Self-funded PhD
Applications are welcome from candidates supported through personal, family, employer, institutional, or fellowship funding.
Lecturer in Computer Science · University of Leicester
Yang Hu
Computational pathology, interpretable foundation models, and multimodal AI for cancer research.
I build biologically grounded AI methods that help us understand disease, connect tissue morphology with molecular evidence, and translate complex medical data into reliable insight.
School of Computing and Mathematical Sciences ↗
Leicester Cancer Research Centre ↗
Computational pathology · Multimodal biomedical AI
01 · About
AI that explains disease, not only predicts it.
My research sits at the intersection of artificial intelligence, pathology, imaging, and cancer biology. I am particularly interested in how pathology foundation models behave, how microscopic features shape larger tissue-level conclusions, and how multimodal evidence can make medical AI more interpretable.
I am a Lecturer in the School of Computing and Mathematical Sciences at the University of Leicester, and a visiting researcher in computational pathology at the University of Oxford and in artificial intelligence at the University of Southampton.
02 · Opportunities
Prospective PhD students
I welcome enquiries from strong candidates who want to develop interpretable and biologically grounded AI for pathology, cancer research, and multimodal medicine.
CSC-funded PhD
I welcome strong applicants seeking full PhD funding through the China Scholarship Council, subject to the annual scheme and university requirements.
Funded openings
Other fully and partially funded PhD opportunities will be added here as soon as new projects and scholarship routes become available.
03 · Research
Computational pathology
Multi-scale histomorphology for molecular trait prediction, cancer relapse analysis, fibrosis phenotyping, and spatial tissue understanding.
Interpretable foundation models
Behavioural analysis, adaptive model fusion, and efficient feature perception for revealing when medical AI is robust and biologically meaningful.
Multimodal biomedical AI
Cross-modal links between histology, spatial transcriptomics, endoscopy, clinical records, and tumour microenvironment evolution.
Seminar recording
Computational pathology before and after the foundation model era
A short recorded seminar if you would like to know more about my research.
Watch on YouTube ↗04 · News
Recent activity
Newest firstAwarded 10,000 hours on the UKRI Isambard-AI and Dawn AIRR supercomputers through the Gateway route (PI).
Organized and chaired the IEEE ICME 2026 workshop Physical Principles for Reliable 3D Modelling in Multimedia.
Invited talk, The post-foundation model era of computational pathology, at the 2nd Royal College of Radiologists Global AI Conference in London.
Clinically-informed prompt learning for explainable diagnosis with biomedical vision-language models published in Pattern Recognition.
Distilling Knowledge from Multiple Foundation Models for Accurate and Efficient Spatial Gene Expression Prediction accepted at ISBI as an oral presentation.
Decoding fibrosis, an AI-derived study of collagen deposition phenotypes in MASLD, published in Hepatology.
Self-supervised Monocular Depth and Pose Estimation for Endoscopy with Latent Priors published in IEEE Transactions on Medical Imaging.
TraceTrans: Translation and Spatial Tracing for Surgical Prediction accepted at AAAI.
Invited talk, AI in Computational Pathology, at the RadExIORSBoost Project Workshop and Training, University of Leicester.
Invited talk, The post-foundation model era of Computational Pathology, at the Discovering Challenges and Opportunities in AI for Medicine and Surgery workshop, University of Leeds.
Guest lecture for BS3083 Respiratory and Cancer Precision Medicine at the University of Leicester.
Invited talk, Does AI-Powered Cancer Understanding Come with Sufficient Interpretability? A Computational Pathology Perspective, at the Cancer Research UK Data-driven Cancer Research Conference in Edinburgh.
Invited seminar, Computational Pathology Before and After the Foundation Model Era, at the University of Warwick.
Joined the University of Leicester as Lecturer in Computer Science.
Seminar, Exploring the Impact of Micro-features on Macro-morphological Understanding in Computational Pathology, CMS Computing seminar series, University of Leicester.
Oral presentation of GenST at the MICCAI Workshop on Computational Pathology and AI for Life Sciences.
Invited talk, Instability of Feature-Driven XAI in Computational Pathology, at MICCAI SIG-xMedIA.
Featured on Oxford's To Immunity and Beyond podcast to discuss self-interactive learning in computational pathology.
Invited talk, When Machines Interpret, at the LEAP Digital Health Hub Seminar Series, University of Bristol.
Invited keynote, Next generation of AI and clinician interaction, Unlimidata Ltd., London.
Invited keynote, Where is the meeting point for AI for medical science?, University of Bristol.
05 · Publications
Selected publications
A broader selection of recent, high-impact, and representative work. Yang Hu is shown in bold.
2026 6
Xie, H., Fan, Y., Law, N. F., Zheng, Y.-P., Ling, S. H., Hu, Y., & Ju, Y. Clinically-informed prompt learning for explainable diagnosis with biomedical vision-language models. Pattern Recognition, 180, 114114.
Wojciechowska, M., Thing, M., Hu, Y., et al. Decoding fibrosis: Transcriptomic and clinical insights via AI-derived collagen deposition phenotypes in MASLD. Hepatology.
Li, Z., Li, B., Hu, Y., Rittscher, J., & Verrill, C. Distilling Knowledge from Multiple Foundation Models for Accurate and Efficient Spatial Gene Expression Prediction. ISBI, oral presentation.
Xu, Z., Li, B., Hu, Y., et al. Self-supervised Monocular Depth and Pose Estimation for Endoscopy with Latent Priors. IEEE Transactions on Medical Imaging.
Luo, X., Li, H., Cheng, X., Zhao, H., Hu, Y., et al. TraceTrans: Translation and Spatial Tracing for Surgical Prediction. AAAI.
Hu, Y., Batchkala, G., Gaitskell, K., et al. Harness Behavioural Analysis for Unpacking the Bio-Interpretability of Pathology Foundation Models. medRxiv.
2025 5
Hu, Y., Sirinukunwattana, K., Li, B., et al. Self-interactive learning: Fusion and evolution of multi-scale histomorphology features for molecular traits prediction in computational pathology. Medical Image Analysis.
Hu, J., Guo, J., Luo, C., Hu, Y., Lanzinger, M., & Li, Z. Enabling Generalized Zero-Shot Vulnerability Classification. IEEE Transactions on Dependable and Secure Computing.
Xiao, Y., Hu, Y., Li, B., et al. AdaFusion: Prompt-Guided Inference with Adaptive Fusion of Pathology Foundation Models. arXiv:2508.05084.
Bonnaffe, W., Hu, Y., Chatrian, A., et al. Histology-informed tiling of whole tissue sections improves the interpretability and predictability of cancer relapse and genetic alterations. arXiv:2511.10432.
Wood, R., Hu, Y., Rittscher, J., & Li, B. GenST: A Generative Cross-Modal Model for Predicting Spatial Transcriptomics from Histology Images. MICCAI Workshop COMPAYL.
2024 3
Xu, Y., Wen, G., Hu, Y., & Yang, P. Modeling Hierarchical Structural Distance for Unsupervised Domain Adaptation. IEEE Transactions on Circuits and Systems for Video Technology.
Yao, Y., Liu, X., Yu, Z., Lv, J., Hu, Y., & Yang, K. Unsupervised Cross-Modal Medical Image Retrieval with Ensemble Prototype Alignment. IEEE MedAI.
Shi, Y., Yang, K., Wang, M., et al. Boosted unsupervised feature selection for tumor gene expression profiles. CAAI Transactions on Intelligence Technology.
2022 3
Hu, Y., Sirinukunwattana, K., Li, B., et al. Predicting Molecular Traits from Tissue Morphology Through Self-interactive Multi-instance Learning. MICCAI.
Dai, D., Yu, Z., Huang, W., Hu, Y., & Chen, C. P. Multi-Objective Cluster Ensemble Based on Filter Refinement Scheme. IEEE Transactions on Knowledge and Data Engineering.
Hu, Y., Chapman, A., Wen, G., & Hall, W. What can knowledge bring to machine learning? A survey of low-shot learning for structured data. ACM Transactions on Intelligent Systems and Technology.
2021 6
Hu, Y., Wen, G., Luo, M., et al. Inner-Imaging Networks: Put Lenses Into Convolutional Structure. IEEE Transactions on Cybernetics.
Hu, Y., Wen, G., Luo, M., et al. Fully-channel regional attention network for disease-location recognition with tongue images. Artificial Intelligence in Medicine.
Hu, Y., Wen, G., Chapman, A., et al. Graph-based visual-semantic entanglement network for zero-shot image recognition. IEEE Transactions on Multimedia.
Xu, Y., Wen, G., Hu, Y., et al. Task-Coupling Elastic Learning for Physical Sign-Based Medical Image Classification. IEEE Journal of Biomedical and Health Informatics.
Li, Y., Wen, G., Hu, Y., et al. Multi-source Seq2seq guided by knowledge for Chinese healthcare consultation. Journal of Biomedical Informatics.
Xu, Y., Wen, G., Hu, Y., & Luo, M. Multiple attentional pyramid networks for Chinese herbal recognition. Pattern Recognition.
2020 3
Wen, G., Chen, H., Li, H., Hu, Y., et al. Cross domains adversarial learning for Chinese named entity recognition for online medical consultation. Journal of Biomedical Informatics.
Liang, H., Wen, G., Hu, Y., et al. MVANet: Multi-Task Guided Multi-View Attention Network for Chinese Food Recognition. IEEE Transactions on Multimedia.
Wen, G., Ma, J., Hu, Y., et al. Grouping attributes zero-shot learning for tongue constitution recognition. Artificial Intelligence in Medicine.
2019 3
Hu, Y., Wen, G., Liao, H., et al. Automatic construction of Chinese herbal prescriptions from tongue images using CNNs and auxiliary latent therapy topics. IEEE Transactions on Cybernetics.
Dai, D., Tang, J., Yu, Z., et al. An inception convolutional autoencoder model for Chinese healthcare question clustering. IEEE Transactions on Cybernetics.
Hu, Y., Wen, G., Ma, J., et al. Label-indicator morpheme growth on LSTM for Chinese healthcare question department classification. Journal of Biomedical Informatics.
06 · Contact
For research collaboration, talks, and PhD enquiries.
KE523, Ken Edwards Building
University of Leicester
Leicester LE1 7RH, UK