A deep learning segmentation method to assess dose to organs at risk during breast radiotherapy

Abstract

Background and purpose: Contouring of organs at risk is important for studying health effects following breast radiotherapy. However, manual contouring is time-consuming and subject to variability. The purpose of this study was to develop a deep learning-based method to automatically segment multiple structures on breast radiotherapy planning computed tomography (CT) images. Materials and methods: We used data from 118 patients, including 90 diagnostic CT scans with expert structure delineations for training and 28 breast radiotherapy planning CT images for testing. The radiotherapy CT images also had expert delineations for evaluating performance. We targeted a total of eleven organs at risk including five heart substructures. Segmentation performance was evaluated using the metrics of Dice similarity coefficient (DSC), overlap fraction, volume similarity, Hausdorff distance, mean surface distance, and dose. Results: The average DSC achieved on the radiotherapy planning images was 0.94 ± 0.02 for the whole heart, 0.96 ± 0.02 and 0.97 ± 0.01 for the left and right lung, 0.61 ± 0.10 for the esophagus, 0.81 ± 0.04 and 0.86 ± 0.04 for left and right atrium, 0.91 ± 0.02 and 0.84 ± 0.04 for left and right ventricle, and 0.21 ± 0.11 for the left anterior descending artery (LAD), respectively. Except for the LAD, the median difference in mean dose to these structures was small with absolute (relative) differences < 0.1 Gy (6 %). Conclusions: Except for the LAD, our method demonstrated excellent performance and can be generalized to segment additional structures of interest.

Keywords

• Deep learning
• Image segmentation
• Artificial intelligence
• Computed tomography
• Breast radiotherapy
• Late effects