CBCT-guided Adaptive Radiotherapy using Self-Supervised Sequential Domain

Adaptive radiotherapy (ART) is an advanced technology in modern cancer treatment that incorporates progressive changes in patient anatomy into active plan/dose adaption during the fractionated treatment. However, the clinical application relies on the accurate segmentation of cancer tumors on low-quality on-board images, which has posed challenges for both manually delineation and deep learning-based models. In this paper, we propose a novel sequence transduction deep neural networks with attention mechanism to learn the shrinkage of the cancer tumor based on patients' weekly cone-beam computed tomography (CBCT). We design a self-supervised domain adaption (SDA) method to learn and adapt the rich textural and spatial features from pre-treatment high-quality computed tomography (CT) to CBCT modality in order to address the poor image quality and lack of labels. We also provide uncertainty estimation for sequential segmentation, which aids not only in the risk management of treatment planning but also in the calibration and reliability of the model. Our experimental results based on a clinical non-small cell lung cancer (NSCLC) dataset with six-teen patients and ninety-six longitudinal CBCTs show that our model properly learns weekly deformation of the tumor over time with an average dice score of 0.92 on the immediate next step, and is able to predict multiple steps (up to 5 weeks) for future patient treatments with an average dice score reduction of 0.05. By incorporating the tumor shrinkage predictions into a weekly re-planning strategy, our proposed method demonstrates a significant reduction in the risk of radiation-induced pneumonitis up to 35% while maintaining the high tumor control probability.

The code that supports the findings of the study is openly available in the repository, patient data is available on request due to institutional restrictions.

自适应放射治疗（ART）是现代癌症治疗领域的一项尖端技术，该技术将患者解剖结构的渐进性变化整合到分次治疗过程中的主动计划/剂量调整中。然而，其临床应用依赖于对低质量车载图像上癌症肿瘤的精确分割，这对手动描绘和基于深度学习的模型均构成了挑战。在本文中，我们提出了一种新颖的序列转导深度神经网络，并引入了注意力机制，以基于患者每周锥束计算机断层扫描（CBCT）学习癌症肿瘤的收缩情况。我们设计了一种自监督领域自适应（SDA）方法，以学习并适应从术前高质量计算机断层扫描（CT）到CBCT模态的丰富纹理和空间特征，以解决图像质量不佳和标签缺乏的问题。此外，我们还提供了序列分割的不确定性估计，这不仅有助于治疗计划的风险管理，也有助于模型的校准和可靠性。基于包含十六位患者和九十六次纵向CBCT的临床非小细胞肺癌（NSCLC）数据集的实验结果表明，我们的模型能够正确地学习肿瘤随时间变化的每周变形，在紧接着的下一次步长上平均dice分数为0.92，并且能够预测多达5周的未来患者治疗，平均dice分数降低0.05。通过将肿瘤收缩预测纳入每周重新规划策略，我们提出的方法在保持高肿瘤控制概率的同时，显著降低了辐射诱导性肺炎的风险，高达35%。研究支持代码已公开在代码库中提供，受机构限制，患者数据可应要求提供。