BosomShield is a project funded by MARIE SKŁODOWSKA-CURIE doctoral networks actions (HORIZON-MSCA-2021-DN-01-01) with a grant number of 101073222.
A comprehensive CAD system based on radiologic- and pathologic-image biomarkers for diagnosis and prognosis of breast cancer relapse
BosomShield proposes 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 high-level training in breast cancer research to young researchers by offering the necessary transferable skills for thriving careers underpinned using diverse disciplines, digital radiology and pathology, biomedical, AI, privacy and software development. The consortium of BosomShield has ten beneficiaries and twelve associated partners, and it is well balanced with:
- Expert radiologists and pathologists (Pere Virgili Institute for Health Research (Spain), University Hospital Sant Joan de Reus (Spain), Skåne University Hospital (Sweden), Univerzitetni klinicni center Maribor (Solvenia), Hospital Universitario Puerta del Mar (Spain), Azienda Sanitaria Universitaria Friuli Centrale (Italy) and Hospital de Tortosa Vergé de la Cinta (Spain))
- Biomedical researchers (Universitat Rovira i Virgili (Spain), KTH Royal Institute of Technology (Sweden), Stichting Radboud Universitair Medisch Centrum (Netherland), Nalecz Institute of Biocybernetics and Biomedical Engineering (Poland), University of Udine (Italy), Université Bourgogne Franche-Comté (France), University of Maribor (Slovenia), Institute of Technology Petronas (Malaysia) and The University of Texas Health Science Center at Houston (USA))
- Biomedical software developers including SMEs (NVISION Systems and Technologies SL (Spain), Mediri GmbH (Germany), UMMON HEALTHTECH (France) and SFERA IT STORITVE DOO (Slovenia))
- International large companies (O3 Enterprise S.R.L. (Italy) and General Electric Research (USA))
The fact that all key areas related to the application of advanced methods for breast cancer relapse prediction are covered by more than one participant ensures the uninterrupted progress of the project, as well as its scientific integrity.
University of Maribor hosts project DC8, Explainable Prediction model of breast-cancer relapse combining histopathological, radiological and clinical biomarkers. The project will be co-supervised with Oncology Department at University Clinical Center Maribor to achieve the overarching goal, to build an (X)AI-based breast-cancer relapse prediction model by combining three types of data; histopathological, radiological biomarkers and clinical records (including medical history).
