Despite tremendous advances in modern imaging technology, both early detection and accurate diagnosis of breast cancer are still unresolved challenges. Unnecessary biopsies are taken and tumours frequently go undetected until a stage where therapy is costly or unsuccessful.
HAMAM will tackle this challenge by providing a means to seamlessly integrate the available multi-modal images and the patient information on a single clinical workstation. Based on knowledge gained from a large multi-disciplinary database, populated within the scope of this project, suspicious breast tissue will be characterised and classified.
The exact diagnosis of suspicious breast tissue is ambiguous in many cases. HAMAM will resolve this using statistical knowledge extracted from the large case database. The clinical workstation will suggest additional image modalities that may be captured to optimally resolve these uncertainties. The workstation thus guides the clinician in establishing a patient-specific optimal diagnosis. This ultimately leads to a more specific and sensitive individual diagnosis.
HAMAM advances the state-of-the-art as it proposes a sound statistical and mathematical framework to integrate and combine the whole spectrum of patient information. HAMAM also goes beyond currently available technology by developing a prototypical solution that will be able to efficiently integrate all relevant clinical and imaging information within a single platform.
The overall strategy of the project is to foster the exchange and collaboration between basic scientists, clinicians, and IT experts, and to condense all information and knowledge in a common database and prototypical platform for multi-modal breast diagnosis.
For further information, please visit: