The EuCanImage project has made significant advancements, beginning with the establishment of a legal and ethical framework for sharing oncological imaging data for AI purposes, as addressed in WP 1 and 9. The project successfully completed the requirements analysis for all use cases, covering elements such as case descriptions, anonymisation methods, and data linkage protocols. Currently, the EuCanImage repository hosts over 30,000 individual cases, following the ingestion and annotation processes by project partners and the incorporation of new external datasets (WP 2). In WP3, we've developed a FAIR-compliant data point within XNAT for managing non-raw DICOM data. The coding frameworks and data models for non-imaging clinical data have been finalised, and electronic case report forms (eCRFs) are now operational for uploading non-imaging data. We've also established linkages between XNAT, EGA (based in Europe), and the project catalogue, including a connection to TCIA (based in the US), to support international studies. WP4 focused on optimising data curation and quality control, tailoring these processes to specific use cases. Annotation strategies for colorectal and liver cases are in place, and tools for breast case annotations, utilising public datasets, have been integrated into the AI-VRE, which now includes the completed Machine Learning Toolbox (T5.3). WP5 saw the introduction of an updated, publicly available version of the Federated Learning platform, the implementation of the latest FUTURE-AI guidelines, reflecting insights from over 100 experts in multiple fields along with the training of AI models on the different clinical questions of each use case. In WP6 the tool, featuring Radiomics Readiness Levels, is now available online. The MAMA-MIA Challenge was launched to establish a fairness-aware benchmark for breast cancer prediction and segmentation. The in silico trial platform has been deployed to enable virtual clinical trials with 3D image visualization. Cost-effectiveness models are completed. Benchmarking workflows and tools for standardized metrics evaluation are being implemented in OpenEBench. Communication and dissemination efforts under WP7 have resulted in enhanced website performance, increased social media engagement, and successful video content along with the organization of focused workshops, webinars and hands-on sessions. The project coordinator continues to provide scientific, administrative and financial support to all partners, while encouraging EuCanImage partners to engage with other initiatives, such as the AI4HI network and EUCAIM initiative through joint events and papers.
