文献速递中枢神经肿瘤放疗放疗物理与技术

深度学习全自动勾画胶质母细胞瘤术后切除腔用于放疗靶区定义

Fully automated brain resection cavity delineation for radiation target volume definition in glioblastoma patients using deep learning.
PubMed 文献 · Radiat Oncol · 2020-05-06

本研究纳入30例胶质母细胞瘤患者的术后多模态MRI,由三名放疗肿瘤学家手动勾画切除腔作为参考,开发并评估一种利用全部四种MRI序列的深度学习切除腔分割方法。自动分割与三位勾画者之间的Dice系数为0.83、0.81、0.81,显著低于勾画者之间的Dice系数,但测得的切除腔体积在不同勾画者与自动方法间无统计学显著差异。

要点

  • 深度学习法自动勾画切除腔的Dice系数为0.81–0.83,低于专家间0.84–0.86。
  • 自动方法与不同勾画者测得的切除腔体积无统计学显著差异。
  • 主要误差来源为信号不均匀及腔与脑组织强度模式相似。

核心结论

  • 该深度学习方法在概念验证研究中用于自动勾画切除腔结果有前景,但Dice系数仍低于人类专家。

研究设计与样本

  • 研究纳入30例胶质母细胞瘤患者的术后T1w增强与平扫、T2w及FLAIR MRI,由三名放疗肿瘤学家手动勾画切除腔作为参考分割。
  • 开发一种利用全部四种MRI序列和参考分割进行学习的深度学习切除腔分割方法,并以Dice系数和估计体积测量进行评估。

主要发现

  • 三名放疗肿瘤学家手动勾画的中位Dice系数分别为0.85(IQR 0.08)、0.84(IQR 0.07)、0.86(IQR 0.07)。
  • 自动分割与三位不同勾画者比较的Dice系数分别为0.83(IQR 0.14)、0.81(IQR 0.12)、0.81(IQR 0.13),显著低于勾画者之间的Dice系数(卡方=11.63,p=0.04)。
  • 不同勾画者与自动方法测得的切除腔体积无统计学显著差异(Kruskal-Wallis检验:卡方=1.46,p=0.69)。
  • 主要误差来源为信号不均匀以及切除腔与脑组织之间的相似强度模式。

临床怎么用

  • 该深度学习自动勾画方法可作为胶质母细胞瘤术后切除腔靶区定义的辅助工具,但当前Dice系数仍低于人类专家,需谨慎使用。

局限性

  • 本研究为概念验证研究,样本量有限(30例胶质母细胞瘤患者)。
  • 自动分割的Dice系数仍低于人类专家间的一致性。

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: Automated brain tumor segmentation methods are computational algorithms that yield tumor delineation from, in this case, multimodal magnetic resonance imaging (MRI). We present an automated segmentation method and its results for resection cavity (RC) in glioblastoma multiforme (GBM) patients using deep learning (DL) technologies. METHODS: Post-operative, T1w with and without contrast, T2w and fluid attenuated inversion recovery MRI studies of 30 GBM patients were included. Three radiation oncologists manually delineated the RC to obtain a reference segmentation. We developed a DL cavity segmentation method, which utilizes all four MRI sequences and the reference segmentation to learn to perform RC delineations. We evaluated the segmentation method in terms of Dice coefficient (DC) and estimated volume measurements. RESULTS: Median DC of the three radiation oncologist were 0.85 (interquartile range [IQR]: 0.08), 0.84 (IQR: 0.07), and 0.86 (IQR: 0.07). The results of the automatic segmentation compared to the three different raters were 0.83 (IQR: 0.14), 0.81 (IQR: 0.12), and 0.81 (IQR: 0.13) which was significantly lower compared to the DC among raters (chi-square = 11.63, p = 0.04). We did not detect a statistically significant difference of the measured RC volumes for the different raters and the automated method (Kruskal-Wallis test: chi-square = 1.46, p = 0.69). The main sources of error were due to signal inhomogeneity and similar intensity patterns between cavity and brain tissues. CONCLUSIONS: The proposed DL approach yields promising results for automated RC segmentation in this proof of concept study. Compared to human experts, the DC are still subpar.

来源:Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Ermiş E, Jungo A, Poel R, et al. Fully automated brain resection cavity delineation for radiation target volume definition in glioblastoma patients using deep learning. Radiat Oncol. 2020. PMID: 32375839. doi:10.1186/s13014-020-01553-z

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。