文献速递中枢神经肿瘤放疗放疗物理与技术姑息放疗与转移瘤

基于MRI的神经网络用于脑转移瘤分割:AURORA多中心研究的开发与外部验证

Development and external validation of an MRI-based neural network for brain metastasis segmentation in the AURORA multicenter study.
PubMed 文献 · Radiother Oncol · 2022-11-26

该研究纳入6个中心348例至少有一个脑转移瘤患者的MRI(T1加权序列±对比增强、T2加权序列和FLAIR序列),手工分割所有GTV和FLAIR高信号水肿区作为参考;用2个中心260例训练3D-U-Net分割GTV及周围FLAIR高信号区,并在4个中心88例独立国际多中心测试队列中外部验证。结果显示外部队列GTV分割总体Dice相似系数(DSC)均值0.92±0.08、单个转移瘤DSC均值0.89±0.11,脑转移瘤检测F1分数均值0.93±0.16,模型性能不依赖中心(p=0.3),转移瘤体积与DSC无相关性(Pearson相关系数0.07)。作者认为神经网络可靠的自动分割脑转移瘤是可能的,可能通过提供更客观的GTV定义来支持放疗计划。

要点

  • 外部队列GTV分割总体DSC均值0.92±0.08,单个转移瘤DSC均值0.89±0.11。
  • 脑转移瘤检测F1分数均值0.93±0.16,模型性能不依赖中心(p=0.3)。
  • 数据增强显著改善分割性能,转移瘤体积与DSC无相关性(Pearson相关系数0.07)。

核心结论

  • 作者认为神经网络可靠的自动分割脑转移瘤是可能的,可能通过提供更客观的GTV定义来支持放疗计划。

研究设计与样本

  • 研究分析6个中心348例至少有一个脑转移瘤患者的MRI(T1加权序列±对比增强、T2加权序列和FLAIR序列),手工分割所有GTV和FLAIR高信号水肿区作为参考分割。
  • 用2个中心260例训练3D-U-Net分割GTV及周围FLAIR高信号区,训练中应用不同程度的数据增强。
  • 使用4个中心88例独立国际多中心测试队列进行外部验证。

主要发现

  • 外部队列GTV分割总体DSC均值0.92±0.08,单个转移瘤DSC均值0.89±0.11。
  • 数据增强显著改善分割性能。
  • 脑转移瘤检测有效,F1分数均值0.93±0.16。
  • 模型性能不依赖中心(p=0.3)。
  • 转移瘤体积与DSC无相关性(Pearson相关系数0.07)。

关键数值与推荐

  • 外部队列GTV分割总体DSC均值0.92±0.08。
  • 外部队列单个转移瘤DSC均值0.89±0.11。
  • 脑转移瘤检测F1分数均值0.93±0.16。
  • 模型性能与中心无关(p=0.3)。
  • 转移瘤体积与DSC的Pearson相关系数0.07。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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

BACKGROUND: Stereotactic radiotherapy is a standard treatment option for patients with brain metastases. The planning target volume is based on gross tumor volume (GTV) segmentation. The aim of this work is to develop and validate a neural network for automatic GTV segmentation to accelerate clinical daily routine practice and minimize interobserver variability. METHODS: We analyzed MRIs (T1-weighted sequence ± contrast-enhancement, T2-weighted sequence, and FLAIR sequence) from 348 patients with at least one brain metastasis from different cancer primaries treated in six centers. To generate reference segmentations, all GTVs and the FLAIR hyperintense edematous regions were segmented manually. A 3D-U-Net was trained on a cohort of 260 patients from two centers to segment the GTV and the surrounding FLAIR hyperintense region. During training varying degrees of data augmentation were applied. Model validation was performed using an independent international multicenter test cohort (n = 88) including four centers. RESULTS: Our proposed U-Net reached a mean overall Dice similarity coefficient (DSC) of 0.92 ± 0.08 and a mean individual metastasis-wise DSC of 0.89 ± 0.11 in the external test cohort for GTV segmentation. Data augmentation improved the segmentation performance significantly. Detection of brain metastases was effective with a mean F1-Score of 0.93 ± 0.16. The model performance was stable independent of the center (p = 0.3). There was no correlation between metastasis volume and DSC (Pearson correlation coefficient 0.07). CONCLUSION: Reliable automated segmentation of brain metastases with neural networks is possible and may support radiotherapy planning by providing more objective GTV definitions.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Buchner JA, Kofler F, Etzel L, et al. Development and external validation of an MRI-based neural network for brain metastasis segmentation in the AURORA multicenter study. Radiother Oncol. 2022. PMID: 36442609. doi:10.1016/j.radonc.2022.11.014

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。