TIA Centre Seminars

Dr Yuri Tolkach

University Hospital Cologne, Germany

Yuri Tolkach, MD, PhD, is an attending pathologist at the University Hospital Cologne, Germany, and a Lead of the Research Group for AI applications in digital pathology (tolklab.de). His work has focused on developing diagnostic tools across multiple tumour types, quality control in pathology, and computational pathology challenges (e.g. SemiCOL). He has served as Vice-President of ESDIP and a Chair of scientific committee of ECDP (2022-2024).

🔬 Computational Pathology •💬 LLMs & Agents • 🤖 Foundation Models

An agentic framework for autonomous scientific discovery in cancer pathology

📅 Monday 19th October 2026

🕐 2:00-3:00 PM

SPARK is an agentic AI framework that autonomously generates biologically-driven concepts for cancer pathology. Across 18 cohorts and more than 5,400 patients, SPARK identified clinically relevant concepts associated with prognosis, pathology variables and predictive biomarkers.

📄An agentic framework for autonomous scientific discovery in cancer pathology | Nature Medicine

Safety and Security of Large Language Models in Healthcare

📅 Monday 9th November 2026

🕐 2:00-3:00 PM

Large language models (LLMs) are rapidly entering clinical practice. Drawing on insights from a recent Nature Review, Germany’s largest survey of clinician AI chatbot use (>4,000 respondents), and real-world deployment experience, Dr Jan Clusmann explores the opportunities, risks, and readiness of LLMs for healthcare.

📄Safety and security of large language models in healthcare | Nature

Dr Jan Clusmann

TU Dresden, Germany

🩺 Clinical AI • 💬 LLMs & Agents • 🏥 Digital Health

Dr Hao Chen

The Hong Kong University of Science and Technology, China

Prof. Hao Chen is an Assistant Professor at the Department of CSE&CBE&LIFE, The Hong Kong University of Science and Technology. He leads the SmartX Lab focusing on large and trustworthy AI for healthcare. He serves as Director of Collaboration Center for Medical and Engineering Innovation, HKUST. He received the Ph.D. degree from The Chinese University of Hong Kong (CUHK) in 2017. He has 100+ publications (Google Scholar Citations 51200, h-index 101) in top-tier journal/conferences including Nature Medicine, Nature Biomedical Engineering, Nature Machine Intelligence, Lancet Digital Health, IEEE-TPAMI, CVPR, etc. He also has rich industrial research experience and holds a dozen of patents in AI and medical image analysis. He received several premium awards such as Asian Young Scientist Fellowship, MICCAI Young Scientist Impact Award, and several best paper awards. He serves as the Associate Editor of multiple journals including IEEE RBME, TMI, TNNLS, JBHI, etc. He also led the team winning 15 medical grand challenges. SmartX website: https://smartx.ust.hk/

Pathology Foundation Models-driven Agentic AI for Precision Oncology

📅 Monday 16th November 2026

🕐 2:00-3:00 PM

With the deep integration of AI and digital pathology, large pathology models become the foundation backbones in computational pathology for precise cancer diagnosis and treatment. This talk will systematically explore the cutting-edge advancements of large pathological models in precise cancer diagnosis, molecular subtyping prediction, treatment response assessment, and prognostic analysis, revealing the breakthrough potential in achieving "micro-meso-macro" analysis through multimodal data integration (such as whole-slice images, imaging, genomics, and clinical information). We will further explore how large pathology models-driven agentic AI are transforming the paradigm in precision oncology and beyond.

Explainable Artificial Intelligence (XAI) in Computational Pathology

📅 Monday 30th November 2026

🕐 2:00-3:00 PM

Computational pathology models are increasingly used for diagnosis, prognosis, and treatment prediction, yet many remain difficult to interpret. Drawing on a recent MICCAI SIG-CompPath review, this talk presents a pathology-focused framework for explainable AI, including a structured taxonomy of XAI methods and practical guidance for linking clinical questions to appropriate interpretability approaches.

📄 [2608.28820] Explainable Artificial Intelligence (XAI) in Computational Pathology: Definitions, Taxonomy, and Recommendations

Shubham Innani

Indiana University School of Medicine, USA

Shubham is a Research Data Analyst at Indiana University School of Medicine, USA, working at the intersection of biomedical image analysis, clinical AI and translation. His research focus spans diagnostic, biomarker prediction and prognostic modelling from whole-slide images, with broader interests in deep learning, foundation models and agentic AI in computational pathology. He aims to bridge computational innovation with clinical needs by developing AI approaches that are reproducible, explainable, and translatable to real-world decision-making for precision oncology.