Abstract：
OBJECTIVE: To investigate the performance of 4 atlas-based (multi-ABAS) and 2 deep learning (DL) solutions for head-and-neck (HN) elective nodes (CTVn) automatic segmentation (AS) on CT images.
METHODS: Bilateral CTVn levels of 69 HN cancer patients were delineated on contrast-enhanced planning CT. Ten and 49 patients were used for atlas library and for training a mono-centric DL model, respectively. The remaining 20 patients were used for testing. Additionally, three commercial multi-ABAS methods and one commercial multi-centric DL solution were investigated. Quantitative evaluation was assessed using volumetric Dice Similarity Coefficient (DSC) and 95-percentile Hausdorff distance (HD95%). Blind evaluation was performed for 3 solutions by 4 physicians. One recorded the time needed for manual corrections. A dosimetric study was finally conducted using automated planning.
RESULTS: Overall DL solutions had better DSC and HD95% results than multi-ABAS methods. No statistically significant difference was found between the 2 DL solutions. However, the contours provided by multi-centric DL solution were preferred by all physicians and were also faster to correct (1.1 min vs 4.17 min, on average). Manual corrections for multi-ABAS contours took on average 6.52 min Overall, decreased contour accuracy was observed from CTVn2 to CTVn3 and to CTVn4. Using the AS contours in treatment planning resulted in underdosage of the elective target volume.
CONCLUSIONS: Among all methods, the multi-centric DL method showed the highest delineation accuracy and was better rated by experts. Manual corrections remain necessary to avoid elective target underdosage. Finally, AS contours help reducing the workload of manual delineation task.
METHODS: Bilateral CTVn levels of 69 HN cancer patients were delineated on contrast-enhanced planning CT. Ten and 49 patients were used for atlas library and for training a mono-centric DL model, respectively. The remaining 20 patients were used for testing. Additionally, three commercial multi-ABAS methods and one commercial multi-centric DL solution were investigated. Quantitative evaluation was assessed using volumetric Dice Similarity Coefficient (DSC) and 95-percentile Hausdorff distance (HD95%). Blind evaluation was performed for 3 solutions by 4 physicians. One recorded the time needed for manual corrections. A dosimetric study was finally conducted using automated planning.
RESULTS: Overall DL solutions had better DSC and HD95% results than multi-ABAS methods. No statistically significant difference was found between the 2 DL solutions. However, the contours provided by multi-centric DL solution were preferred by all physicians and were also faster to correct (1.1 min vs 4.17 min, on average). Manual corrections for multi-ABAS contours took on average 6.52 min Overall, decreased contour accuracy was observed from CTVn2 to CTVn3 and to CTVn4. Using the AS contours in treatment planning resulted in underdosage of the elective target volume.
CONCLUSIONS: Among all methods, the multi-centric DL method showed the highest delineation accuracy and was better rated by experts. Manual corrections remain necessary to avoid elective target underdosage. Finally, AS contours help reducing the workload of manual delineation task.
摘要：
目的：研究4种基于图谱（多ABAS）和2种深度学习（DL）解决方案在CT图像上的头颈部（HN）选择性节点（CTVn）自动分割（AS）的性能。
方法：在对比增强计划CT上描绘了69例HN癌症患者的双侧CTVn水平。10例和49例患者用于图谱库和训练单中心DL模型，分别。其余20名患者用于测试。此外,研究了三种商业多ABAS方法和一种商业多中心DL解决方案。使用体积骰子相似性系数(DSC)和95百分位数Hausdorff距离(HD95%)评估定量评价。由4名医师对3种溶液进行盲评价。一个记录了手动校正所需的时间。最后使用自动计划进行了剂量学研究。
结果：总体DL解决方案比多ABAS方法具有更好的DSC和HD95％结果。在2种DL溶液之间没有发现统计学上的显著差异。然而,多中心DL解决方案提供的轮廓是所有医生的首选，并且纠正速度也更快(1.1minvs4.17min，平均而言）。多ABAS轮廓的手动校正平均为6.52分钟。从CTVn2到CTVn3和CTVn4观察到轮廓准确性降低。在治疗计划中使用AS轮廓会导致选择性目标体积的剂量不足。
结论：在所有方法中，多中心DL方法显示出最高的划分精度，并且得到了专家的更好评价。手动校正仍然是必要的，以避免选择性目标剂量不足。最后,AS轮廓有助于减少手动描绘任务的工作量。
方法：在对比增强计划CT上描绘了69例HN癌症患者的双侧CTVn水平。10例和49例患者用于图谱库和训练单中心DL模型，分别。其余20名患者用于测试。此外,研究了三种商业多ABAS方法和一种商业多中心DL解决方案。使用体积骰子相似性系数(DSC)和95百分位数Hausdorff距离(HD95%)评估定量评价。由4名医师对3种溶液进行盲评价。一个记录了手动校正所需的时间。最后使用自动计划进行了剂量学研究。
结果：总体DL解决方案比多ABAS方法具有更好的DSC和HD95％结果。在2种DL溶液之间没有发现统计学上的显著差异。然而,多中心DL解决方案提供的轮廓是所有医生的首选，并且纠正速度也更快(1.1minvs4.17min，平均而言）。多ABAS轮廓的手动校正平均为6.52分钟。从CTVn2到CTVn3和CTVn4观察到轮廓准确性降低。在治疗计划中使用AS轮廓会导致选择性目标体积的剂量不足。
结论：在所有方法中，多中心DL方法显示出最高的划分精度，并且得到了专家的更好评价。手动校正仍然是必要的，以避免选择性目标剂量不足。最后,AS轮廓有助于减少手动描绘任务的工作量。
