LIMR: Explainable AI for Prognostic and Predictive Digital Histopathology in Endometrial Cancer

This PhD project aims to develop explainable artificial intelligence (AI) models to analyse digital histopathology whole-slide images (WSIs) of endometrial cancer and its precursor, endometrial hyperplasia, with the goal of improving prognosis prediction, molecular subtyping (ER, PR, P53, MMR, POLE), and therapy response evaluation.<br /> Leveraging deep learning techniques, the project will segment and classify histomorphological features from WSIs and fuse these with clinical and molecular data using multi-modal AI models. Publicly available datasets (e.g. TCGA-UCEC) and local institutional cohorts will be utilised for training and validation.<br /> The project also emphasises explainability to ensure clinical interpretability, using techniques such as attention mapping and SHAP to visualise morphological drivers of AI decisions. Outcomes will include the development of an open-source AI pipeline, identification of novel prognostic markers, and potential translation into clinical decision support systems in gynaecological oncology.

<p>Techniques associated with the project:</p> <ul> <li>Deep learning (CNNs, vision transformers, survival models)</li> <li>Whole-slide image processing (tiling, segmentation, normalisation)</li> <li>Multi-modal data fusion (genomic, clinical, and image data)</li> <li>Explainability methods</li> <li>Digital pathology software (e.g. QuPath)</li> <li>Survival and risk modelling</li> <li>Access and analysis of large datasets (e.g. TCGA, CPTAC)</li> <li>Laboratory testing (e.g. immunohistochemistry)</li> <li>Clinical profiling (e.g. electronic healthcare record interrogation, case sourcing) </li> <li>Histological evaluation (e.g. identification of hyperplasia/carcinoma)</li> <li>Slide scanning</li> </ul>

<p>Please note these are not standalone projects and applicants must apply to the PhD academy directly.</p> <p>Applications can be made at any time. You should complete an <a href="https://medicinehealth.leeds.ac.uk/faculty-graduate-school/doc/apply-2">online application form</a> and attach the following documentation to support your application. </p> <ul> <li>a full academic CV</li> <li>degree certificate and transcripts of marks (or marks so far if still studying)</li> <li>Evidence that you meet the programme’s minimum English language requirements (if applicable, see requirement below)</li> <li>Evidence of funding to support your studies</li> </ul> <p>To help us identify that you are applying for this project please ensure you provide the following information on your application form;</p> <ul> <li>Select PhD in Medicine, Health & Human Disease as your planned programme of study</li> <li>Give the full project title and name the supervisors listed in this advert</li> </ul> <p><em>As an international research-intensive university, we welcome students from all walks of life and from across the world. We foster an inclusive environment where all can flourish and prosper, and we are proud of our strong commitment to student education. Across all Faculties we are dedicated to diversifying our community and we welcome the unique contributions that individuals can bring, and particularly encourage applications from, but not limited to Black, Asian, people who belong to a minority ethnic community, people who identify as LGBT+ and people with disabilities. Applicants will always be selected based on merit and ability.</em></p>

A degree in biological sciences, dentistry, medicine, midwifery, nursing, psychology or a good honours degree in a subject relevant to the research topic. A Masters degree in a relevant subject may also be required in some areas of the Faculty. For entry requirements for all other research degrees we offer, please contact us.

Applicants whose first language is not English must provide evidence that their English language is sufficient to meet the specific demands of their study. The minimum requirements for this programme in IELTS and TOEFL tests are: • British Council IELTS - score of 7.0 overall, with no element less than 6.5 • TOEFL iBT - overall score of 95 with not less than 22 in listening, 22 in reading, 24 in speaking and 22 in writing.

<p>Women's Health Research Group<br /> Division of Pathology & Data Analytics<br /> Leeds Institute of Medical Research<br /> Wellcome Trust Brenner Building<br /> St James's University Hospital<br /> Beckett Street<br /> Leeds LS9 7TF, UK<br /> Email: <a href="mailto:n.m.orsi@leeds.ac.uk">n.m.orsi@leeds.ac.uk</a></p> <p>Enquiries regarding the application process should be directed to the Faculty of Medicine and Health PGR Admissions team: <a href="mailto:fmhpgradmissions@leeds.ac.uk">fmhpgradmissions@leeds.ac.uk</a></p>