文献速递消化道肿瘤放疗放疗物理与技术

深度学习自动勾画直肠癌术后放疗临床靶区与危及器官

Automatic delineation of the clinical target volume and organs at risk by deep learning for rectal cancer postoperative radiotherapy.
PubMed 文献 · Radiother Oncol · 2020-02-07

本研究回顾性收集199例直肠癌术后放疗患者的CT扫描,构建并验证两种卷积神经网络(DeepLabv3+与ResUNet)自动勾画临床靶区(CTV)和危及器官(OAR)。DeepLabv3+在CTV勾画上定量参数优于ResUNet,且客观评分最高;两种模型对OAR勾画的手动修正时间均小于4分钟。

要点

  • DeepLabv3+勾画CTV的体积Dice系数0.88,优于ResUNet的0.87(P=0.0005)。
  • 315例评分中DeepLabv3+有284例获最高分,与客观标准一致。
  • CTVResUNet平均手动修正时间最短,为7.29分钟。

核心结论

  • 不同特征分辨率级别的CNN能高质量勾画直肠癌CTV和OAR,计算与手动修正时间较短。

研究设计与样本

  • 回顾性收集2018年2月至2019年4月在本院治疗的199例直肠癌患者的CT扫描。
  • 使用DeepLabv3+提取高层语义信息、ResUNet提取低层视觉特征,分别用于CTV和小肠、膀胱和股骨头勾画。
  • 采用配对t检验比较勾画质量,由两名经验丰富的放疗肿瘤学家独立进行五点客观评分并由第三名验证。

主要发现

  • DeepLabv3+勾画的CTV(CTVDeepLabv3+)体积Dice系数0.88 vs 0.87(P=0.0005),表面Dice系数0.79 vs 0.78(P=0.008),均优于CTVResUNet。
  • 315例评分中,DeepLabv3+在284例获得最高分,与客观标准一致;CTVResUNet平均手动修正时间最短为7.29分钟。
  • 小肠勾画DeepLabv3+优于ResUNet,膀胱和股骨头勾画ResUNet优于DeepLabv3+。
  • 两种模型对OAR的手动修正时间均小于4分钟。

关键数值与推荐

  • CTVDeepLabv3+体积Dice系数0.88,表面Dice系数0.79。
  • CTVResUNet体积Dice系数0.87,表面Dice系数0.78。
  • CTVResUNet平均手动修正时间7.29分钟。
  • OAR手动修正时间两种模型均小于4分钟。

临床怎么用

  • CNN可辅助直肠癌术后放疗的CTV和OAR自动勾画,减少手动修正时间。
  • CTV勾画可优先考虑DeepLabv3+,小肠勾画DeepLabv3+更优,膀胱和股骨头勾画ResUNet更优。

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: Manual delineation of clinical target volumes (CTVs) and organs at risk (OARs) is time-consuming, and automatic contouring tools lack clinical validation. We aimed to construct and validate the use of convolutional neural networks (CNNs) to set better contouring standards for rectal cancer radiotherapy. MATERIALS AND METHODS: We retrospectively collected and evaluated computed tomography (CT) scans of 199 rectal cancer patients treated at our hospital from February 2018 to April 2019. Two CNNs-DeepLabv3+ for extracting high-level semantic information and ResUNet for extracting low-level visual features-were used for the CTV and small intestine contouring, and bladder and femoral head contouring, respectively. Contouring quality was compared using the paired t test. Five-point objective grading was performed independently by two experienced radiation oncologists and verified by a third. The CNN manual correction time was recorded. RESULTS: CTVs calculated using DeepLabv3+ (CTVDeepLabv3+) had significant quantitative parameter advantages over CTVResUNet (volumetric Dice coefficient, 0.88 vs 0.87, P = 0.0005; surface Dice coefficient, 0.79 vs 0.78, P = 0.008). Among 315 graded cases, DeepLabv3+ obtained the highest scores with 284 cases, consistent with the objective criteria, whereas CTVResUNet had the minimum mean manual correction time (7.29 min). DeepLabv3+ performed better than ResUNet for small intestine contouring and ResUNet performed better for bladder and femoral head contouring. The manual correction time for OARs was <4 min for both models. CONCLUSION: CNNs at various feature resolution levels well delineate rectal cancer CTVs and OARs, displaying high quality and requiring shorter computation and manual correction time.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Song Y, Hu J, Wu Q, et al. Automatic delineation of the clinical target volume and organs at risk by deep learning for rectal cancer postoperative radiotherapy. Radiother Oncol. 2020. PMID: 32044531. doi:10.1016/j.radonc.2020.01.020

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。