Next-Gen Catalysts

FIREDANSE: Federated Infrastructure for Digital Pathology Reporting and Expert Data Annotation in a Secure Environment

FIREDANSE is enabling secure, federated access to digital pathology data, enabling clinicians to support trustworthy AI development across hospitals.

Digital pathology images are essential for developing and validating AI tools, but access to these data is often restricted due to privacy concerns and technical fragmentation. Centralising such data is rarely feasible, particularly across NHS organisations with different governance arrangements. This limits the ability to develop robust, generalisable AI models.

FIREDANSE will create a federated infrastructure that allows de-identified pathology data to be accessed securely across sites without moving the underlying data. The project enhances an existing collaborative annotation platform previously used to facilitate multicentre clinical trials via data-sharing, to enable experts to review and validate AI outputs across federated Trusted Research Environments (TREs). This approach ensures that AI development remains clinically grounded and accountable.

By demonstrating real-world federated workflows, FIREDANSE will show how digital pathology data can be used responsibly at scale. The project will provide practical insights into how federated TRE architectures can support safe, collaborative AI research in healthcare.

FIREDANSE builds on extensive prior public and patient involvement through the Royal Marsden PPIE programme and the  Imperial Discover-NOW Citizens Advisory Group. Public contributors have shaped the project design and will continue to participate via representation on the Project Management Board. Engagement activities will focus on explaining AI, federation, and privacy in accessible terms.

By the end of the project, FIREDANSE will:

  • Demonstrate federated access to digital pathology data across NHS sites
  • Enable clinician-led annotation and validation of AI models
  • Produce guidance for secure, federated pathology research
  • Support trustworthy AI development in clinical settings

Project information

Lead organisation: Institute of Cancer Research
Principal investigator: Prof Manuel Salto-Tellez
Project duration: 12 months
Project partners: Imperial College London, Royal Marsden NHS Foundation Trust, Erasmus Medical Center
Funding provided: £356,961
Primary contact email: simon.doran@icr.ac.uk

GET IN TOUCH

If you’re interested in learning more about our work, how it can benefit you, or how to get involved, click the button to get in touch with us using our contact form.