Yang Cheng-Kun, Yeh Joe Chao-Yuan, Yu Wei-Hsiang, Chien Ling-I, Lin Ko-Han, Huang Wen-Sheng, Hsu Po-Kuei
aetherAI, Co., Ltd., Taipei 112, Taiwan.
Department of Nursing, Taipei Veterans General Hospital, Taipei 112, Taiwan.
J Clin Med. 2019 Jun 13;8(6):844. doi: 10.3390/jcm8060844.
In esophageal cancer, few prediction tools can be confidently used in current clinical practice. We developed a deep convolutional neural network (CNN) with 798 positron emission tomography (PET) scans of esophageal squamous cell carcinoma and 309 PET scans of stage I lung cancer. In the first stage, we pretrained a 3D-CNN with all PET scans for a task to classify the scans into esophageal cancer or lung cancer. Overall, 548 of 798 PET scans of esophageal cancer patients were included in the second stage with an aim to classify patients who expired within or survived more than one year after diagnosis. The area under the receiver operating characteristic curve (AUC) was used to evaluate model performance. In the pretrain model, the deep CNN attained an AUC of 0.738 in identifying patients who expired within one year after diagnosis. In the survival analysis, patients who were predicted to be expired but were alive at one year after diagnosis had a 5-year survival rate of 32.6%, which was significantly worse than the 5-year survival rate of the patients who were predicted to survive and were alive at one year after diagnosis (50.5%, < 0.001). These results suggest that the prediction model could identify tumors with more aggressive behavior. In the multivariable analysis, the prediction result remained an independent prognostic factor (hazard ratio: 2.830; 95% confidence interval: 2.252-3.555, < 0.001). We conclude that a 3D-CNN can be trained with PET image datasets to predict esophageal cancer outcome with acceptable accuracy.
在食管癌中，目前临床实践中几乎没有可放心使用的预测工具。我们利用798例食管鳞状细胞癌的正电子发射断层扫描（PET）和309例I期肺癌的PET扫描数据开发了一种深度卷积神经网络（CNN）。在第一阶段，我们使用所有PET扫描数据对3D-CNN进行预训练，以将扫描数据分类为食管癌或肺癌。总体而言，798例食管癌患者的PET扫描中有548例被纳入第二阶段，目的是对诊断后一年内死亡或存活超过一年的患者进行分类。采用受试者操作特征曲线下面积（AUC）来评估模型性能。在预训练模型中，深度CNN在识别诊断后一年内死亡的患者时，AUC达到0.738。在生存分析中，预测为死亡但诊断后一年仍存活的患者5年生存率为32.6%，明显低于预测为存活且诊断后一年仍存活的患者的5年生存率（50.5%，<0.001）。这些结果表明，该预测模型可以识别具有更侵袭性的肿瘤。在多变量分析中，预测结果仍然是一个独立的预后因素（风险比：2.830；95%置信区间：2.252 - 3.555，<0.001）。我们得出结论，3D-CNN可以通过PET图像数据集进行训练，以可接受的准确率预测食管癌的预后。
