Ke Yuan -- Mapping the landscape of histomorphological cancer phenotypes with self-supervised learning [IN PERSON]
| Dates: | 15 June 2026 |
|---|
| Times: | 14:00 - 15:00 |
|---|
| What is it: | Seminar |
|---|
| Organiser: | Department of Mathematics |
|---|
| Who is it for: | University staff, External researchers, Current University students |
|---|
| Speaker: | Ke Yuan |
|---|
|
Join us for this seminar by Ke Yuan (Glasgow) as part of the Maths in the Life Sciences seminar series (and the online North West Seminar Series in Mathematical Biology and Data Sciences in collaboration with Liverpool Universities).
Title: Mapping the landscape of histomorphological cancer phenotypes with self-supervised learning
Abstract:
Self-supervised representation learning is transforming computational pathology, enabling powerful predictive models for cancer diagnosis, prognosis, and treatment response. We leverage this technology to systematically map recurrent and rare histomorphological patterns directly from unannotated pathology slides. Across multiple cancer types, we found previously underappreciated histological features strongly correlated with patient outcomes and molecular data. The patterns define a quantitative landscape of cancer phenotypes, facilitating novel hypothesis generation and deeper biological understanding. This work demonstrates the power of self-supervised AI to unlock clinically relevant insights and discoveries from routinely collected pathology data.
Bio:
Ke Yuan is a Reader in Machine Learning and Computational Biology at the School of Cancer Sciences, University of Glasgow and a Group Leader at the Cancer Research UK Scotland Institute. Previously, he served as a Lecturer and then Senior Lecturer at the School of Computing Science, also at the University of Glasgow. He received his PhD from the University of Southampton in 2013 under the supervision of Mahesan Niranjan. Until April 2016, he worked as a postdoctoral research fellow at the Cancer Research UK Cambridge Institute at the University of Cambridge, working with Florian Markowetz. His research focuses on developing novel machine learning and AI methods for genomic and image data to advance our understanding of cancer and virus evolution.
The talk will be also be streamed via Teams, please contact carl.whitfield@manchester.ac.uk or igor.chernyavsky@manchester.ac.uk for the link, or sign up to the mailing list.
To subscribe to the mailing list for this event series, please send an e-mail with the phrase “subscribe math-lifesci-seminar” in the message body to listserv@listserv.manchester.ac.uk
Speaker
Ke Yuan
Role: Reader
Organisation: University of Glasgow
Travel and Contact Information
Find event
4.04
Simon Building
Manchester
