Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from (18)F-FDG PET/CT images.
Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from (18)F-FDG PET/CT images.
复制标题
F-18-FDG PET/CT图像分类非小细胞肺癌纵隔淋巴结转移的机器学习方法比较
DOI：
10.1186/s13550-017-0260-9
复制
发表时间：
2017-12
期刊：
影响因子：
3.2
通讯作者：
Yu L
中科院分区：
文献类型：
--
作者：
Wang H;Zhou Z;Li Y;Chen Z;Lu P;Wang W;Liu W;Yu L
本研究旨在比较一种最先进的深度学习方法和四种经典的机器学习方法，用于从18F-FDG PET/CT图像中分类非小细胞肺癌（NSCLC）的纵隔淋巴结转移。另一个目的是比较最近流行的PET/CT纹理特征与广泛使用的诊断特征（如肿瘤大小、CT值、SUV、图像对比度和强度标准差）的区分能力。四种经典的机器学习方法包括随机森林、支持向量机、自适应Boosting和人工神经网络。深度学习方法是卷积神经网络（CNN）。对168例患者的1397个淋巴结进行PET/CT检查，以相应的病理分析结果作为金标准，对5种方法进行评价。基于灵敏度、特异性、准确性（ACC）和ROC曲线下面积（AUC）标准，使用10 × 10倍交叉验证进行比较。对于每种经典方法，比较不同的输入特征以选择最佳特征集。基于最优特征集，将经典方法与CNN以及我们研究所的人类医生进行了比较。对于经典方法，诊断特征得到81~ 85%ACC和0.87~0.92 AUC，显著高于纹理特征的结果。CNN的灵敏度、特异性、ACC和AUC分别为84、88、86和0.91。CNN的结果与最佳经典方法的结果无显著性差异。人类医生的灵敏度、特异性和ACC分别为73、90和82。所有五种机器学习方法都比人类医生具有更高的灵敏度，但特异性较低。目前的研究表明，CNN的性能与最好的经典方法和人类医生从PET/CT图像分类NSCLC纵隔淋巴结转移没有显着差异。由于CNN不需要肿瘤分割或特征计算，因此比经典方法更方便，更客观。然而，CNN没有利用进口诊断特征，这已被证明比纹理特征更有鉴别力的分类小尺寸的淋巴结。因此，将诊断特征纳入CNN是未来研究的一个有前途的方向。
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. 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. 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.