Dr Yang Hu

Supervisor Details

Contact Details

School of Computing and Mathematical Sciences, University of Leicester

Scientific Background

Research Interests

My research focuses on computational pathology, medical image analysis, and the development of lightweight and interpretable artificial intelligence methods. I aim to build biologically grounded AI methods that help us understand cancer, connect tissue morphology with molecular evidence, and translate complex medical data into reliable insights.

Research Groups

Yang Hu Lab

Supervision Style

In three words or phrases: Supportive, curiosity-driven, and structured yet flexible.

Provision of Training

I will provide structured, hands-on training tailored to the student's background, particularly in computational methods and research practice. As the student develops confidence and expertise, I will progressively encourage greater independence in research design, problem-solving and methodological development.

Progression Monitoring and Management

I will establish clear, achievable research milestones and review progress through fortnightly supervision meetings. I maintain high expectations while encouraging open discussion of challenges, with research plans and priorities adjusted collaboratively when necessary.

Communication

I encourage open, regular and constructive communication through meetings, email and Microsoft Teams, and welcome students raising research or personal concerns at an early stage. I respect work–life balance and do not expect students to respond to messages outside normal working hours.

Meetings

PhD Students can expect scheduled meetings with me at least once per fortnight. These meetings will be a mixture of face-to-face and via video chat or telephone. I am usually contactable for an instant response 3 or 4 days per week.

Work Patterns

The timing of work in my lab is completely flexible, and (other than attending pre-arranged meetings) I expect students to manage their own time.

Notice Period for Feedback

I prefer to be involved from the outset of the writing process, providing ongoing guidance and feedback throughout drafting, with flexible timelines agreed according to the student's needs.

MIBTP Project Details

Primary supervisor for:

Resolving the Associations Between Multicellular Ecosystems and Aggressive Molecular and Evolutionary Tumour States

See the PhD Opportunities section to see if this project is currently open for applications via MIBTP.

Please Note: The main page lists projects via BBSRC Research Theme(s) quoted and then relevant Topic(s).

Resolving the Associations Between Multicellular Ecosystems and Aggressive Molecular and Evolutionary Tumour States

Secondary Supervisor(s): Professor Dean Fennell, Professor Hongji Yang

University of Registration: University of Leicester

BBSRC Research Themes:

Understanding the Rules of Life (Immunology, Systems Biology)

Project Outline

Why do some tumours become more aggressive or respond differently to treatment? The answer may lie not only in tumour cells, but also in the immune and stromal cells around them. This PhD will study these local communities as tumour ecosystems and ask how their organisation is linked to tumour evolution, molecular states and treatment response.

The project will address this broader cancer question through the malignant pleural mesothelioma scenario. The project will design the framework for transfer to other cancer types. The existing materials have matched H&E whole-slide images, pathology reports, genomic, DNA methylation, gene-expression and treatment-response data. This allows direct comparison of tissue organisation with molecular activity and treatment response.

The student will first map tumour, immune and stromal communities across whole slides. They will then develop interpretable AI models that connect these maps with molecular and evolutionary states, and test whether disease states and treatment-response patterns can be inferred from tissue structure. Patient-level and within-tumour comparisons will test robustness, followed by pathologist review and targeted tissue validation.

The project will deliver a spatial atlas of mesothelioma ecosystems, a transferable analysis framework, and interpretable models evaluated on molecular subtyping, progression assessment and treatment-response prediction. It will also produce a prioritised set of ecosystem biomarkers and biological pathways, with the strongest candidates tested in tissue where feasible. These outputs could support diagnostic assessment, guide molecular testing and patient stratification, and identify treatment-linked mechanisms for therapeutic validation. The student will gain integrated training in tumour biology, spatial pathology, multi-omics, quantitative modelling and responsible AI.