文献速递头颈部肿瘤放疗放疗物理与技术

基于MR的深度学习自动勾画在头颈放疗计划中的评估

An evaluation of MR based deep learning auto-contouring for planning head and neck radiotherapy.
PubMed 文献 · Radiother Oncol · 2021-02-24

本研究评估了基于MR的深度学习自动勾画模型(modelMRI)在头颈部放疗危及器官勾画中的跨采集应用,并与CT模型(modelCT)比较。modelMRI在诊断和MR放疗计划扫描上对双侧腮腺和颌下腺的DSC和DTA较手动勾画有改善,且与modelCT相比在多个腺体的DTA上差异有统计学意义。结论认为MR自动勾画模型有前景,但性能受MR采集方式影响,需进一步改进以用于MR-Linac图像。

要点

  • MR自动勾画模型在诊断和RTP MR上对腮腺和颌下腺的DSC和DTA较手动勾画有改善。
  • 与CT模型相比,MR模型在左腮腺、右腮腺、左颌下腺和右颌下腺的DTA差异有统计学意义。
  • MR模型性能受MR采集方法影响,用于MRL图像需进一步改进。

核心结论

  • 深度学习MR自动勾画模型在OAR勾画中显示出前景,性能较基于CT的模型有统计学改善。
  • 模型性能受MR采集方法影响,需进一步工作以改善其在MRL图像中的应用。

研究设计与样本

  • 评估两种自动勾画模型(modelCT和modelMRI),使用DLCExpert进行OAR勾画。
  • 模型训练用于生成双侧腮腺和颌下腺的自动轮廓。
  • modelMRI在诊断图像上训练,并在10例诊断、10例MR放疗计划(RTP)、8例MR-Linac(MRL)扫描上测试;modelCT在10例CT计划扫描上测试。
  • 计算拟合优度评分、Dice相似系数(DSC)和距离一致性(DTA)进行比较。

主要发现

  • modelMRI轮廓在诊断和RTP MR上对双侧腮腺和颌下腺的mean DSC和DTA较手动轮廓有改善, compared with the MRL sequence。
  • modelMRI与modelCT相比,左侧腮腺mean DTA 2.3 vs 2.8 mm,右侧腮腺mean DTA 1.9 vs 2.7 mm。
  • 左侧颌下腺mean DTA 2.2 vs 2.4 mm,右侧颌下腺mean DTA 1.6 vs 3.2 mm,差异有统计学意义。

关键数值与推荐

  • 左侧腮腺mean DTA:modelMRI 2.3 mm vs modelCT 2.8 mm。
  • 右侧腮腺mean DTA:modelMRI 1.9 mm vs modelCT 2.7 mm。
  • 左侧颌下腺mean DTA:modelMRI 2.2 mm vs modelCT 2.4 mm。
  • 右侧颌下腺mean DTA:modelMRI 1.6 mm vs modelCT 3.2 mm。

临床怎么用

  • MR深度学习自动勾画可用于头颈放疗OAR勾画,可能减少临床工作量并提高一致性。
  • 在临床使用中需注意MR采集方法对模型性能的影响,尤其是MRL图像。

局限性

  • modelMRI仅在诊断图像上训练,测试样本量较小(10例诊断、10例RTP、8例MRL、10例CT)。
  • 性能受MR采集方法影响,需进一步改进以用于MRL图像。

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

INTRODUCTION: Auto contouring models help consistently define volumes and reduce clinical workload. This study aimed to evaluate the cross acquisition of a Magnetic Resonance (MR) deep learning auto contouring model for organ at risk (OAR) delineation in head and neck radiotherapy. METHODS: Two auto contouring models were evaluated using deep learning contouring expert (DLCExpert) for OAR delineation: a CT model (modelCT) and an MR model (modelMRI). Models were trained to generate auto contours for the bilateral parotid glands and submandibular glands. Auto-contours for modelMRI were trained on diagnostic images and tested on 10 diagnostic, 10 MR radiotherapy planning (RTP), eight MR-Linac (MRL) scans and, by modelCT, on 10 CT planning scans. Goodness of fit scores, dice similarity coefficient (DSC) and distance to agreement (DTA) were calculated for comparison. RESULTS: ModelMRI contours improved the mean DSC and DTA compared with manual contours for the bilateral parotid glands and submandibular glands on the diagnostic and RTP MRs compared with the MRL sequence. There were statistically significant differences seen for modelMRI compared to modelCT for the left parotid (mean DTA 2.3 v 2.8 mm), right parotid (mean DTA 1.9 v 2.7 mm), left submandibular gland (mean DTA 2.2 v 2.4 mm) and right submandibular gland (mean DTA 1.6 v 3.2 mm). CONCLUSION: A deep learning MR auto-contouring model shows promise for OAR auto-contouring with statistically improved performance vs a CT based model. Performance is affected by the method of MR acquisition and further work is needed to improve its use with MRL images.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Hague C, McPartlin A, Lee LW, et al. An evaluation of MR based deep learning auto-contouring for planning head and neck radiotherapy. Radiother Oncol. 2021. PMID: 33636229. doi:10.1016/j.radonc.2021.02.018

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。