ESTRO 2025 - Abstract Book

S468

Clinical - Breast

ESTRO 2025

Figure 1: Example of automatic delineation of target volumes and organs-at-risk in the isocentric lateral decubitus position. A: The breast clinical target volume (CTV, in red), heart (orange), and lungs (right lung in blue, left lung in yellow) are delineated by the autosegmentation algorithm. B and C: Comparison between the automatically segmented CTV (red) and the manual CTV (blue). Conclusion: This neural network-based auto-contouring algorithm offers a practical, time-saving solution for breast cancer radiotherapy planning in the isocentric lateral decubitus position. Its strong geometric performance, clinical acceptability, and significant time efficiency make it a valuable tool for modern radiotherapy practices, particularly in high-volume centers.

Keywords: automated contouring; lateral decubitus

1037

Digital Poster Predictors of Pneumonitis in Patients Treated with Systemic Therapy and Radiotherapy for Localized Triple Negative or HER2+ Breast Cancer Hannah Bacon 1 , Xiang Y Ye 2 , Zhihui Amy Liu 2 , Eitan Amir 3 , Ezra Hahn 1,4 , Andrew Hope 1,4 , Anne Koch 1,4 1 Department of Radiation Oncology, University of Toronto, Toronto, Canada. 2 Department of Biostatistics, Princess Margaret Cancer Centre, Toronto, Canada. 3 Division of Medical Oncology and Hematology, Princess Margaret Cancer Centre, Toronto, Canada. 4 Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Canada Purpose/Objective: Recent RCTs including KEYNOTE-522 and KATHERINE have established perioperative immune checkpoint inhibitors (ICIs) as a standard of care treatment for patients with stage II or stage III triple negative (TN) breast cancer, 1 and adjuvant trastuzumab emantasine (T-DM1) as a standard of care treatment for patients with stage I to stage III