Division of Medical Physics, Stellenbosch University, Tygerberg Academic Hospital, Cape Town, South Africa.
Department of Oncology, University Hospitals Plymouth NHS trust, Plymouth, UK.
J Appl Clin Med Phys. 2023 Aug;24(8):e13988. doi: 10.1002/acm2.13988. Epub 2023 Apr 12.
The high-dose rate (HDR) brachytherapy treatment planning workflow for cervical cancer is a labor-intensive, time-consuming, and expertise-driven process. These issues are amplified in low/middle-income countries with large deficits in experienced healthcare professionals. Automation has the ability to substantially reduce bottlenecks in the planning process but often require a high level of expertise to develop.
To implement the out of the box self-configuring nnU-Net package for the auto-segmentation of the organs at risk (OARs) and high-risk CTV (HR CTV) for Ring-Tandem (R-T) HDR cervical brachytherapy treatment planning.
The computed tomography (CT) scans of 100 previously treated patients were used to train and test three different nnU-Net configurations (2D, 3DFR, and 3DCasc). The performance of the models was evaluated by calculating the Sørensen-dice similarity coefficient, Hausdorff distance (HD), 95 percentile Hausdorff distance, mean surface distance (MSD), and precision score for 20 test patients. The dosimetric accuracy between the manual and predicted contours was assessed by looking at the various dose volume histogram (DVH) parameters and volume differences. Three different radiation oncologists (ROs) scored the predicted bladder, rectum, and HR CTV contours generated by the best performing model. The manual contouring, prediction, and editing times were recorded.
The mean DSC, HD, HD95, MSD and precision scores for our best performing model (3DFR) were 0.92/7.5 mm/3.0 mm/ 0.8 mm/0.91 for the bladder, 0.84/13.8 mm/5.3 mm/1.4 mm/0.84 for the rectum, and 0.81/8.5 mm/6.0 mm/2.2 mm/0.80 for the HR CTV. Mean dose differences (D ) and volume differences were 0.08 Gy/1.3 cm for the bladder, 0.02 Gy/0.7 cm for the rectum, and 0.33 Gy/1.5 cm for the HR CTV. On average, 65% of the generated contours were clinically acceptable, 33% requiring minor edits, 2% required major edits, and no contours were rejected. Average manual contouring time was 14.0 min, while the average prediction and editing times were 1.6 and 2.1 min, respectively.
Our best performing model (3DFR) provided fast accurate auto generated OARs and HR CTV contours with a large clinical acceptance rate.
宫颈癌的高剂量率（HDR）近距离治疗计划工作流程是一个劳动密集型、耗时且需要专业知识的过程。在经验丰富的医疗保健专业人员严重短缺的中低收入国家，这些问题更加突出。自动化有能力大大减少规划过程中的瓶颈，但通常需要高水平的专业知识来开发。
为了实现用于 Ring-Tandem（R-T）HDR 宫颈癌近距离治疗计划的自动分割危及器官（OAR）和高危CTV（HR CTV）的 nnU-Net 自配置包。
使用 100 名已接受治疗的患者的计算机断层扫描（CT）扫描来训练和测试三种不同的 nnU-Net 配置（2D、3DFR 和 3DCasc）。通过计算 20 名测试患者的索伦森迪塞相似系数、豪斯多夫距离（HD）、95 百分位豪斯多夫距离、平均表面距离（MSD）和精度评分，评估模型的性能。通过查看各种剂量体积直方图（DVH）参数和体积差异来评估手动和预测轮廓之间的剂量准确性。三位不同的放射肿瘤学家（RO）对最佳表现模型生成的预测膀胱、直肠和 HR CTV 轮廓进行评分。记录手动轮廓、预测和编辑时间。
对于我们表现最佳的模型（3DFR），其平均 DSC、HD、HD95、MSD 和精度评分为膀胱 0.92/7.5mm/3.0mm/0.8mm/0.91、直肠 0.84/13.8mm/5.3mm/1.4mm/0.84 和 HR CTV 0.81/8.5mm/6.0mm/2.2mm/0.80。膀胱的平均剂量差异（D）和体积差异分别为 0.08Gy/1.3cm，直肠为 0.02Gy/0.7cm，HR CTV 为 0.33Gy/1.5cm。平均而言，生成的轮廓中有 65%具有临床可接受性，33%需要进行小的编辑，2%需要进行大的编辑，没有轮廓被拒绝。手动轮廓绘制平均时间为 14.0 分钟，而平均预测和编辑时间分别为 1.6 分钟和 2.1 分钟。
我们表现最佳的模型（3DFR）提供了快速准确的自动生成的 OAR 和 HR CTV 轮廓，具有很高的临床接受率。
