TIA Centre: News
To see our previous half-yearly newsletters click here.
Bigpicture Annual Meeting 2026: The Consortium Gathers in Berlin
The fifth took place from 28 to 30 January 2026 in Berlin, kindly hosted by Bayer at its Müllerstraße venue. Over three packed days, partners from across the consortium gathered to share progress, align priorities, and plan the next steps in developing a large-scale digital pathology platform and repository.
The Bigpicture ProjectThe Bigpicture project is an initiative aimed at transforming the field of pathology through the creation of a comprehensive, high-quality digital repository of three million pathology images. Funded by the EU Innovative Medicines Initiative (IMI), Bigpicture brings together a consortium of leading academic institutions, research organisations, and industry partners from across Europe and beyond. The project’s mission is to develop an open-access platform that leverages artificial intelligence and machine learning to analyse vast amounts of pathology data, advancing research, diagnostics, and treatment in healthcare. By fostering collaboration and innovation, Bigpicture envisions a future where digital pathology becomes a cornerstone of precision medicine, enabling faster, more accurate diagnoses and personalised patient care. The Bigpicture project is structured into six Work Packages (WPs), each focusing on a critical aspect of building and leveraging a large-scale digital pathology platform. Further information on the Bigpicture work packages can be found . |
|
How the TIA Centre is Contributing to Bigpicture
The TIA Centre is a key contributor to the consortium and the Bigpicture project, which primarily focuses on Work Package 4 (WP4). This work package aims to advance AI-driven computational pathology by developing tools for accessing, annotating, and analysing digital pathology slides. It leverages Cytomine, Bigpicture’s platform, for Whole Slide Imaging (WSI) access and visualisation and is dedicated to creating task-agnostic AI models, federated learning strategies and an integrated app store for AI algorithms.
At the TIA Centre, our focus has been on developing AI tools like automated tumour-infiltrating lymphocytes (TILs) detection and nuclear instance segmentation/classification to improve diagnostic accuracy and efficiency. We’ve also carried out domain generalisability research to ensure AI models perform reliably across different datasets and institutions. Our aims have been to integrate these tools into Cytomine for AI-powered slide analysis and annotation, and to document models transparently to support reproducibility and interoperability. By bridging cutting-edge AI research with the Cytomine platform, the TIA Centre strengthens Bigpicture’s mission to transform digital pathology into a scalable, standardised resource for global healthcare innovation.
The Fifth Annual Meeting in Berlin
Each year the Bigpicture consortium convenes to share insights, address challenges, and plan future steps. This year’s meeting was hosted by Bayer in Berlin. Berlin provided a fitting setting for a project that sits at the intersection of pathology and computing. The city’s scientific and technical history, associated with figures such as Rudolf Virchow and Konrad Zuse, reflects the deep scientific roots behind today’s computational pathology.

The Annual Meeting Programme Highlights
The three-day programme combined consortium-wide updates and work package highlights with interactive sessions that supported discussion and alignment across partners. Alongside focused showcases, the agenda included five workshops and a hands-on demo session, giving attendees opportunities to share feedback and shape priorities for the next phase of work.

Showcases ranged from how partners can find datasets and access material through the repository, to examples of AI development being integrated into the platform. Taken together, they offered a tour of what’s currently working and what’s coming next while connecting the dots between data, the platform, tools, and real end-user workflows.
The workshops were where much of the detailed discussion happened. These interactive sessions were designed to collect input and agree on priorities for the next stage of the project. Much of the discussion centred on how to scale data access and usage in a way that stays fit-for-purpose, and how to improve integration and usability so the platform feels coherent and easy to use. Other sessions looked ahead to bigger technical and strategic questions, including foundation models, benchmarking and indirect access, and sustainability planning beyond the current funding period.
The live demos, run alongside a walking lunch, brought a lot of energy. With short rounds of laptop/poster demonstrations in small groups, attendees could see tools running and give feedback.
The consortium dinner at the Museum für Naturkunde (Museum of Natural History) was truly memorable. We dined in a remarkable setting surrounded by 150-million-year-old dinosaur skeletons. Impressively, one of the specimens holds the Guinness World Record for the tallest mounted dinosaur skeleton at 13.27 metres (43 feet 6 inches). Beyond the venue, the dinner provided a space for people to reconnect across work packages and continue informal conversations.

Key Takeaways
From a WP4 perspective, several themes stood out stood out as themes likely to shape the next phase of work.
![]() |
Growing emphasis on enabling wider use of the data A recurring topic was how to help the consortium members and the wider community start engaging with Bigpicture resources in practice. In that context, the emphasis on “benchmarking and indirect access” felt especially important: it offers a realistic route for researchers to work with the data through structured evaluation tasks, even when direct access is not immediately available. These discussions also naturally connected to the idea of organising new grand challenges that bring in external teams and support reproducible benchmarking and evaluation while still respecting governance and access constraints. Foundation models on the horizon It was notable to see the foundation models take an important place in the discussions. While not part of the project’s original design, these approaches have gained significant traction in computational pathology in recent years. Their presence in the agenda reflects how the consortium is adapting as the research landscape changes. Sustainability and adapting to what’s nextSustainability was a recurring theme throughout the meeting. Partners revisited what it will take to support Bigpicture in the long term, exploring different models and next steps for keeping the platform, data, and workflows viable and accessible beyond the current project timeline. |
Summary
Bigpicture’s Annual Meeting in Berlin was a valuable chance to reconnect across the consortium and align priorities for what comes next. Alongside platform and data updates, the programme highlighted growing interest in benchmarking and indirect access, forward-looking discussion around foundation models, and continued attention to sustainability.
It was a productive three days, leaving many of us with fresh ideas and renewed motivation for the next phase.
Many thanks to the organisers and all consortium partners for another productive annual meeting, and to Bayer for hosting the event in Berlin.
![]() |
![]() |
By Gozde Gunesli
Newsletters
Newsletters from 2024/25:



