institute in the Centre for Inflammation Research. The project aim is to develop new technologies to understand and evaluate disease and drug effectiveness.
 
Endomicroscopy is an emerging medical imaging modality that facilitates the acquisition of in vivo and in-situ optical biopsies, assisting fast diagnostic and potentially therapeutic interventions. To date, real-time endomicroscopy has been dominated and limited to intensity mode imaging due to existing detector technology. This limitation has now been overcome by the Kronoscan system by incorporating both intensity and lifetime imaging. This breakthrough technology will enable multidimensional high-content real-time sensing and imaging of dynamic biological processes. These systems are now poised for disruptive healthcare impact, and a key ambition of the research will be to pave the way for subsequent clinical and commercial impact.
This project will use image processing and machine learning techniques for further developing the FLIM platforms with two key aims: to improve (1) image reconstruction and quantification of samples for assessment; and (2) monitoring of drug-target engagement.  You may build on various techniques for image reconstruction and bacteria detection,  including computationally efficient Bayesian estimation and deep learning methods.
 
The project will be undertaken in partnership with GSK, who have the eventual aim of applying high-resolution ultra-sensitive microscopic imaging to the evaluation of drug action as an essential step to improving a currently expensive and poorly productive drug development pathway. Input from NPL will provide expertise and guidance on metrology and uncertainty considerations and practices applied to data processing, analysis and machine learning.  The student will also be enrolled in the Postgraduate Institute for Measurement Science (www.npl.pgi.co.uk) and receive training and co-supervision from NPL scientists.

This project will also be supervised by Dr Neil Finlayson in Engineering.

Further Information: 

The successful applicant will be awarded a 4 year studentship, which includes their stipend and tuition fees at the UK/EU rate, and contributions towards travel and research costs for their PhD project.  
 
http://www.gsk.com
https://proteus.ac.uk/
www.npl.co.uk
 

 

Closing Date: 

Thursday, December 31, 2020

Principal Supervisor: 

Assistant Supervisor: 

Eligibility: 

An undergraduate degree with background in Signal and Image Processing, Machine Learning, or related areas.

Minimum entry qualification - an Honours degree at 2:1 or above (or International equivalent) in a relevant science or engineering discipline, possibly supported by an MSc Degree. Further information on English language requirements for EU/Overseas applicants.

Funding: 

Tuition fees + stipend are available for Home/EU students (International students can apply, but the funding only covers the Home/EU fee rate)

Further information and other funding options.

Informal Enquiries: