Advanced medical imaging in oncology has gained increasing interest for its potentials in radiotherapy image guidance and more recently for treatment personalization. There exists a general consensus that the information derivable from the multi-modal image dataset, which is typically acquired on patients during the radiotherapy treatment workflow, can serve for identifying image-based biomarkers, which exhibit relevant predictive power on treatment outcomes. Despite these evidences, the current models applied in the clinics to tune the treatment plan dosimetry, as a function of the expected tumour response and radiation-induced toxicity, do not make use of patient-specific imaging data, but rely on radiobiological parameters typically derived from in-vitro experiments, thus abdicating from describing the in-vivo biological complexity of the pathology and organs at risk on a patient-specific and multi-scale basis.

The project TAILOR - A technical framework for combining multi-parametric imaging with advanced modelling in personalized radiotherapy, proposed by Prof. Guido Baroni and CartCasLab, and funded by Associazione Italiana per la Ricerca contro il Cancro (AIRC), aims at overcoming the above-mentioned limitations by integrating patient-specific multi-parametric imaging and advanced mathematical models revealing macroscopic, microscopic and radiobiological information, to provide the empowerment of treatment outcome prediction, patients' stratification and subsequent treatment optimization and personalization in external beam radiotherapy.

Through a key collaboration with clinical institutions, including the National Center for Oncological Hadrontherapy (CNAO, Pavia, Italy) and the European Institute of Oncology (IEO, Milano, Italy), the envisioned mathematical models will exploit optimized multi-parametric imaging to predict treatment outcome at different scales. These models will then serve as decision-making tools in radiation therapy towards an optimized and personalized approach which will lead to improved patient care and reduced treatment costs.