文献速递神经MR

深度学习自动勾画高级别胶质瘤大体肿瘤体积的研究

Automated Gross Tumor Volume (GTV) Contouring in High-Grade Gliomas Using a Deep Learning Approach.
PubMed 文献 · Acad Radiol · 2026-01-15

本研究采用改良3D U-Net,在469例BraTS 2018-2019多序列MRI数据上训练,用于高级别胶质瘤GTV自动勾画。GTV依据ESTRO-EANO指南,以增强T1WI上强化区为准,不包括水肿。结果显示模型DSC为91.70%±4.62%,HD95为2.43±1.30 mm。

要点

  • GTV勾画依据ESTRO-EANO指南,基于增强T1WI强化区,不包括水肿区域
  • 自动勾画模型DSC达91.70%±4.62%,与手动勾画重叠度高
  • 深度学习勾画可辅助放疗计划,提升工作流程效率

核心结论

  • 深度学习在高级别胶质瘤GTV自动勾画中具有高效应用潜力,可支持放疗计划并改善临床工作流程

研究设计与样本

  • 研究类型为深度学习算法开发与验证,训练样本量469例,数据来源于BraTS 2018-2019挑战赛多序列MRI
  • 采用改良3D U-Net架构,以多序列MRI增强特征学习
  • GTV参考标准依据ESTRO-EANO指南,以增强后T1WI对比强化区为基准,不包括水肿,对应数据集中增强肿瘤与坏死核心标签
  • 分割精度以Dice相似系数和95百分位Hausdorff距离评估

关键影像表现/征象

  • GTV在增强后T1WI上表现为肿瘤对比强化区,不包括周围水肿

诊断标准与关键数值

  • 自动分割模型DSC为91.70%±4.62%(mean±SD),HD95为2.43±1.30 mm
  • GTV定义标准为增强后T1WI上对比强化区,不包括水肿,对应增强肿瘤与坏死核心标签

临床应用与阅片要点

  • 自动GTV勾画可用于高级别胶质瘤放疗计划,辅助减少手动勾画时间
  • 勾画范围仅包括增强后T1WI强化区,阅片报告时需注意水肿不应计入GTV

局限性

  • 训练数据仅来自BraTS 2018-2019挑战赛公开数据集,缺乏多中心外部验证

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)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: Accurate contouring of the Gross Tumor Volume (GTV) in High-Grade Gliomas (HGGs) is a cornerstone of effective Radiation Therapy (RT) planning, as it influences tumor control and spares normal tissue, thereby directly impacting treatment precision. However, the standard manual approach to GTV contouring requires considerable time and is prone to inter-observer variability. Accordingly, this study presents a deep learning framework for automatic GTV contouring in HGG cases.

MATERIALS AND METHODS: A modified 3D U-Net architecture was employed and trained on 469 subjects sourced from the Brain Tumor Segmentation (BraTS) 2018-2019 challenges, with multi-sequence magnetic resonance imaging (MRI) to enhance feature learning. The GTV was delineated following the European Society for Radiotherapy and Oncology (ESTRO) and the European Association of Neuro-Oncology (EANO) guidelines, based on the contrast-enhancing region of the tumor on post-contrast T1-weighted images, excluding edema. This corresponds to the enhancing tumor and necrotic core labels in our dataset. The segmentation accuracy was assessed using the Dice Similarity Coefficient (DSC) and the 95th-percentile Hausdorff Distance (HD95).

RESULTS: The proposed model yielded a DSC of 91.70% ± 4.62% (mean ± standard deviation) and an HD95 of 2.43 ± 1.30 mm, indicating a high degree of overlap with minimal boundary deviation.

CONCLUSION: The results of our study highlight the potential of deep learning as a promising and efficient solution for GTV contouring in HGGs, supporting RT planning, improving clinical workflow, and enhancing treatment accuracy.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Elmezayen, Eladawi, Akl, et al. Automated Gross Tumor Volume (GTV) Contouring in High-Grade Gliomas Using a Deep Learning Approach. Acad Radiol. 2026. PMID: 41545259. doi:10.1016/j.acra.2025.12.046

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。