ESTRO 2025 - Abstract Book

S467

Clinical - Breast

ESTRO 2025

2. Krekel NM, Haloua MH, Lopes Cardozo AM, de Wit RH, Bosch AM, de Widt-Levert LM, et al. Intraoperative ultrasound guidance for palpable breast cancer excision (COBALT trial): a multicentre, randomised controlled trial. Lancet Oncol. 2013;14(1):48-54.

1020

Digital Poster Automated contouring for breast cancer radiotherapy in isocentric lateral decubitus position Pierre Loap, Rémi Monteil, Youlia Kirova, Jeremi Vu Bezin Department of Radiation Oncology, Institut Curie, Paris, France Purpose/Objective: Adjuvant radiotherapy is essential in reducing local recurrence and improving survival in breast cancer patients, but it carries a risk of ischemic cardiac toxicity, which increases with heart exposure. The isocentric lateral decubitus position, where the breast rests flat on a support, reduces heart exposure and delivers a more uniform dose. This position is particularly beneficial for patients with unique anatomies, such as those with pectus excavatum or larger breast sizes. While artificial intelligence (AI) algorithms for auto-contouring have shown promise, they have not been tailored for this specific position. This study aimed to develop and evaluate a neural network-based auto-contouring algorithm for patients treated in the isocentric lateral decubitus position. Material/Methods: In this single-center study, 1,189 breast cancer patients treated after breast-conserving surgery were included. Their simulation CT scans (1,209 scans) were used to train and validate a neural network-based auto-contouring algorithm (nnU-Net). Of these, 1,087 scans were used for training, and 122 scans were reserved for validation. The algorithm's performance was assessed using the Dice Similarity Coefficient (DSC) to compare the automatically delineated volumes with manual contours. A clinical evaluation of the algorithm was performed on 30 additional patients, with contours rated by two expert radiation oncologists. Results: The neural network-based algorithm achieved a segmentation time of approximately 4 minutes, compared to 20 minutes for manual segmentation. The DSC values for the validation cohort were 0.88 for the treated breast, 0.90 for the heart, 0.98 for the right lung, and 0.97 for the left lung. In the clinical evaluation, 90% of the automatically contoured breast volumes were rated as acceptable without corrections, while the remaining 10% required minor adjustments. All lung contours were accepted without corrections, and heart contours were rated as acceptable in 93.3% of cases, with minor corrections needed in 6.6% of cases.