Division of Radiation Oncology, National Cancer Centre Singapore, Singapore.
Department of Oncology, University of Cambridge, United Kingdom.
Phys Med Biol. 2023 Jul 28;68(15). doi: 10.1088/1361-6560/ace6f0.
. Automatic deformable image registration (DIR) is a critical step in adaptive radiotherapy. Manually delineated organs-at-risk (OARs) contours on planning CT (pCT) scans are deformably registered onto daily cone-beam CT (CBCT) scans for delivered dose accumulation. However, evaluation of registered contours requires human assessment, which is time-consuming and subjects to high inter-observer variability. This work proposes a deep learning model that allows accurate prediction of Dice similarity coefficients (DSC) of registered contours in prostate radiotherapy.. Our dataset comprises 20 prostate cancer patients with 37-39 daily CBCT scans each. The pCT scans and planning contours were deformably registered to each corresponding CBCT scan to generate virtual CT (vCT) scans and registered contours. The DSC score, which is a common contour-based validation metric for registration quality, between the registered and manual contours were computed. A Siamese neural network was trained on the vCT-CBCT image pairs to predict DSC. To assess the performance of the model, the root mean squared error (RMSE) between the actual and predicted DSC were computed.. The model showed promising results for predicting DSC, giving RMSE of 0.070, 0.079 and 0.118 for rectum, prostate, and bladder respectively on the holdout test set. Clinically, a low RMSE implies that the predicted DSC can be reliably used to determine if further DIR assessment from physicians is required. Considering the event where a registered contour is classified as poor if its DSC is below 0.6 and good otherwise, the model achieves an accuracy of 92% for the rectum. A sensitivity of 0.97 suggests that the model can correctly identify 97% of poorly registered contours, allowing manual assessment of DIR to be triggered.. We propose a neural network capable of accurately predicting DSC of deformably registered OAR contours, which can be used to evaluate eligibility for plan adaptation.
自动形变图像配准（DIR）是自适应放疗的关键步骤。手动勾画的危及器官（OAR）轮廓在计划 CT（pCT）扫描上进行形变配准，以便在每日锥形束 CT（CBCT）扫描上进行累积剂量。然而，配准轮廓的评估需要人工评估，这既费时又容易受到观察者间变异性的影响。本研究提出了一种深度学习模型，能够准确预测前列腺放疗中配准轮廓的 Dice 相似系数（DSC）。
我们的数据集包含 20 名前列腺癌患者，每位患者每天进行 37-39 次 CBCT 扫描。将 pCT 扫描和计划轮廓与每个对应的 CBCT 扫描进行形变配准，以生成虚拟 CT（vCT）扫描和配准轮廓。计算配准轮廓与手动轮廓之间的 DSC 评分，这是注册质量的常用基于轮廓的验证指标。在 vCT-CBCT 图像对上训练了一个孪生神经网络来预测 DSC。为了评估模型的性能，计算了实际和预测 DSC 之间的均方根误差（RMSE）。
该模型在预测 DSC 方面表现出了良好的性能，在测试集上，直肠、前列腺和膀胱的 RMSE 分别为 0.070、0.079 和 0.118。临床上，低 RMSE 意味着预测的 DSC 可以可靠地用于确定是否需要医生进一步进行 DIR 评估。考虑到如果注册轮廓的 DSC 低于 0.6 则被分类为差，否则为好的情况，该模型对直肠的准确率为 92%。敏感性为 0.97，这意味着模型能够正确识别 97%的配准较差的轮廓，从而可以触发对 DIR 的手动评估。
我们提出了一种能够准确预测形变 OAR 轮廓配准的 DSC 的神经网络，该模型可用于评估计划适应性的资格。
