Jan. 27, 2023 — The EUCAIM consortium and the European Commission (EC) have announced the official launch of the European Federation for Cancer Images (EUCAIM), a ground-breaking federated infrastructure deployment project aiming to power up imaging and AI towards precision medicine for Europe’s cancer patients and citizens.
EUCAIM will address the fragmentation of existing cancer image repositories and establish a distributed Atlas of Cancer Imaging with over 60 million anonymized cancer image data from over 100,000 patients, accessible to clinicians, researchers and innovators across the European Union (EU) for the development and benchmarking of trustworthy AI tools.
The infrastructure will be further populated by observational studies from hospitals (21 clinical sites in 12 EU countries), include clinical images and link with pathology, molecular and laboratory data, and will be expanded to at least 30 distributed data providers from 15 countries by the end of the 4-year project. Federated AI solutions will be trained at the hospital data warehouses, keeping data privacy.
EUCAIM is the cornerstone of the European Commission initiated European Cancer Imaging Initiative, a flagship of the Europe’s Beating Cancer Plan (EBCP), 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.
It is scientifically led by Prof. Luis Martí-Bonmatí, Director of the Medical Imaging Department, Chairman of Radiology, La Fe University and Polytechnic Hospital (Valencia, Spain) and coordinated by the European Institute for Biomedical Imaging Research (EIBIR), established by and headquartered at the European Society of Radiology in Vienna, Austria.
The project builds upon the results of the work of the “AI for Health Imaging” (AI4HI) Network, which consists of 5 large EU-funded projects on big data and Artificial Intelligence in cancer imaging: Chaimeleon, EuCanImage, ProCancer-I, INCISIVE and Primage.
EUCAIM brings together 76 partners from 14 EU member states, covering competences in cancer imaging and care, big data in medical imaging, FAIR data management, ethical and legal aspects of medical data, development and deployment of research infrastructures, AI and machine learning, as well as dissemination, communication and stakeholder outreach in biomedical imaging.
The Barcelona Supercomputing Center-Centro Nacional de Supercomputación (BSC-CNS) 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.
EUCAIM was born from a cluster of biomedical imaging projects, including EuCanImage and INCISIVE, in which the BSC participates.
EUCAIM and GDI, the European Genomic Data Infrastructure, are part of the flagship projects by the EC to facilitate access to high-quality data from research and clinical settings (secondary use of data for research purposes) to advance in different scientific endeavors.
BSC researcher Salvador Capella-Gutierrez said: “This project aligns with a whole series of efforts within the Life Sciences department, connecting not only with other important projects such as GDI but also with projects like EOSC4Cancer and the [email protected] pilot, which aim to create the building blocks for both the Cancer Mission and the European Health Data Space from an infrastructure perspective. On a different scale, national projects such as IMPaCT-Data can benefit from EUCAIM outcomes by taking advantage of existing synergies. For example, the EUCAIM scientific coordinator, Prof. Luis Martí-Bonmatí, Director of the Medical Imaging Department, Chairman of Radiology, La Fe University and Polytechnic Hospital (Valencia, Spain), also leads the biomedical imaging efforts in IMPaCT-Data, the Data Science program at the Spanish National Infrastructure for Precision Medicine associated with Science and Technology.”
In line with the European data strategy and supporting the goals of the European Health Data Space, the EUCAIM will partner with the AI Testing and Experimentation Facility for Health under the Digital Europe Programme, allowing SMEs to access its infrastructure, and the services of the European Digital Innovation Hubs will support rollout.
EUCAIM follows an inclusive, collaborative approach and will interact with a plethora of stakeholders to ensure uptake at the political level in member states and wide use of the infrastructure by clinicians, researchers and innovators. Clinical data providers will be invited to join the initiative through an open call procedure during the project.
Source: The Barcelona Supercomputing Center-Centro Nacional de Supercomputación (BSC-CNS)