Lei Weijie, Han Lixiang, Cao Zhenmei, Duan Tingting, Wang Bin, Li Caihong, Pei Xi
Department of Radiation Oncology, Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, China.
Department of Radiation Oncology, Xuzhou First People's Hospital, Xuzhou, China.
Radiat Oncol. 2025 Aug 28;20(1):135. doi: 10.1186/s13014-025-02715-7.
To evaluate the precision of automated segmentation facilitated by deep learning (DL) and dose calculation in adaptive radiotherapy (ART) for nasopharyngeal cancer (NPC), leveraging synthetic CT (sCT) images derived from cone-beam CT (CBCT) scans on a conventional C-arm linac.
Sixteen NPC patients undergoing a two-phase offline ART were analyzed retrospectively. The initial (pCT) and adaptive (pCT) CT scans served as gold standard alongside weekly acquired CBCT scans. Patient data, including manually delineated contours and dose information, were imported into ArcherQA. Using a cycle-consistent generative adversarial network (cycle-GAN) trained on an independent dataset, sCT images (sCT, sCT, sCT) were generated from weekly CBCT scans (CBCT, CBCT, CBCT) paired with corresponding planning CTs (pCT, pCT, pCT). Auto-segmentation was performed on sCTs, followed by GPU-accelerated Monte Carlo dose recalculation. Auto-segmentation accuracy was assessed via Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (HD). Dose calculation fidelity on sCTs was evaluated using dose-volume parameters. Dosimetric consistency between recalculated sCT and pCT plans was analyzed via Spearman's correlation, while volumetric changes were concurrently evaluated to quantify anatomical variations.
Most anatomical structures demonstrated high pCT-sCT agreement, with mean values of DSC > 0.85 and HD < 5.10 mm. Notable exceptions included the primary Gross Tumor Volume (GTVp) in the pCT-sCT comparison (DSC: 0.75, HD: 6.03 mm), involved lymph node (GTVn) showing lower agreement (DSC: 0.43, HD: 16.42 mm), and submandibular glands with moderate agreement (DSC: 0.64-0.73, HD: 4.45-5.66 mm). Dosimetric analysis revealed the largest mean differences in GTVn D: -1.44 Gy (95% CI: [-3.01, 0.13] Gy) and right parotid mean dose: -1.94 Gy (95% CI: [-3.33, -0.55] Gy, p < 0.05). Anatomical variations, quantified via sCTs measurements, correlated significantly with offline adaptive plan adjustments in ART. This correlation was strong for parotid glands (ρ > 0.72, p < 0.001), a result that aligned with sCT-derived dose discrepancy analysis (ρ > 0.57, p < 0.05).
The proposed method exhibited minor variations in volumetric and dosimetric parameters compared to prior treatment data, suggesting potential efficiency improvements for ART in NPC through reduced human dependency.
为评估深度学习（DL）辅助的自动分割及鼻咽癌（NPC）自适应放疗（ART）中的剂量计算精度，利用传统C型臂直线加速器上锥束CT（CBCT）扫描生成的合成CT（sCT）图像。
回顾性分析16例接受两阶段离线ART的NPC患者。初始（pCT）和自适应（pCT）CT扫描作为金标准，同时每周进行CBCT扫描。将患者数据，包括手动勾勒的轮廓和剂量信息，导入ArcherQA。使用在独立数据集上训练的循环一致生成对抗网络（cycle-GAN），从每周的CBCT扫描（CBCT、CBCT、CBCT）与相应的计划CT（pCT、pCT、pCT）配对生成sCT图像（sCT、sCT、sCT）。对sCT进行自动分割，随后进行GPU加速的蒙特卡洛剂量重新计算。通过骰子相似系数（DSC）和第95百分位数豪斯多夫距离（HD）评估自动分割准确性。使用剂量体积参数评估sCT上的剂量计算保真度。通过Spearman相关性分析重新计算的sCT和pCT计划之间的剂量学一致性，同时评估体积变化以量化解剖学变异。
大多数解剖结构在pCT与sCT之间显示出高度一致性，DSC平均值>0.85且HD<5.10mm。显著例外包括pCT与sCT比较中的原发大体肿瘤体积（GTVp）（DSC：0.75，HD：6.03mm）、受累淋巴结（GTVn）一致性较低（DSC：0.43，HD：16.42mm）以及颌下腺一致性中等（DSC：0.64 - 0.73，HD：4.45 - 5.66mm）。剂量学分析显示GTVn D的最大平均差异为 -1.44Gy（95%CI：[-3.01, 0.13]Gy）和右侧腮腺平均剂量为 -1.94Gy（95%CI：[-3.33, -0.55]Gy，p<0.05）。通过sCT测量量化的解剖学变异与ART中的离线自适应计划调整显著相关。对于腮腺，这种相关性很强（ρ>0.72，p<0.001），这一结果与sCT衍生的剂量差异分析一致（ρ>0.57，p<0.05）。
与先前的治疗数据相比，所提出的方法在体积和剂量学参数上表现出较小的差异，表明通过减少对人工的依赖，NPC的ART可能提高效率。
