基于CT图像卷积神经网络处理的新冠肺炎检测

doi:10.3969/j.issn.1000-1158.2021.04.21

摘要
图/表
参考文献(23)
相关文章 (15)

全文: PDF (3419 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要为增强对新冠肺炎与普通肺炎的区分能力,协助医护人员对肺炎患者进行胸部CT检测,在人工智能图像分析的基础上提出了一种基于CT图像卷积神经网络处理新冠肺炎的检测方法。首先,搭建一个卷积神经网络模型,通过评估模型深度对检测结果的影响,以选择最佳的网络结构;其次,提出了一种禁忌遗传算法,用以获取网络模型中最优的超参数组合,增强模型的辨识能力;最后,通过最佳的卷积神经网络模型来辨别新冠肺炎与普通肺炎。实验结果表明:所提出的检测算法的准确率、MCC值和F1Score值分别为93.89%,93.32%和91.40%,相对其他模型具有更高的检测精度。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	郭保苏
	庄集超
	吴凤和
	车小双
	袁林栋
	齐军

关键词 ：计量学, 新冠肺炎检测, 卷积神经网络, 禁忌遗传算法, CT图像, 超参数优化

Abstract：To improve the ability to distinguish novel coronavirus pneumonia from common pneumonia and assist medical staff in chest CT examination of pneumonia patients, a detection method using convolution neural network and CT image based on artificial intelligence image analysis was proposed. First, a convolution neural network model was built, and the influence of model depth on detection results was evaluated to select the best network structure. Second, a tabu genetic algorithm was proposed to obtain the optimal hyper-parameter combination of the network model and to enhance the performance of the model. Finally, the best network model was employed to distinguish novel coronavirus pneumonia from common pneumonia. Experimental results show that the accuracy, MCC, and F1Score of the proposed detection algorithm are 93.89%, 93.32% and 91.40%, respectively, which has higher detection accuracy than other algorithms.

Key words： metrology novel coronavirus pneumonia detection convolutional neural network tabu genetic algorithm CT image hyper-parameter optimization

收稿日期: 2020-04-17 发布日期: 2021-04-20

PACS:	TB99
	TP391.41

基金资助:国家自然科学基金(51605422);河北省自然科学基金(E2017203156,E2017203372)

通讯作者: 齐军(1987-),男,山东茌平人,聊城市人民医院主治医师,主要从事呼吸内科疾病诊治工作研究。Email: qijun369369@126.com E-mail: qijun369369@126.com

作者简介: 郭保苏(1986-),男,博士,山东茌平人,燕山大学讲师,主要研究方向为图像处理和排样。Email: guobaosu@ysu.edu.cn

引用本文:

郭保苏,庄集超,吴凤和,车小双,袁林栋,齐军. 基于CT图像卷积神经网络处理的新冠肺炎检测[J]. 计量学报, 2021, 42(4): 537-544.
GUO Bao-su,ZHUANG Ji-chao,WU Feng-he,CHE Xiao-shuang,YUAN Lin-dong,QI Jun. Detection of Novel Coronavirus Pneumonia Based on CT Image with Convolutional Neural Network Processing. Acta Metrologica Sinica, 2021, 42(4): 537-544.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2021.04.21 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2021/V42/I4/537

［1］Fang Y, Zhang H, Xie J, et al. Sensitivity of chest CT for COVID-19: comparison to RT-PCR［EB］. https://pubs.rsna.org/doi/full/10.1148/radiol.2020200432, 2020-02-19.
［2］Bernheim A, Mei X, Huang M, et al. Chest CT findings in coronavirus disease-19 (COVID-19): relationship to duration of infection［EB］. https:/pubs.rsna.org/doi/10.1148/radiol.2020200463, 2020-02-20.
［3］冯雨, 易本顺, 吴晨玥, 等. 基于三维卷积神经网络的肺结节识别研究［J］. 光学学报. 2019, 39(6): 256-261.
Feng Y, Yi B S, Wu C Y, et al. Pulmonary nodule recognition based on three-dimensional convolution neural network［J］. Acta Optica Sinica, 2019, 39(6): 256-261.
［4］马圆, 王风, 韩勇, 等. 基于深度信念网络检测PET/CT图像肺结节良恶性［J］. 中国医学影像技术. 2020, 36(1): 77-80.
Ma Y, Wang F, Han Y, et al. Classification of pulmonary nodule on PET/CT image based on deep belief network［J］. Chin J Med Imaging Technol, 2020, 36(1): 77-80.
［5］黄盛, 李菲菲, 陈虬. 基于改进深度残差网络的计算断层扫描图像分类算法［J］. 光学学报. 2020, 40(3): 56-64.
Huang S, Li F F, Chen Q. Computed tomography image classification algorithm based on improved deep residual network［J］. Acta Optica Sinica, 2020, 40(3): 56-64.
［6］Zhu W, Zhuang J, Guo B, et al. An optimized convolutional neural network for chatter detection in the milling of thin-walled parts［J］. The International Journal of Advanced Manufacturing Technology, 2020, 106(9): 3881-3895.
［7］Shalu C, Sachin T, Varun B, et al. Convolutional neural network based approach towards motor imagery tasks EEG signals classification［J］. IEEE Sensors Journal, 2019, 19(12): 4494-4500.
［8］Ma M, Liu L, Chen Y L. A KM-net model based on k-means weight initialization for images classification［C］//2018 IEEE 20th International Conference on High Performance Computing and Communications, Exeter, United Kingdom, 2018.
［9］Ijjina E P, Chalavadi K M. Human action recognition using genetic algorithms and convolutional neural networks［J］. Pattern Recognition, 2016, 59: 199-212.
［10］Zheng M, Tang W, Zhao X. Hyperparameter optimization of neural network-driven spatial models accelerated using cyber-enabled high-performance computing［J］. International Journal of Geographical Information Science, 2019, 33(2): 314-345.
［11］Zhang M, Li H Q, Lyu J, et al. Multi-level CNN for lung nodule classification with gaussian process assisted hyperparameter optimization［EB］. hattps://arXive-prints:arXiv:1901.00276, 2019-01-02.
［12］Wang Y, Zhang H, Zhang G. cPSO-CNN: An efficient PSO-based algorithm for fine-tuning hyper-parameters of convolutional neural networks［J］. Swarm and Evolutionary Computation, 2019, 49: 114-123.
［13］谢未央, 陈彦博, 王季勇, 等. 基于卷积神经网络的CT图像肺结节检测［J］. 计算机工程与设计. 2019, 40(12): 3575-3581.
Xie W Y, Chen Y B, Wang J Y, et al. Detection of pulmonary nodules in CT images based on convolutional neural networks［J］. Computer Engineering and Design, 2019, 40(12): 3575-3581.
［14］程淑红, 张仕军, 赵考鹏. 基于卷积神经网络的生物式水质监测方法［J］. 计量学报, 2019, 40(4): 721-727.
Chen S H, Zhang S J, Zhao K P. Biological water quality monitoring method based on convolution neural network［J］. Acta Metrologica Sinica, 2019, 40(4): 721-727.
［15］Zhang J P, Xie Y T, Xia Y, et al. Attention residual learning for skin lesion classification［J］. IEEE Transactions on Medical Imaging, 2019, 38(9): 2092-2103.
［16］孙美艳, 田玉玲. 基于混沌免疫算法的深度信念网络参数优化［J］. 计算机工程与设计. 2019, 40(9): 2643-2648.
Sun M Y, Tian Y L. Parameter optimization of deep belief network based on chaos immune algorithm［J］. Computer Engineering and Design, 2019, 40(9): 2643-2648.
［17］Springenberg J T, Dosovitskiy A, Brox T, et al. Striving for simplicity: the all convolutional net［EB］. hattp: //arXiv preprint arXiv: 1412. 6806, 2014-12-21.
［18］Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting［J］. J. Mach. Learn. Res, 2014, 15(1): 1929-1958.
［19］Xia Y, Fu Z. A tabu search algorithm for distribution network optimization with discrete split deliveries and soft time windows［J］. Cluster Computing, 2019, 22(6): 15447-15457.
［20］张沫, 郑慧峰, 倪豪, 等. 基于遗传算法优化支持向量机的超声图像缺陷分类［J］. 计量学报. 2019, 40(5): 887-892.
Zhang M, Zheng H F, Ni H, et al. Ultrasonic image defect classification based on support vector machine optimized by genetic algorithm ［J］. Acta Metrologica Sinica, 2019, 40(5): 887-892.
［21］Boussad I, Lepagnot J, Siarry P. A survey on optimization metaheuristics［J］. Information Sciences, 2013, 237: 82-117.
［22］Wu Q, Wang Y, Glover F. Advanced tabu search algorithms for bipartite boolean quadratic programs guided by strategic oscillation and path relinking［J］. Informs Journal on Computing, 2019, 32(1): 74-89.
［23］杨振良, 汪俊亮, 张洁, 等. 数据驱动的晶圆图缺陷模式识别方法［J］. 中国机械工程. 2019, 30(2): 230-236.
Yang Z L, Wang J L, Zhang J, et al. Data driven wafer pattern defect pattern recognition method［J］. China Mechanical Engineering, 2019, 30(2): 230-236.