Yan Shunyu, Maniscalco Austen, Wang Biling, Nguyen Dan, Jiang Steve, Shen Chenyang
The Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX 75390, United States of America.
Mach Learn Sci Technol. 2024 Dec 1;5(4):045013. doi: 10.1088/2632-2153/ad829e. Epub 2024 Oct 11.
In online adaptive radiotherapy (ART), quick computation-based secondary dose verification is crucial for ensuring the quality of ART plans while the patient is positioned on the treatment couch. However, traditional dose verification algorithms are generally time-consuming, reducing the efficiency of ART workflow. This study aims to develop an ultra-fast deep-learning (DL) based secondary dose verification algorithm to accurately estimate dose distributions using computed tomography (CT) and fluence maps (FMs). We integrated FMs into the CT image domain by explicitly resolving the geometry of treatment delivery. For each gantry angle, an FM was constructed based on the optimized multi-leaf collimator apertures and corresponding monitoring units. To effectively encode treatment beam configuration, the constructed FMs were back-projected to cm away from the isocenter with respect to the exact geometry of the treatment machines. Then, a 3D U-Net was utilized to take the integrated CT and FM volume as input to estimate dose. Training and validation were performed on prostate cancer cases, with an additional testing cases for independent evaluation of model performance. The proposed model can estimate dose in ∼ ms for each patient. The average passing rate ( , threshold) for the estimated dose was 99.9% ± 0.15% on testing patients. The mean dose differences for the planning target volume and organs at risk were and , respectively. We have developed a geometry-resolved DL framework for accurate dose estimation and demonstrated its potential in real-time online ART doses verification.
在在线自适应放疗（ART）中，基于快速计算的二次剂量验证对于在患者躺在治疗床上时确保ART计划的质量至关重要。然而，传统的剂量验证算法通常耗时较长，降低了ART工作流程的效率。本研究旨在开发一种基于超快速深度学习（DL）的二次剂量验证算法，以使用计算机断层扫描（CT）和注量图（FM）准确估计剂量分布。我们通过明确解析治疗投送的几何结构，将FM整合到CT图像域中。对于每个机架角度，基于优化的多叶准直器孔径和相应的监测单位构建一个FM。为了有效地编码治疗束配置，根据治疗机器的确切几何结构，将构建的FM反投影到距等中心 cm处。然后，利用一个3D U-Net将整合后的CT和FM体积作为输入来估计剂量。对 例前列腺癌病例进行了训练和验证，另外还有 例测试病例用于独立评估模型性能。所提出的模型可以在约 ms内为每个患者估计剂量。在测试患者中，估计剂量的平均 通过率（ ， 阈值）为99.9%±0.15%。计划靶体积和危及器官的平均剂量差异分别为 和 。我们已经开发了一个几何解析的DL框架用于准确的剂量估计，并展示了其在实时在线ART剂量验证中的潜力。
