| PhD openings | |
  | Next-generation inflammation imaging combining computational modelling and machine learning This is an outstanding opportunity to be undertake an EPSRC-funded PhD studentship based between the UCL departments of Computer Science and Medicine. This project aims to develop a new approach to imaging inflammation, harnessing recently advances in computational modelling and machine learning to address the key gaps in our ability to diagnose and phenotype inflammatory diseases. Inflammation – the body’s response to harm and danger signals, which can occur inappropriately to cause pathology – is a fundamental process in human disease and causes a massive global burden of ill-health across all organ systems and in patients of all ages. To improve our ability to detect, quantify and characterise inflammation, this project will develop a set of interlinked computational methods, with deep learning as the core technology, aiming to provide detailed, quantitative imaging assessments of inflammation. These tools will focus on (1) the generation of biologically-relevant spatial maps describing key pathophysiological processes in inflammation (2) the extraction of biologically-meaningful summary metrics, describing the burden and type of disease in each patient and (3) precise measurement of changes in disease over time. A schematic describing each of these steps is given below.  Schematic illustration of the proposed next-generation inflammation imaging. The project will involve technical innovations at each step in the pipeline, including (1) novel methods for generating spatial maps of tissue properties (2) extraction of biologically-meaningful summary metrics and (3) precise measurement of changes in disease severity and type over time. Each of these steps are labelled on the schematic. These tools will allow us to quantitatively phenotype inflammation in individual patients, and thus enable therapy to be tailored to individual patients for maximum benefit. The techniques will be evaluated in a unique cohort of patients with axial spondyloarthritis (axSpA), forming the first step towards development of a tool capable of comprehensive inflammation assessment in clinical care. If successful, the methods developed will be rapidly introduced into a large (n=800) multisite UK study in axSpA, offering a test-bed for translation into clinical care and, ultimately, introduction across the NHS. For details on how to apply and funding eligibility criteria, please see this link. Interested students shall send their up-to-date CV via email to Tim Bray (t.bray@ucl.ac.uk) and Gary Zhang (gary.zhang@ucl.ac.uk) by 16th of January 2023. |
| | Spotting signs of damage in the brain: white matter hyperintensity segmentation from MRI using deep learning This is an exciting opportunity to be considered for an EPSRC funded PhD studentship at UCL department of Computer Science. This project aims to develop novel deep learning-based approaches to assess damage in the brain, and to understand its impact on brain functions, using routine MRI scans. The damage of particular importance is the damage to white matter, brain's communication pathways; damaged white matter is known as white matter hyperintensity because it appears brighter than healthy white matter in routine MRI scans. Current approaches to assess this, known as white matter hyperintensity segmentation, identify spatial locations and extent of the damage. However, this information offers limited value for quantifying the nature of functional impairment. In particular, they do not inform on the extent to which individual communication pathways supporting specific brain functions have been disrupted. In this PhD, you will have the opportunity to develop novel approaches that address this limitation using deep learning. For funding eligibility criteria, please refer to the relevant section of this page. Interested students shall send their up-to-date CV to me via email (gary.zhang@ucl.ac.uk) by 1st of April 2022. |