Objective. In image-guided radiotherapy (IGRT), off-by-one vertebral body misalignments are rare but potentially catastrophic. In this study, a novel detection method for such misalignments in IGRT was investigated using densely-connected convolutional networks (DenseNets) for applications towards real-time error prevention and retrospective error auditing. Approach. A total of 4213 images acquired from 527 radiotherapy patients aligned with planar kV or MV radiographs were used to develop and test error-detection software modules. Digitally reconstructed radiographs (DRRs) and setup images were retrieved and co-registered according to the clinically applied alignment contained in the DICOM REG files. A semi-automated algorithm was developed to simulate patient positioning errors on the anterior-posterior (AP) and lateral (LAT) images shifted by one vertebral body. A DenseNet architecture was designed to classify either AP images individually or AP and LAT image pairs. Receiver-operator characteristic curves (ROC) and areas under the curves (AUC) were computed to evaluate the classifiers on test subsets. Subsequently, the algorithm was applied to the entire dataset in order to retrospectively determine the absolute off-by-one vertebral body error rate for planar radiograph guided RT at our institution from 2011–2021. Main results. The AUCs for the kV models were 0.98 for unpaired AP and 0.99 for paired AP-LAT. The AUC for the MV AP model was 0.92. For a specificity of 95%, the paired kV model achieved a sensitivity of 99%. Application of the model to the entire dataset yielded a per-fraction off-by-one vertebral body error rate of 0.044% [0.0022%, 0.21%] for paired kV IGRT including one previously unreported error. Significance. Our error detection algorithm was successful in classifying vertebral body positioning errors with sufficient accuracy for retrospective quality control and real-time error prevention. The reported positioning error rate for planar radiograph IGRT is unique in being determined independently of an error reporting system.

中文翻译：

---

正交 kV 和 MV 引导放射治疗中椎体错位的自动检测：在综合回顾性数据集中的应用

客观的。在图像引导放射治疗（IGRT）中，椎体错位的情况很少见，但可能是灾难性的。在本研究中，使用密集连接的卷积网络（DenseNets）研究了一种针对 IGRT 中此类未对准的新颖检测方法，用于实时错误预防和回顾性错误审计的应用。方法。从 527 名放射治疗患者采集的总共 4213 张图像与平面 kV 或 MV 射线照片对齐，用于开发和测试错误检测软件模块。根据 DICOM REG 文件中包含的临床应用对齐，检索并共同配准数字重建放射线照片 (DRR) 和设置图像。开发了一种半自动算法来模拟由一个椎体移动的前后（AP）和侧向（LAT）图像上的患者定位误差。 DenseNet 架构旨在对单独的 AP 图像或 AP 和 LAT 图像对进行分类。计算接受者-操作者特征曲线（ROC）和曲线下面积（AUC）以评估测试子集上的分类器。随后，将该算法应用于整个数据集，以便回顾性地确定 2011 年至 2021 年我们机构平面 X 线引导 RT 的绝对差一椎体误差率。主要结果。 kV 模型的 AUC 对于未配对的 AP 为 0.98，对于配对的 AP-LAT 为 0.99。 MV AP 模型的 AUC 为 0.92。对于 95% 的特异性，配对 kV 模型的灵敏度为 99%。将模型应用于整个数据集，对于配对 kV IGRT，每分数相差一个椎体误差率为 0.044% [0.0022%，0.21%]，包括一个先前未报告的误差。意义。我们的错误检测算法成功地对椎体定位错误进行了分类，具有足够的精度，可用于回顾性质量控制和实时错误预防。所报告的平面放射线照片 IGRT 的定位错误率是独特的，它是独立于错误报告系统确定的。