ESTRO 2021 Abstract Book

S952

ESTRO 2021

breast volume (>750cc) and dermitis G1-2 (P: 0.03), however analysis didn´t show any relation between the age (p: 0.14), the use of hormonotherapy (p: 0.43), dose to PTV boost (p: 0.2), PTV Boost Volume (P: 0.31) or ratio PTV Boost/PTV Breast (P: 0.43) and tolerance. Conclusion Ultra-hypofractionated whole breast irradiation with simultateous integrated boost in 5 fractions along one- week is feasible and well tolerated in DCIS although longer follow-up is neccessary to confirm these results. PO-1144 Analysis of geometric and dosimetric effects of bra application during breast radiotherapy planning J. Choi 1 1 Jeju National University College of Medicine, Radiation Oncology, Jeju, Korea Republic of Purpose or Objective To evaluate geometric and dosimetric effects of bra application during radiotherapy planning for breast cancer patients with large and pendulous breasts Materials and Methods Twenty patients with chest sizes >38 inches between April 2019 and July 2019 underwent radiotherapy planning with and without a radiation bra (Chabner XRT ® ). Geometric and dosimetric parameters included the breast volume, superior-inferior (SI) distance, separation (S) as the distance of the longest diameter of the clinical target volume (CTV), conformity number (CN), and homogeneity index (HI) of CTV. The organs at risk (OARs) were defined as the lungs, heart, and liver. Results The use of the radiation bra provided mean changes of –0.51 cm for S, –1.45 cm for SI, and –61.18 cc for breast volume (all p<0.05). Breast volume was correlated with bra-related changes in cross diameter (r=0.641, p=0.002) and volume (r=0.680, p=0.001). Significant dose reductions were observed for the lungs (mean V 10 : 19.58 cc, V 20 : 17.13 cc, D mean : 86.24 cGy) and heart (D mean : 170.23 cGy). No significant differences were observed for CN (0.62–0.67) and HI (0.19–0.20) of the CTV. Conclusion The application of a radiation bra was associated with better geometric and dosimetric planning parameters, with a smaller CTV and lower doses to the OARs (lungs and heart) in the radiotherapy field. In addition, we expect that bra use during radiotherapy would provide emotional benefits. PO-1145 Evaluation of deep learning-based auto-segmentation of OARs for breast cancer radiotherapy H.K. Byun 1 , J.S. Chang 1 , M.S. Choi 1 , J. Chun 1 , J. Jung 2 , C. Jeong 2 , J.S. Kim 1 , Y. Chang 3 , S. Lee 4 , Y.B. Kim 1 1 Yonsei University College of Medicine, Department of Radiation Oncology, Seoul, Korea Republic of; 2 Asan Medical Center, University of Ulsan, College of Medicine, Department of Radiation Oncology, Seoul, Korea Republic of; 3 Coreline Soft, Co., Ltd, Coreline Soft, Co., Ltd, Seoul, Korea Republic of; 4 Yonsei University College of Medicine, Yonsei University College of Medicine, Seoul, Korea Republic of Purpose or Objective A large inter-physician variation can be seen when delineating organ-at-risks (OARs) for breast radiotherapy. This study aimed to externally validate the performance of deep learning-based auto-contouring system (ACS) Eleven experts from two institutions were asked to delineate 9 OARs of 10 cases of breast radiotherapy. Then, auto-contours were provided to the experts for correction. To compare the performance of auto-, corrected- auto-, and experts’ manual contours, Dice similarity coefficient (DSC) and Hausdorff distance (HD) between each contour and the best manual contour were used, where higher DSC and lower HD means better geometric overlap. Results Total mean time for 9 OARs was 37±20 min for manual and 6±5 min for corrected-auto-contours. Among the DSC of experts’ manual contours and an auto-contour, DSC of an auto-contour ranked the second place and HD ranked the first place. Better performance was shown in corrected-auto-contours than in manual contours (median DSC: 0.90 vs. 0.88; median HD: 4.5 vs. 6.5 mm). The inter-physician variations among experts were reduced in corrected-auto-contours, compared with manual contours (DSC range: 0.86–0.90 vs. 0.89–0.90; HD range: 5.1–9.1 mm vs. 4.3–5.7 mm). Among manual OARs, breast contours had the largest variations, which were most significantly improved with an aid of ACS. Conclusion ACS showed at least similar performance in OARs compared with experts’ manual contouring, which anticipates further applications of ACS to target volumes. ACS can be a valuable tool for improving the quality of breast radiotherapy and reducing inter-physician variability in clinical practice. PO-1146 Perioperative HDR brachytherapy for breast cancer, technique implementation in a single institution M. Gaztañaga 1 , E. Cerezo 1 , N. Sanmamed 1 , P. Alcantara 1 , A. Doval 1 , J. Corona 1 , Z. Aza 2 , B. Gonzalez 3 , A. Pascual 4 , M. Montes 5 , A. de Luna 6 , G. Vázquez 1 1 Hospital Clínico San Carlos, Radiation Oncology, Madrid, Spain; 2 Hospital Clínico San Carlos, Medical Physics, Madrid, Spain; 3 Hospital Clínico San Carlos, Gynaecology, Madrid, Spain; 4 Hospital Clínico San Carlos, Pathological Anatomy, Madrid, Spain; 5 Hospital Clínico San Carlos, Radiology, Madrid, Spain; 6 Hospital Clínico San Carlos, Medical Oncology, Madrid, Spain for breast radiotherapy. Materials and Methods

Purpose or Objective Breast brachytherapy for accelerated partial breast irradiation (APBI) in the perioperative setting has been