文献速递头颈部肿瘤放疗泌尿生殖与妇科肿瘤放疗放疗物理与技术

深度学习合成CT用于头颈与盆腔肿瘤MRI-only VMAT的临床实施

Clinical implementation of deep learning-based synthetic CT for MRI-only volumetric modulated arc therapy in head and neck and pelvic cancer patients.
PubMed 文献 · Radiat Oncol · 2025-11-12

本研究回顾性纳入33例头颈及盆腔肿瘤患者,采用深度学习商用软件生成合成CT(sCT),并与计划CT对比图像质量、剂量学精度、计划QA及摆位验证。结果显示sCT图像精度高,剂量差异在2%以内,gamma通过率头颈≥92%、盆腔≥96%,QA与摆位差异小,支持MRI-only工作流用于VMAT的可行性。

要点

  • 深度学习sCT在头颈和盆腔患者中图像精度高,剂量计算差异在2%以内。
  • sCT与CT计划的QA gamma通过率差异头颈≤0.05%、盆腔≤0.12%。
  • CT-CBCT与sCT-CBCT摆位差异各方向≤0.17 mm和≤0.13°。

核心结论

  • 深度学习软件生成的sCT图像在头颈和盆腔肿瘤患者中准确,支持可靠的剂量计算、计划QA和摆位验证,使MRI-only VMAT工作流具备实施潜力。

研究设计与样本

  • 回顾性分析纳入33例患者(头颈10例、前列腺9例、直肠9例、宫颈5例),均行CT和MRI定位,使用基于深度学习的MRI Planner™软件生成sCT。
  • 临床计划先在CT上优化,再以相同参数在sCT上重新计算,比较图像质量、DVH差异、全局gamma分析及EPID计划QA。
  • 摆位验证通过比较CT-CBCT与sCT-CBCT的差异进行评估。

主要发现

  • sCT图像全身DSC头颈0.99(SD=0.00)、盆腔1.00(SD=0.00),ME头颈-8.94 HU(SD=9.50)、盆腔-8.74 HU(SD=6.26),MAE头颈67.30 HU(SD=6.94)、盆腔33.64 HU(SD=3.91)。
  • 骨性结构DSC较低,头颈0.87(SD=0.03)、盆腔0.88(SD=0.02)。
  • 剂量差异在2%以内,所有标准下平均gamma通过率头颈≥92%、盆腔≥96%。
  • CT与sCT的计划QA gamma通过率差异头颈≤0.05%、盆腔≤0.12%。
  • CT-CBCT与sCT-CBCT平均摆位差异头颈各方向≤0.13 mm和≤0.06°,盆腔≤0.17 mm和≤0.13°。

关键数值与推荐

  • 图像质量评估采用DSC、ME和MAE。
  • 剂量学比较采用DVH差异和全局gamma分析(3%/2 mm至1%/1 mm)。
  • 计划QA比较采用全局gamma分析(3%/2 mm至2%/2 mm)。

临床怎么用

  • 在头颈和盆腔肿瘤VMAT中,可基于深度学习sCT进行剂量计算、计划QA和摆位验证,推动MRI-only工作流临床落地。

局限性

  • 本文为回顾性分析,样本量33例,结论需更大样本验证。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

RATIONALE AND OBJECTIVE: This study investigates the implementation of an MRI-only workflow in radiotherapy, focusing on synthetic CT (sCT) images generated through a deep learning-based commercial software to facilitate dose calculation and treatment delivery for volumetric modulated arc therapy (VMAT) in head and neck (H&N) and pelvic cancer patients. METHODS: This retrospective analysis included 33 patients (10 H&N, 9 prostate, 9 rectum, and 5 cervical cancer). All patients underwent CT and MRI for radiotherapy planning. sCT images were generated using deep learning-based MRI Planner™ software. Clinical treatment plans were initially optimized on CT and then recalculated on sCT with identical parameters. Image quality was evaluated using the dice similarity coefficient (DSC), mean error (ME), and mean absolute error (MAE). Dosimetric accuracy was assessed by comparing dose-volume histogram (DVH) differences and performing global gamma analysis (3%/2 mm to 1%/1 mm) between CT- and sCT-based plans. Treatment plan quality assurance (QA) conducted with an electronic portal imaging device (EPID) was compared between sCT and CT using global gamma analysis (3%/2 mm to 2%/2 mm). Patient set-up verification was evaluated by comparing CT-cone beam CT (CBCT) and sCT-CBCT. RESULTS: sCT images demonstrated high accuracy, with average body DSCs of 0.99 (SD = 0.00), ME of -8.94 HU (SD = 9.50), and MAE of 67.30 HU (SD = 6.94) for H&N, and DSCs of 1.00 (SD = 0.00), ME of -8.74 HU (SD = 6.26), and MAE of 33.64 HU (SD = 3.91) for the pelvis. Lower DSCs were observed in bone, with 0.87 (SD = 0.03) in H&N and 0.88 (SD = 0.02) in pelvis. Dose differences were within 2%, with average gamma pass rates of all criteria [Formula: see text]92% for H&N and [Formula: see text]96% for pelvis, across all criteria. QA plan evaluation revealed the gamma pass rate between CT and sCT of ≤0.05% for H&N and ≤0.12% for pelvis. Mean positioning differences between CT-CBCT and sCT-CBCT were ≤0.13 mm and ≤0.06[Formula: see text] for the H&N and ≤0.17 mm and ≤0.13[Formula: see text] for the pelvis in all directions. CONCLUSION: Deep learning-based software successfully generated accurate sCT images for both H&N and pelvic cancer patients, supporting reliable dose calculation, treatment plan QA, and patient set-up verification. This enables the potential implementation of MRI-only workflows for VMAT in H&N and pelvic cancer treatment.

来源:Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Earwong P, Puttanawarut C, Suphaphong S, et al. Clinical implementation of deep learning-based synthetic CT for MRI-only volumetric modulated arc therapy in head and neck and pelvic cancer patients. Radiat Oncol. 2025. PMID: 41225562. doi:10.1186/s13014-025-02744-2

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。