文献速递肿瘤 PET/CT

基于18F-FDG PET/CT图像对非小细胞肺癌纵隔淋巴结转移分类的机器学习方法比较

Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images.
PubMed 文献 · EJNMMI Res · 2017-01-28

本研究比较了卷积神经网络(CNN)与四种经典机器学习方法(随机森林、支持向量机、自适应提升、人工神经网络)在18F-FDG PET/CT图像上分类非小细胞肺癌纵隔淋巴结转移的性能,使用168例患者的1397枚淋巴结及病理结果作为金标准,采用10次10折交叉验证。结果显示经典方法使用诊断特征时准确率81~85%、AUC 0.87~0.92,显著高于纹理特征;CNN的敏感度、特异度、准确率、AUC分别为84、88、86、0.91,与最佳经典方法无显著差异。所有五种机器学习方法的敏感度均高于本院医生而特异度均低于本院医生。

要点

  • 经典机器学习方法使用诊断特征(肿瘤大小、CT值、SUV等)的准确率81~85%、AUC 0.87~0.92,显著高于纹理特征。
  • CNN的敏感度84、特异度88、准确率86、AUC 0.91,与最佳经典方法无显著差异。
  • 本院医生的敏感度73、特异度90、准确率82;五种机器学习方法敏感度均高于医生而特异度均低于医生。

核心结论

  • CNN在基于PET/CT图像分类非小细胞肺癌纵隔淋巴结转移方面与最佳经典方法和本院医生无显著差异。
  • CNN无需肿瘤分割或特征计算,比经典方法更便捷、更客观。
  • CNN未利用已证明对小结节分类比纹理特征更具判别力的诊断特征,将诊断特征纳入CNN是未来研究的有希望方向。

研究设计与样本

  • 本研究为方法学比较研究,比较一种深度学习方法和四种经典机器学习方法。
  • 四种经典机器学习方法包括随机森林、支持向量机、自适应提升和人工神经网络;深度学习方法为卷积神经网络(CNN)。
  • 使用168例患者的PET/CT图像中收集的1397枚淋巴结,以相应病理分析结果为金标准。
  • 采用10次10折交叉验证,基于敏感度、特异度、准确率(ACC)和ROC曲线下面积(AUC)进行比较。
  • 每种经典方法比较不同输入特征以选择最优特征集,基于最优特征集与CNN及本院医生比较。

主要发现

  • 经典方法中,诊断特征导致81~85%的ACC和0.87~0.92的AUC,显著高于纹理特征的结果。
  • CNN的敏感度、特异度、ACC、AUC分别为84、88、86、0.91。
  • CNN与最佳经典方法的结果之间无显著差异。
  • 本院医生的敏感度、特异度、ACC分别为73、90、82。
  • 所有五种机器学习方法的敏感度均高于本院医生,但特异度均低于本院医生。

关键数值与推荐

  • 经典方法使用诊断特征的ACC为81~85%,AUC为0.87~0.92。
  • CNN的敏感度84、特异度88、ACC 86、AUC 0.91。
  • 本院医生的敏感度73、特异度90、ACC 82。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • CNN未利用已证明比纹理特征更具判别力的诊断特征。
  • 将诊断特征纳入CNN是未来研究的有希望方向。

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: This study aimed to compare one state-of-the-art deep learning method and four classical machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer (NSCLC) from 18F-FDG PET/CT images. Another objective was to compare the discriminative power of the recently popular PET/CT texture features with the widely used diagnostic features such as tumor size, CT value, SUV, image contrast, and intensity standard deviation. The four classical machine learning methods included random forests, support vector machines, adaptive boosting, and artificial neural network. The deep learning method was the convolutional neural networks (CNN). The five methods were evaluated using 1397 lymph nodes collected from PET/CT images of 168 patients, with corresponding pathology analysis results as gold standard. The comparison was conducted using 10 times 10-fold cross-validation based on the criterion of sensitivity, specificity, accuracy (ACC), and area under the ROC curve (AUC). For each classical method, different input features were compared to select the optimal feature set. Based on the optimal feature set, the classical methods were compared with CNN, as well as with human doctors from our institute. RESULTS: For the classical methods, the diagnostic features resulted in 81~85% ACC and 0.87~0.92 AUC, which were significantly higher than the results of texture features. CNN's sensitivity, specificity, ACC, and AUC were 84, 88, 86, and 0.91, respectively. There was no significant difference between the results of CNN and the best classical method. The sensitivity, specificity, and ACC of human doctors were 73, 90, and 82, respectively. All the five machine learning methods had higher sensitivities but lower specificities than human doctors. CONCLUSIONS: The present study shows that the performance of CNN is not significantly different from the best classical methods and human doctors for classifying mediastinal lymph node metastasis of NSCLC from PET/CT images. Because CNN does not need tumor segmentation or feature calculation, it is more convenient and more objective than the classical methods. However, CNN does not make use of the import diagnostic features, which have been proved more discriminative than the texture features for classifying small-sized lymph nodes. Therefore, incorporating the diagnostic features into CNN is a promising direction for future research.

来源:EJNMMI Res,查看原文。版权归原作者所有。

引用

  1. Wang H, Zhou Z, Li Y, et al. Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images. EJNMMI Res. 2017. PMID: 28130689. doi:10.1186/s13550-017-0260-9

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。