Haq Rabia, Hotca Alexandra, Apte Aditya, Rimner Andreas, Deasy Joseph O, Thor Maria
Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York NY 10017, USA.
Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York NY 10017, USA.
Phys Imaging Radiat Oncol. 2020 Jun 10;14:61-66. doi: 10.1016/j.phro.2020.05.009. eCollection 2020 Apr.
Radiation dose to the cardio-pulmonary system is critical for radiotherapy-induced mortality in non-small cell lung cancer. Our goal was to automatically segment substructures of the cardio-pulmonary system for use in outcomes analyses for thoracic cancers. We built and validated a multi-label Deep Learning Segmentation (DLS) model for accurate auto-segmentation of twelve cardio-pulmonary substructures.
The DLS model utilized a convolutional neural network for segmenting substructures from 217 thoracic radiotherapy Computed Tomography (CT) scans. The model was built in the presence of variable image characteristics such as the absence/presence of contrast. We quantitatively evaluated the final model against expert contours for a hold-out dataset of 24 CT scans using Dice Similarity Coefficient (DSC), 95th Percentile of Hausdorff Distance and Dose-volume Histograms (DVH). DLS contours of an additional 25 scans were qualitatively evaluated by a radiation oncologist to determine their clinical acceptability.
The DLS model reduced segmentation time per patient from about one hour to 10 s. Quantitatively, the highest accuracy was observed for the Heart (median DSC = (0.96 (0.95-0.97)). The median DSC for the remaining structures was between 0.81 and 0.93. No statistically significant difference was found between DVH metrics of the auto-generated and manual contours (p-value 0.69). The expert judged that, on average, 85% of contours were qualitatively equivalent to state-of-the-art manual contouring.
The cardio-pulmonary DLS model performed well both quantitatively and qualitatively for all structures. This model has been incorporated into an open-source tool for the community to use for treatment planning and clinical outcomes analysis.
心肺系统所受辐射剂量对于非小细胞肺癌放疗所致死亡率至关重要。我们的目标是自动分割心肺系统的子结构，以用于胸段癌症的预后分析。我们构建并验证了一个多标签深度学习分割（DLS）模型，用于准确自动分割12个心肺子结构。
DLS模型利用卷积神经网络从217例胸部放疗计算机断层扫描（CT）图像中分割子结构。该模型是在存在诸如有无对比剂等可变图像特征的情况下构建的。我们使用骰子相似系数（DSC）、豪斯多夫距离第95百分位数和剂量体积直方图（DVH），针对24例CT扫描的保留数据集，将最终模型与专家轮廓进行定量评估。另外25例扫描的DLS轮廓由放射肿瘤学家进行定性评估，以确定其临床可接受性。
DLS模型将每位患者的分割时间从约1小时缩短至10秒。在定量方面，心脏的分割精度最高（中位数DSC = 0.96（0.95 - 0.97））。其余结构的中位数DSC在0.81至0.93之间。自动生成轮廓和手动轮廓的DVH指标之间未发现统计学显著差异（p值>0.69）。专家判断，平均而言，85%的轮廓在质量上等同于当前最先进的手动轮廓绘制。
心肺DLS模型在所有结构的定量和定性方面均表现良好。该模型已被纳入一个开源工具，供社区用于治疗计划和临床结果分析。
