ESTRO 2021 Abstract Book

S656

ESTRO 2021

A summary of key dosimetric factors for MCO GS can be found in Table 1. No statistically significant dosimetric differences were found between the two techniques overall; dose distributions were highly similar and all were clinically acceptable. D 98% and D 2% for both PTVs were highly comparable to one decimal place. Marginal differences were observed for other metrics with the largest differences observed for rectum. Figure 1 shows an example of dosimetric differences between the two plans. and MCO ML

Conclusion This study shows evidence that ML with MCO can be used to effectively calibrate plans for prostate cancer patients. As MCO ML yielded plans that were clinically equivalent to MCO GS plans, there is evidence of only a nominal advantage to GS planning over ML planning and that expert planning with MCO can be modelled using regression. [1]Physics and Imaging in Radiation Oncology, 10, 41-48. doi: 10.1016/j.phro.2019.04.005 PD-0823 Development of artificial intelligence based treatment planning for locally advanced breast cancer D. van de Sande 1 , H. Bluemink 1 , E. Kneepkens 1 , N. Bakx 1 , E. Hagelaar 1 , M. Sharabiani 2 , C. Hurkmans 1 1 Catharina Hospital, Radiation Oncology, Eindhoven, The Netherlands; 2 European Organisation for Research and Treatment of Cancer (EORTC), Headquarters, Brussels, Belgium Purpose or Objective Treatment planning of locally advanced breast cancer patients can be a time consuming process. Artificial intelligence based treatment planning could be used as a tool to speed up this process and to maintain plan quality consistency. The