摘要
目的:探究ResNet模型对肺腺癌不同亚型结节的分类表现及稳定性。方法:回顾性收集2014年2月—2020年10月期间的364例肺腺癌结节CT影像数据,以7∶3的比例分为训练集和内部测试集,将2020年4月到2020年11月的58例结节数据作为外部测试集。使用基于ResNet的三维卷积神经网络在训练集中进行训练以及调参,并使用内部测试集和外部测试集对模型的准确性及泛化性进行评估。使用随机中心移动和掩膜处理的方式分别以内部测试集和外部测试集为基础构造新的测试集,新数据集对模型进行测试验证模型的稳定性。结果:模型在内部测试集AUC为0.9491(95%CI:0.9108~0.9874),模型在随机中心移动以及掩膜处理之后的数据集的AUC值分别为0.9404和0.9181,与其差异无统计学意义(P值分别为0.4253和0.2393)。在外部测试集中模型AUC为0.9596(95%CI:0.9012~1.0000),在用于稳定性测试的随机中心移动以及掩膜处理之后的数据集中,模型所得AUC分别为0.9485和0.9473,与其同样差异无统计学意义(均P>0.05)。结论:ResNet模型对肺腺癌结节亚型有优异的鉴别能力,并且具有一定稳定性。
Objective:To investigate the classification performance and model stability of ResNet models for different subtypes of nodules in lung adenocarcinoma.Methods:The CT image of 364 lung adenocarcinoma nodules collected retrospectively between February 2014 and October 2020 were divided into a training set and an internal test set in a ratio of 7∶3,and data of 58 nodules from April 2020 to November 2020 were used as the external test set.The ResNet-based 3D convolutional neural network was trained and tuned in the training set,and the accuracy and generalization of the model was evaluated using both internal and external test sets.To verify the stability of the model,two new test sets were constructed using random center shifts and masking process in both internal and external test set,and the model was tested using the new test set.Results:The model obtained an AUC of 0.9491(95%CI:0.9108-0.9874)on the internal test set,and the AUC values of the model were not statistically different(P=0.4253 and 0.2393,respectively)from those measured on the data sets with the random center shift and after the masking process.The model AUC in the external test set was 0.9596(95%CI:0.9012-1.0000).In the dataset after the random center shift and mask processing used for stability testing,the AUC obtained for the model(0.9485 and 0.9473,respectively)was again not statistically different from it(all P>0.05).Conclusion:ResNet model has excellent ability to discriminate subtypes of lung adenocarcinoma,and the model has considerable stability.
作者
骆源
徐启飞
吕泽政
蔡娜
郭丽
LUO Yuan;XU Qi-fei;LYU Ze-zheng;CAI Na;GUO Li(Department of Medical Image Processing,School of Medical Technology,Tianjin Medical University,Tianjin 300203,China;Department of Imaging,Linyi People′s Hospital,Linyi 276000,China)
出处
《天津医科大学学报》
2022年第3期295-300,共6页
Journal of Tianjin Medical University
基金
国家自然科学基金(8197070539)
天津市自然科学基金(18JCYBJC95600)。
关键词
人工智能
深度学习
卷积神经网络
肺腺癌
诊断
artificial intelligence
deep learning
convolutional neural network
lung adenocarcinoma
diagnosis
