文献速递肿瘤 PET/CT

基于自注意力卷积神经网络的全自动头颈癌[18F]FDG PET/CT代谢肿瘤体积勾画

A convolutional neural network with self-attention for fully automated metabolic tumor volume delineation of head and neck cancer in [ 18 F]FDG PET/CT.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2023-04-20

研究开发了含多头自注意力模块的残差3D U-Net卷积神经网络,用于头颈癌[18F]FDG PET/CT中原发灶和淋巴结转移灶的自动勾画与分类。训练测试用3个中心及5个公共数据库的698例扫描,外部验证用2个额外中心的181例扫描。交叉验证中原发灶、淋巴结转移灶及两者联合的Dice相似系数分别为0.885、0.805、0.870,外部测试分别为0.850、0.724、0.823;手动与自动总MTV的Cox分析风险比基本一致。

要点

  • 交叉验证中自动勾画原发灶、淋巴结转移灶及联合的Dice系数分别为0.885、0.805、0.870。
  • 外部测试中上述Dice系数分别为0.850、0.724、0.823,体素分类准确率97.9%。
  • 交叉验证与外部测试中手动和自动总MTV的风险比基本一致,对总生存均有预后价值。

核心结论

  • 据作者所知,这是首个成功用于头颈癌MTV勾画和病灶分类的CNN模型。
  • 在绝大多数患者中,网络对原发灶和淋巴结转移灶的勾画与分类表现令人满意,仅很少需要超过 minimal 的人工修正。
  • 该工具能极大促进大样本患者群的研究数据评估,并在监督下具有明确的临床应用潜力。

研究设计与样本

  • 采用含多头自注意力模块的残差3D U-Net卷积神经网络进行自动病灶勾画。
  • 使用来自3个不同中心和5个公共数据库的698例[18F]FDG PET/CT扫描进行网络训练和测试。
  • 使用来自2个额外中心的181例[18F]FDG PET/CT扫描作为外部数据集评估泛化能力。
  • 由两名经验丰富的医师交互式勾画并标记原发灶和淋巴结转移灶。
  • 在主数据集中通过5折交叉验证评估训练模型性能,在外部数据集中通过汇总5个已开发模型的结果进行评估。

主要发现

  • 交叉验证中,训练U-Net模型勾画所有恶性病灶的原发灶、淋巴结转移灶及两者联合的Dice相似系数分别为0.885、0.805、0.870。
  • 外部测试中,原发灶、淋巴结转移灶及两者联合的Dice相似系数分别达到0.850、0.724、0.823。
  • 体素分类准确率在交叉验证和外部数据中分别为98.0%和97.9%。
  • 交叉验证中单因素Cox分析显示手动与自动总MTV对总生存均有高度预后价值,风险比基本一致(HRman=1.9;p<0.001 vs HRcnn=1.8;p<0.001)。
  • 外部测试中单因素Cox分析显示手动与自动总MTV风险比基本一致(HRman=1.8;p=0.011 vs HRcnn=1.9;p=0.004)。

关键数值与推荐

  • 交叉验证中原发灶、淋巴结转移灶及联合的Dice相似系数分别为0.885、0.805、0.870。
  • 外部测试中原发灶、淋巴结转移灶及联合的Dice相似系数分别为0.850、0.724、0.823。
  • 体素分类准确率在交叉验证和外部数据中分别为98.0%和97.9%。
  • 交叉验证中手动与自动总MTV的HR分别为1.9(p<0.001)和1.8(p<0.001)。
  • 外部测试中手动与自动总MTV的HR分别为1.8(p=0.011)和1.9(p=0.004)。

临床怎么用

  • 作者认为该网络在绝大多数患者中勾画和分类表现令人满意,仅很少需要超过 minimal 的人工修正。
  • 作者认为该工具能极大促进大样本患者群的研究数据评估,并在监督下具有明确的临床应用潜力。

局限性

  • 原文未报告局限性。

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

PURPOSE: PET-derived metabolic tumor volume (MTV) and total lesion glycolysis of the primary tumor are known to be prognostic of clinical outcome in head and neck cancer (HNC). Including evaluation of lymph node metastases can further increase the prognostic value of PET but accurate manual delineation and classification of all lesions is time-consuming and prone to interobserver variability. Our goal, therefore, was development and evaluation of an automated tool for MTV delineation/classification of primary tumor and lymph node metastases in PET/CT investigations of HNC patients. METHODS: Automated lesion delineation was performed with a residual 3D U-Net convolutional neural network (CNN) incorporating a multi-head self-attention block. 698 [ 18 F]FDG PET/CT scans from 3 different sites and 5 public databases were used for network training and testing. An external dataset of 181 [ 18 F]FDG PET/CT scans from 2 additional sites was employed to assess the generalizability of the network. In these data, primary tumor and lymph node (LN) metastases were interactively delineated and labeled by two experienced physicians. Performance of the trained network models was assessed by 5-fold cross-validation in the main dataset and by pooling results from the 5 developed models in the external dataset. The Dice similarity coefficient (DSC) for individual delineation tasks and the primary tumor/metastasis classification accuracy were used as evaluation metrics. Additionally, a survival analysis using univariate Cox regression was performed comparing achieved group separation for manual and automated delineation, respectively. RESULTS: In the cross-validation experiment, delineation of all malignant lesions with the trained U-Net models achieves DSC of 0.885, 0.805, and 0.870 for primary tumor, LN metastases, and the union of both, respectively. In external testing, the DSC reaches 0.850, 0.724, and 0.823 for primary tumor, LN metastases, and the union of both, respectively. The voxel classification accuracy was 98.0% and 97.9% in cross-validation and external data, respectively. Univariate Cox analysis in the cross-validation and the external testing reveals that manually and automatically derived total MTVs are both highly prognostic with respect to overall survival, yielding essentially identical hazard ratios (HR) ( HR man = 1.9 ; p < 0.001 vs. HR cnn = 1.8 ; p < 0.001 in cross-validation and HR man = 1.8 ; p = 0.011 vs. HR cnn = 1.9 ; p = 0.004 in external testing). CONCLUSION: To the best of our knowledge, this work presents the first CNN model for successful MTV delineation and lesion classification in HNC. In the vast majority of patients, the network performs satisfactory delineation and classification of primary tumor and lymph node metastases and only rarely requires more than minimal manual correction. It is thus able to massively facilitate study data evaluation in large patient groups and also does have clear potential for supervised clinical application.

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

引用

  1. Nikulin P, Zschaeck S, Maus J, et al. A convolutional neural network with self-attention for fully automated metabolic tumor volume delineation of head and neck cancer in [ 18 F]FDG PET/CT. Eur J Nucl Med Mol Imaging. 2023. PMID: 37079128. doi:10.1007/s00259-023-06197-1

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。