Evaluation of Automated Breast Cancer Contour Propagation From Planning CT to Cone Beam CT Based on Deep Learning

Abstract

<h3>Purpose/Objective(s)</h3> To evaluate a regional deformable model based on deep unsupervised learning framework for automated contour propagation in breast Cone Beam Computed Tomography (CBCT) guided radiation therapy. <h3>Materials/Methods</h3> We introduce an unsupervised learning framework to map the breast tumor bed, clinical target volume (CTV), heart, left lung, right lung, and spinal cord from planning CT (pCT) to daily CBCT. To improve the performance of the traditional deformable image registration method, the proposed unsupervised learning method uses a regional deformable model based on the narrow band mapping, which can mitigate the effect of the image artifacts. We retrospectively selected 380 anonymized CBCT volumes from 107 patients with breast cancer. The CBCTs are divided into three sets. 311 / 20 / 49 CBCTs were used for training, validation, and testing. For the testing set, one physician-generated contours were generated as the references. Through the Dice similarity coefficients (DSC), the Hausdorff distances, and the distances of the center-of-mass, the results were compared between the proposed model and physician-generated contours. <h3>Results</h3> The mean DSC between the proposed segmentations and the physician-generated segmentations for breast tumor bed, clinical target volume (CTV), heart, left lung, right lung, and spinal cord were 0.79 ± 0.09, 0.89 ± 0.08, 0.90 ± 0.08, 0.93 ± 0.03, 0.94 ± 0.04, and 0.76 ± 0.13, respectively. The average distances of the center-of-mass for the whole testing images were less than 4 mm. The proposed regional deformable model's performance was better than the traditional global deformable model, especially in the CBCT image with severe image artifacts. <h3>Conclusion</h3> This novel deep learning-based regional deformable model technique can automatically propagate contours for breast cancer patient radiotherapy. The proposed approach shows that the deep learning technique can accomplish highly precise contour propagation for breast CBCT-guided adaptive radiotherapy.