文献速递肿瘤 PET/CT

基于深度学习的头颈癌PET/CT图像肿瘤大体体积及受累淋巴结自动勾画

Deep learning-based auto-delineation of gross tumour volumes and involved nodes in PET/CT images of head and neck cancer patients.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2021-02-09

本研究评估卷积神经网络(CNN)在头颈癌(HNC)患者FDG-PET/CT图像上全自动勾画肿瘤大体体积(GTV)的适用性,并与专家手动勾画比较。U-Net模型在197例HNC患者数据上训练和评估,基于PET/CT的模型平均Dice为71%,识别86%的真实GTV结构,而仅基于CT的模型仅识别55%。结论认为多模态PET/CT结合CNN可提供高质量自动勾画。

要点

  • 基于PET/CT的CNN模型平均Dice为71%,优于CT-only(55%)和PET-only(69%)。
  • PET/CT模型识别86%的真实GTV结构,CT-only模型仅识别55%。
  • 肿瘤学家对15例随机选取患者中的14例自动勾画评价为非常高质量。

核心结论

  • CNN利用多模态PET/CT可为头颈癌提供高质量GTV自动勾画,新结构评价指标有助于评估模型优劣。

研究设计与样本

  • 研究训练和评估U-Net CNN模型,使用197例HNC患者图像及手动GTV勾画,数据集分为训练142例、验证15例和测试40例。

主要发现

  • CT-based、PET-based和PET/CT-based CNN模型的平均Dice分别为55%、69%和71%。
  • PET信号对所有结构的勾画至关重要,PET/CT模型识别86%的真实GTV结构,CT-only模型仅识别55%。
  • 肿瘤学家对测试队列中随机选取的15例患者中的14例自动勾画报告为非常高质量。

关键数值与推荐

  • 采用Dice score、表面距离指标和新的结构基础指标评估模型,并由肿瘤学家对15例随机患者手动评估自动勾画。

临床怎么用

  • 基于PET/CT的CNN自动勾画可作为头颈癌放疗GTV勾画的高质量辅助工具,但需结合临床评估。

局限性

  • 自动勾画在部分患者中仍需人工评估,且研究样本量有限,外部泛化性未验证。

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)。

原文

PURPOSE: Identification and delineation of the gross tumour and malignant nodal volume (GTV) in medical images are vital in radiotherapy. We assessed the applicability of convolutional neural networks (CNNs) for fully automatic delineation of the GTV from FDG-PET/CT images of patients with head and neck cancer (HNC). CNN models were compared to manual GTV delineations made by experienced specialists. New structure-based performance metrics were introduced to enable in-depth assessment of auto-delineation of multiple malignant structures in individual patients. METHODS: U-Net CNN models were trained and evaluated on images and manual GTV delineations from 197 HNC patients. The dataset was split into training, validation and test cohorts (n= 142, n = 15 and n = 40, respectively). The Dice score, surface distance metrics and the new structure-based metrics were used for model evaluation. Additionally, auto-delineations were manually assessed by an oncologist for 15 randomly selected patients in the test cohort. RESULTS: The mean Dice scores of the auto-delineations were 55%, 69% and 71% for the CT-based, PET-based and PET/CT-based CNN models, respectively. The PET signal was essential for delineating all structures. Models based on PET/CT images identified 86% of the true GTV structures, whereas models built solely on CT images identified only 55% of the true structures. The oncologist reported very high-quality auto-delineations for 14 out of the 15 randomly selected patients. CONCLUSIONS: CNNs provided high-quality auto-delineations for HNC using multimodality PET/CT. The introduced structure-wise evaluation metrics provided valuable information on CNN model strengths and weaknesses for multi-structure auto-delineation.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Moe YM, Groendahl AR, Tomic O, et al. Deep learning-based auto-delineation of gross tumour volumes and involved nodes in PET/CT images of head and neck cancer patients. Eur J Nucl Med Mol Imaging. 2021. PMID: 33559711. doi:10.1007/s00259-020-05125-x

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。