Wang Zhiming, Dong Jingjing, Zhang Junpeng
College of Electrical Engineering, Sichuan University, Chengdu, 610056 China.
Key Laboratory of Aerospace Medicine of Ministry of Education, Air Force Medical University, Xi'an, 710032 China.
J Shanghai Jiaotong Univ Sci. 2022;27(1):70-80. doi: 10.1007/s12204-021-2392-3. Epub 2021 Dec 26.
Deep learning based analyses of computed tomography (CT) images contribute to automated diagnosis of COVID-19, and ensemble learning may commonly provide a better solution. Here, we proposed an ensemble learning method that integrates several component neural networks to jointly diagnose COVID-19. Two ensemble strategies are considered: the output scores of all component models that are combined with the weights adjusted adaptively by cost function back propagation; voting strategy. A database containing 8 347 CT slices of COVID-19, common pneumonia and normal subjects was used as training and testing sets. Results show that the novel method can reach a high accuracy of 99.37% (recall: 0.9981, precision: 0.989 3), with an increase of about 7% in comparison to single-component models. And the average test accuracy is 95.62% (recall: 0.958 7, precision: 0.955 9), with a corresponding increase of 5.2%. Compared with several latest deep learning models on the identical test set, our method made an accuracy improvement up to 10.88%. The proposed method may be a promising solution for the diagnosis of COVID-19.
基于深度学习的计算机断层扫描（CT）图像分析有助于COVID-19的自动诊断，而集成学习通常可能提供更好的解决方案。在此，我们提出了一种集成学习方法，该方法整合了多个组件神经网络来联合诊断COVID-19。考虑了两种集成策略：所有组件模型的输出分数，通过代价函数反向传播自适应调整权重后进行组合；投票策略。一个包含8347张COVID-19、普通肺炎和正常受试者CT切片的数据库用作训练和测试集。结果表明，该新方法可以达到99.37%的高精度（召回率：0.9981，精确率：0.9893），与单组件模型相比提高了约7%。平均测试精度为95.62%（召回率：0.9587，精确率：0.9559），相应提高了5.2%。与同一测试集上的几个最新深度学习模型相比，我们的方法精度提高了10.88%。所提出的方法可能是诊断COVID-19的一个有前途的解决方案。
