Advanced Computing in the Age of AI | Monday, April 22, 2024

BSC Champions EU’s EUCAIM Initiative: Cancer Image Europe Sets New Standard for AI in Oncology 

Oct. 5, 2023 -- The EUCAIM consortium, of which the Barcelona Supercomputing Center – Centro Nacional de Supercomputación (BSC-CNS) is a member, and the European Commission have announced the first public release of its platform, Cancer Image Europe, marking a major milestone in the project’s development. The first platform release brings benefits to researchers, clinicians and AI innovators across Europe and paves the way for the future of cancer diagnosis and treatment.

By releasing the first version of Cancer Image Europe, sharing of cancer images and supporting clinical data is facilitated and collaboration between researchers, clinicians and AI innovators across Europe is stimulated. The platform aims to accelerate the pace of AI development and other data-intensive cancer research activities, thereby enabling and empowering scientific breakthroughs that will shape the future of cancer diagnosis and treatment. The project’s goals and vision contribute to the strategic objectives of the European Union's initiatives and foster innovation and research.

“This early prototype of EUCAIM serves to bring together the different building blocks of the future federated infrastructure and start collecting feedback from the different users profiles that will be using it. We want to ensure that the platform – including its federated learning capabilities – is fit for purpose by design,” said BSC researcher Salvador Capella.

Key features and highlights of EUCAIM's first platform release include:

  • A public catalogue of cancer imaging datasets from the repositories of the EU-funded AI for Health Imaging projects, following a common metadata schema.
  • A federated searching tool to understand the information available in the federated providers.
  • Full integration with the Life Science Login Authentication and Authorisation Infrastructure.
  • Reusing and adding value to key components of EU-funded research projects and infrastructure in the field of cancer.

Atlas of Cancer Imaging

With the Cancer Image Europe infrastructure, the EUCAIM project addresses the fragmentation of existing cancer image repositories. A distributed Atlas of Cancer Imaging with over 60 million anonymized cancer image data from over 100,000 patients will be established as part of future updates, and the infrastructure will be fully in alignment with the European Health Data Space. The data will be accessible to clinicians, researchers and innovators across the EU for the development and benchmarking of trustworthy AI tools.

The EUCAIM project is a cornerstone of the European Commission-initiated European Cancer Imaging Initiative, a flagship of the Europe's Beating Cancer Plan, which aims to foster innovation and deployment of digital technologies in cancer treatment and care, to achieve more precise and faster clinical decision-making, diagnostics, treatments and predictive medicine for cancer patients.

BSC Contribution

The BSC leads, together with the University of Barcelona (UB), one of the technical work packages (WP6). WP6 deals with federated learning and analysis solutions, and is focused on defining alternative approaches to exploit the data provided by the consortium members, from a fully federated version where computation occurs in each of the data provider nodes to hybrid models where computation can be performed between compute nodes and data nodes, including the EUCAIM central node.

In addition, BSC seeks to bring the computational resources available to the scientific community through EuroHPC. This effort focuses on facilitating the use of the computational infrastructures funded by the EU, in close coordination with the member states, by the European research community.

BSC also leads the project’s technical and scientific benchmarking activities, both in WP6 and WP7, using the OpenEBench platform, developed in the context of ELIXIR, the pan-European infrastructure for managing research data in the Life Sciences.


Source: BSC

EnterpriseAI