Objectives
BosomShield aims to join the two disciplines (pathological and radiological imaging) in a software that will analyse these images to classify the breast cancer subtypes and predict (together with the complete clinical history of the patient) the probability of relapse for distant metastasis. In addition, BosomShield will provide young researchers with high-level training in breast cancer research by offering the necessary transferable skills for thriving careers underpinned by diverse disciplines, digital radiology and pathology, biomedical, AI, privacy and software development.
Our Role
NVISION is responsible for developing a privacy-preserving federated learning framework for breast cancer diagnosis and relapse prediction. Using this approach, multiple hospitals can collaborate to create highly effective AI models while ensuring their private data remains secure and is not shared with other institutions.
Funding
MARIE SKŁODOWSKA-CURIE DOCTORAL NETWORKS ACTIONS
