FREE PhD Study Fairs in Sheffield & Edinburgh | REGISTER NOW FREE PhD Study Fairs in Sheffield & Edinburgh | REGISTER NOW

FULLY FUNDED PHD - Algorithmic inference of tumour biology from histological images of malignant mesothelioma

   College of Medicine, Veterinary and Life Sciences

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Dr Ke Yuan, Prof John LeQuesne  No more applications being accepted  Funded PhD Project (UK Students Only)

About the Project


Malignant pleural mesothelioma (MPM) is an incurable tumour arising in the lining of the chest cavity, causally linked to inhalation of asbestos, and the UK currently endures the highest incidence of mesothelioma worldwide, and asbestos is the leading cause of occupation-related mortality in the UK.

Diagnosis from inspection of pathology microscopy images is difficult, and we urgently require improved biomarkers to differentiate low-risk from high-risk biopsies in symptomatic patients in order to better administer emerging therapies.

This post, funded by the CRUK Early Detection Programme IAMMED-MESO, will make use of the globally unique and powerful set of pre- and post-progression tissue biopsies established in Glasgow’s CRUK PREDICT-Meso Accelerator. This provides a very large and extremely high-quality dataset of images and associated metadata.

The proposal aims to use supervised and unsupervised deep learning algorithms to identify high-risk morphological features within microscopic images of these biopsies, thereby establishing the basis for a novel, AI-driven approach to patient risk stratification. In addition, we will use a similar approach to examine highly information-rich multiplex immunofluorescent images to focus on specific areas of tumour biology likely to be of relevance (eg the immune microenvironment). These approaches will also be applied to large cohorts of late-stage tumour tissue to questions about tumour virulence and to generate biological hypotheses in established disease. See this preprint for a recent application of similar methods from our laboratory:

The ideal candidate will have experience in deep learning artificial intelligence as applied to large sets of images, but we welcome applications from candidates with a diverse range of backgrounds, including but not limited to computer science, histology, pathology, biostatistics or medicine. Applicants must be able to demonstrate interests that bridge computer science and biomedicine, have some relevant experience, and show aptitude for at least basic coding (eg Python, R/Bioconductor).

The successful applicant will work with a team of computer scientists and collaborate closely with academic pathologists and clinicians. They will be well supported with opportunities for training in specific areas, and will be expected to regularly present and discuss their findings locally and at national/international meetings.

This studentship is open to candidates of any nationality – UK, EU or International, but unfortunately we can only pay UK university fees.

Funding Notes

Stipend will be paid at standard UKRI rates (£16062 for the year 2022-2023). Full details:
Additional fees for non-UK students are not covered.
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs