Radiotherapy for prostate cancer (PC) involves irradiation not only of the target volume but also of portions of healthy neighboring Organs at Risk (OaR) such as bladder, rectum or penile bulb. RT-induced morbidity of sexual, urinary, or rectal nature can arise, impacting Quality of life (QoL). RT protocols are currently optimised on the former assumptions that the radio-sensitivity and the functionality are uniform within the same OaR. Image mining of 3D dose distribution in low spatial scales, via voxel-based population methods, has highlighted the existence of radiosensitive sub-regions (SRR) responsible of radio-induced toxicity. Modern RT protocols have not yet incorporated these findings due to the lack of i) extensive validation ii) dosimetric constraints for plan optimisation and iii) automated patient-specific SRR contouring methods. The goal of PerPlanRT is to devise innovative decision-making tools aimed at proposing integrated and feasible strategies for personalised RT in PC with reduced RT-induced toxicities. Multivariable spatially accurate predictive models derived from large set of cohorts prospectively collected will be applied to different RT scenarios to explore their patient-specific benefits in depth. The application of these models to the clinical practice will be performed through the generation of dose distributions adapted to patient-specific anatomies.