文献速递泌尿生殖与妇科肿瘤放疗放疗物理与技术

深度学习用于宫颈癌高剂量率近距离放疗危及器官自动分割

Deep learning-based auto-segmentation of organs at risk in high-dose rate brachytherapy of cervical cancer.
PubMed 文献 · Radiother Oncol · 2021-04-06

测试集DSC分别为95.7±3.7%、96.6±1.5%和92.2±3.3%,表明自动勾画与手动勾画一致性良好,可提高近距离放疗勾画可重复性。

要点

  • ResU-Net可快速自动勾画宫颈癌HDR-BT中膀胱、直肠和乙状结肠。
  • 测试集DSC膀胱95.7%、直肠96.6%、乙状结肠92.2%。
  • 自动勾画与手动勾画一致性良好,有望提高工作流程可重复性。

核心结论

  • 所提出的深度卷积神经网络模型在危及器官预测轮廓与手动定义轮廓之间取得良好一致性,从而提高了近距离放疗工作流程中勾画的可重复性。

研究设计与样本

  • 研究纳入113例局部晚期宫颈癌患者图像,采用ResU-Net深度卷积神经网络架构,利用长和短跳跃连接改进特征提取过程与分割准确性。

主要发现

  • 测试集膀胱、直肠和乙状结肠的DSC分别为95.7±3.7%、96.6±1.5%和92.2±3.3%。
  • 测试集膀胱、直肠和乙状结肠的HD(mm)分别为4.05±5.17、1.96±2.19和3.15±2.03。
  • 测试集膀胱、直肠和乙状结肠的ASSD分别为1.04±0.97、0.45±0.09和0.79±0.25。

临床怎么用

  • 该模型可用于宫颈癌HDR-BT中膀胱、直肠和乙状结肠的快速自动勾画,以提高勾画可重复性。

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 AND PURPOSE: Delineation of organs at risk (OARs), such as the bladder, rectum and sigmoid, plays an important role in the delivery of optimal absorbed dose to the target owing to the steep gradient in high-dose rate brachytherapy (HDR-BT). In this work, we propose a deep convolutional neural network-based approach for fast and reproducible auto-contouring of OARs in HDR-BT. MATERIALS AND METHODS: Images of 113 patients with locally-advanced cervical cancer were utilized in this study. We used ResU-Net deep convolutional neural network architecture, which uses long and short skip connections to improve the feature extraction procedure and the accuracy of segmentation. Seventy-three patients chosen randomly were used for training, 10 patients for validation, and 30 patients for testing. Well established quantitative metrics, such as Dice similarity coefficient (DSC), Hausdorff distance (HD), and average symmetric surface distance (ASSD), were used for evaluation. RESULTS: The DSC values for the test dataset were 95.7 ± 3.7%, 96.6 ± 1.5% and 92.2 ± 3.3% for the bladder, rectum, and sigmoid, respectively. The HD values (mm) were 4.05 ± 5.17, 1.96 ± 2.19 and 3.15 ± 2.03 for the bladder, rectum, and sigmoid, respectively. The ASSDs were 1.04 ± 0.97, 0.45 ± 0.09 and 0.79 ± 0.25 for the bladder, rectum, and sigmoid, respectively. CONCLUSION: The proposed deep convolutional neural network model achieved a good agreement between the predicted and manually defined contours of OARs, thus improving the reproducibility of contouring in brachytherapy workflow.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Mohammadi R, Shokatian I, Salehi M, et al. Deep learning-based auto-segmentation of organs at risk in high-dose rate brachytherapy of cervical cancer. Radiother Oncol. 2021. PMID: 33831446. doi:10.1016/j.radonc.2021.03.030

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。