计算机科学技术学报 ›› 2022,Vol. 37 ›› Issue (2): 330-343.doi: 10.1007/s11390-020-0679-8

所属专题: Artificial Intelligence and Pattern Recognition

• • 上一篇    下一篇

通过新型深度学习架构诊断COVID-19肺炎

  

  • 收稿日期:2020-06-03 修回日期:2021-01-18 接受日期:2021-03-30 出版日期:2022-03-31 发布日期:2022-03-31

Diagnosis of COVID-19 Pneumonia via a Novel Deep Learning Architecture

Xin Zhang1 (张鑫), Siyuan Lu2 (陆思源), Shui-Hua Wang3,4 (王水花), Xiang Yu2 (余翔), Su-Jing Wang5,6 (王甦菁), Lun Yao7 (姚仑), Yi Pan8 (潘毅), and Yu-Dong Zhang2,9,* (张煜东)        

  1. 1Department of Medical Imaging, The Fourth People's Hospital of Huai'an, Huai'an 223002, China
    2School of Informatics, University of Leicester, Leicester, LE1 7RH, U.K.
    3School of Architecture Building and Civil Engineering, Loughborough University, Loughborough, LE11 3TU, U.K.
    4School of Mathematics and Actuarial Science, University of Leicester, Leicester, LE1 7RH, U.K.
    5Key Laboratory of Behavior Sciences, Institute of Psychology, Chinese Academy of Sciences, Beijing 100101, China
    6Department of Psychology, University of the Chinese Academy of Sciences, Beijing 100101, China
    7Department of Infection Diseases, The Fourth People's Hospital of Huai'an, Huai'an 223002, China
    8Department of Computer Science, Georgia State University, Atlanta 30302-5060, U.S.A.
    9Department of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia
  • Received:2020-06-03 Revised:2021-01-18 Accepted:2021-03-30 Online:2022-03-31 Published:2022-03-31
  • Contact: Yu-Dong Zhang E-mail:yudongzhang@ieee.org
  • About author:Yu-Dong Zhang received his Ph.D. degree from Southeast University, Nanjing, in 2010. He worked as a postdoc from 2010 to 2012 with Columbia University, New York, and as an assistant research scientist from 2012 to 2013 with Research Foundation of Mental Hygiene (RFMH), New York. Now he serves as a professor with University of Leicester, Leicester, UK. Prof. Zhang was the 2019 & 2021 recipient of "Web of Science Highly Cited Researcher".
  • Supported by:
    This paper was supported by the Royal Society International Exchanges Cost Share Award of UK under Grant No. RP202G0230, the Medical Research Council Confidence in Concept Award of UK under Grant No. MC_PC_17171, the Hope Foundation for Cancer Research of UK under Grant No. RM60G0680, the British Heart Foundation Accelerator Award of UK under Grant No. AA/18/3/34220, Sino-UK Industrial Fund under Grant No. RP202G0289, the Global Challenges Research Fund (GCRF) of UK under Grant No. P202PF11, the Fundamental Research Funds for the Central Universities of China under Grant No. CDLS-2020-03, the Key Laboratory of Child Development and Learning Science (Southeast University), Ministry of Education of China, Henan Key Research and Development Project of China, under Grant No. 182102310629, and the National Natural Science Foundation of China under Grant Nos. U19B2032 and 61772511.

(研究背景)COVID-19是一种传染性感染,对全球经济和我们的日常生活有严重影响。对会诊医生, 患者和放射科医师而言,(目的)准确诊断COVID-19至关重要。(方法)在本研究中,我们使用称为AlexNet的深度学习网络作为骨干,并提出两种改进:添加了批归一化以帮助加速训练,减少了内部协方差漂移;用三个随机神经网络(SNN,ELM和RVFL)替换了AlexNet中的完全连接层。因此,我们有三个新颖的深度COVID网络(DC-Net)模型,分别称为DC-Net-S,DC-Net-E和DC-Net-R。(结果)经过比较,我们发现提出的DC-Net-R在包含296张图像的私有数据集上达到90.91%的平均准确度,而特异性达到96.13%,并且在所有三个提出的分类器中表现最佳。(结论)此外证明了DC-Net-R的性能比其他现有算法要好。


关键词: 肺炎, 新冠肺炎, 卷积神经网络, Alex网, 深度学习

Abstract:

COVID-19 is a contagious infection that has severe effects on the global economy and our daily life. Accurate diagnosis of COVID-19 is of importance for consultants, patients, and radiologists. In this study, we use the deep learning network AlexNet as the backbone, and enhance it with the following two aspects: 1) adding batch normalization to help accelerate the training, reducing the internal covariance shift; 2) replacing the fully connected layer in AlexNet with three classifiers: SNN, ELM, and RVFL. Therefore, we have three novel models from the deep COVID network (DC-Net) framework, which are named DC-Net-S, DC-Net-E, and DC-Net-R, respectively. After comparison, we find the proposed DC-Net-R achieves an average accuracy of 90.91% on a private dataset (available upon email request) comprising of 296 images while the specificity reaches 96.13%, and has the best performance among all three proposed classifiers. In addition, we show that our DC-Net-R also performs much better than other existing algorithms in the literature.


Key words: pneumonia, COVID-19, convolutional neural network, AlexNet, deep learning

[1] Wang C, Horby P W, Hayden F G, Gao G F. A novel coronavirus outbreak of global health concern. The Lancet, 2020, 395(10223): 470-473. DOI: 10.1016/S0140-6736(20)30185-9.
[2] Wang D, Hu B, Hu C et al. Clinical characteristics of 138 hospitalized patients with 2019 novel coronavirus-infected pneumonia in Wuhan, China. JAMA, 2020, 323(11): 1061-1069. DOI: 10.1001/jama.2020.1585.
[3] Lu Z, Lu S Y, Liu G et al. A pathological brain detection system based on radial basis function neural network. Journal of Medical Imaging and Health Informatics, 2016, 6(5): 1218-1222. DOI: 10.1166/jmihi.2016.1901.
[4] Yang J, Qiu X, Shi J P et al. A pathological brain detection system based on kernel based ELM. Multimedia Tools and Applications, 2018, 77(3): 3715-3728. DOI: 10.1007/s11042-016-3559-z.
[5] Lu S, Qiu X, Shi J P et al. A pathological brain detection system based on extreme learning machine optimized by bat algorithm. CNS & Neurological Disorders-Drug Targets, 2017, 16(1): 23-29. DOI: 10.2174/1871527315666161019153259.
[6] Wang S H, Li P, Chen P et al. Pathological brain detection via wavelet packet Tsallis entropy and real-coded biogeography-based optimization. Fundamenta Informaticae, 2017, 151(1/2/3/4): 275-291. DOI: 10.3233/FI-2017-1492.
[7] Jiang X, Zhang Y. Chinese sign language fingerspelling recognition via six-layer convolutional neural network with leaky rectified linear units for therapy and rehabilitation. Journal of Medical Imaging and Health Informatics, 2019, 9(9): 2031-2038. DOI: 10.1166/jmihi.2019.2804.
[8] Szegedy C, Liu W, Jia Y et al. Going deeper with convolutions. In Proc. the 2015 IEEE Conference on Computer Vision and Pattern Recognition, June 2015, pp.1-9. DOI: 10.1109/CVPR.2015.7298594.
[9] Yu X, Wang S H. Abnormality diagnosis in mammograms by transfer learning based on ResNet18. Fundamenta Informaticae, 2019, 168(2/3/4): 219-230. DOI: 10.3233/FI-2019-1829.
[10] Zhang Y D, Satapathy S C, Zhu L Y et al. A seven-layer convolutional neural network for chest CT based COVID-19 diagnosis using stochastic pooling. IEEE Sensors Journal. DOI: 10.1109/JSEN.2020.3025855.
[11] Wu S, Wu X, Zhang Yet al. Diagnosis of COVID-19 by wavelet renyi entropy and three-segment biogeography-based optimization. International Journal of Computational Intelligence Systems, 2020, 13(1): 1332-1344. DOI: 10.2991/ijcis.d.200828.001.
[10] Peng H, Long F, Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1226-1238. DOI: 10.1109/TPAMI.2005.159.
[11] Chung M, Bernheim A, Mei X et al. CT imaging features of 2019 novel coronavirus (2019-nCoV). Radiology, 2020, 295(1): 202-207. DOI: 10.1148/radiol.2020200230.
[12] Maghdid H S, Ghafoor K Z, Sadiq A S et al. A novel AI-enabled framework to diagnose coronavirus COVID 19 using smartphone embedded sensors: Design study. arXiv:2003.07434, 2020. https://arxiv.org/abs/2003.07434, Dec. 2020.
[13] Wang L, Wong A. COVID-Net: A tailored deep convolutional neural network design for detection of COVID-19 cases from chest radiography images. arXiv:2003.09871, 2020. https://arxiv.org/abs/2003.09871, Dec. 2020.
[14] Al-Karawi D, Al-Zaidi S, Polus N, Jassim S. Machine learning analysis of chest CT scan images as a complementary digital test of coronavirus (COVID-19) patients. medRxiv. DOI: 10.1101/2020.04.13.20063479.
[15] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. In Proc. the 25th International Conference on Neural Information Processing Systems, December 2012, pp.1097-1105. DOI: 10.1145/3065386.
[18] Shakarami A, Tarrah H, Mahdavi-Hormat A. A CAD system for diagnosing Alzheimer's disease using 2D slices and an improved AlexNet-SVM method. Optik, 2020, 212: Article No. 164237. DOI: 10.1016/j.ijleo.2020.164237.
[19] Wang R, Xu J, Han T X. Object instance detection with pruned Alexnet and extended training data. Signal Processing: Image Communication, 2019, 70: 145-156. DOI: 10.1016/j.image.2018.09.013.
[16] Szymak P, Gasiorowski M. Using pretrained AlexNet deep learning neural network for recognition of underwater objects. Na\v{s}e More, 2020, 67(1): 9-13. DOI: 10.17818/NM/2020/1.2.
[17] Guo C J, Xu Y L, Tian Z. Inversion of PM2.5 atmospheric refractivity profile based on AlexNet model from the perspective of electromagnetic wave propagation. Environmental Science and Pollution Research, 2020, 27(30): 37333-37346. DOI: 10.1007/s11356-020-07703-w.
[18] Zhao X Y, Dong C Y, Zhou P, Zhu M J, Ren J W, Chen X Y. Detecting surface defects of wind tubine blades using an Alexnet deep learning algorithm. IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences, 2019, E102A(12): 1817-1824. DOI: 10.1587/transfun.E102.A.1817.
[19] Xiao L, Yan Q, Deng S. Scene classification with improved AlexNet model. In Proc. the 12th International Conference on Intelligent Systems and Knowledge Engineering, Nov. 2017. DOI: 10.1109/ISKE.2017.8258820.
[20] Rakitianskaia A, Engelbrecht A. Measuring saturation in neural networks. In Proc. the 2015 IEEE Symposium Series on Computational Intelligence, Dec. 2015, pp.1423-1430. DOI: 10.1109/SSCI.2015.202.
[21] Gertych A, Swiderska-Chadaj Z, Ma Z et al. Convolutional neural networks can accurately distinguish four histologic growth patterns of lung adenocarcinoma in digital slides. Sci. Rep., 2019, 9(1): Article No. 1483. DOI: 10.1038/s41598-018-37638-9.
[22] Fukae J, Isobe M, Hattori T et al. Convolutional neural network for classification of two-dimensional array images generated from clinical information may support diagnosis of rheumatoid arthritis. Sci. Rep., 2020, 10(1): Article No. 5648. DOI: 10.1038/s41598-020-62634-3.
[23] Nguyen H D, Lloyd-Jones L R, McLachlan G J. A universal approximation theorem for mixture-of-experts models. Neural Computation, 2016, 28(12): 2585-2593. DOI: 10.1162/NECO_a_00892.
[24] Huang Y, Yang D, Wang K, Wang L, Fan J. A quality diagnosis method of GMAW based on improved empirical mode decomposition and extreme learning machine. Journal of Manufacturing Processes, 2020, 54: 120-128. DOI: 10.1016/j.jmapro.2020.03.006.
[25] Schmidt W F, Kraaijveld M A, Duin R P W. Feedforward neural networks with random weights. In Proc. the 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Aug. 30-Sept. 3, 1992. DOI: 10.1109/ICPR.1992.201708.
[26] Pao Y H, Park G H, Sobajic D J. Learning and generalization characteristics of the random vector functional-link net. Neurocomputing, 1994, 6(2): 163-180. DOI: 10.1016/0925-2312(94)90053-1.
[27] Kushwah G S, Ranga V. Voting extreme learning machine based distributed denial of service attack detection in cloud computing. Journal of Information Security and Applications, 2020, 53: Article No. 102532. DOI: 10.1016/j.jisa.2020.102532.
[28] Yager R R, Kreinovich V. Universal approximation theorem for uninorm-based fuzzy systems modeling. Fuzzy Sets and Systems, 2003, 140(2): 331-339. DOI: 10.1016/S0165-0114(02)00521-3.
[29] Scardapane S, Fierimonte R, Wang D H, Panella M, Uncini A. Distributed music classification using random vector functional-link nets. In Proc. the 2015 International Joint Conference on Neural Networks, July 2015. DOI: 10.1109/IJCNN.2015.7280333.
[30] Chaudhuri A. The minimization of empirical risk through stochastic gradient descent with momentum algorithms. In Proc. the 8th Computer Science On-line Conference on Artificial Intelligence Methods in Intelligent Algorithms, April 2019, pp.168-181. DOI: 10.1007/978-3-030-19810-7_17.
[31] Dean J, Corrado G, Monga R et al. Large scale distributed deep networks. In Proc. the 25th International Conference on Neural Information Processing Systems, December 2012, pp.1223-1231.
[32] Rajaraman S, Candemir S, Kim I, Thoma G, Antani S. Visualization and interpretation of convolutional neural network predictions in detecting pneumonia in pediatric chest radiographs. Applied Sciences, 2018, 8(10): Article No. 1715. DOI: 10.3390/app8101715.
[33] Ardila D, Kiraly A P, Bharadwaj S et al. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nature Medicine, 2019, 25(6): 954-961. DOI: 10.1038/s41591-019-0447-x.
[34] Chae K J, Jin G Y, Ko S B, Wang Y, Zhang H, Choi E J, Choi H. Deep learning for the classification of small (≤2 cm) pulmonary nodules on CT imaging: A preliminary study. Acad. Radiol., 2020, 27(4): e55-e63. DOI: 10.1016/j.acra.2019.05.018.
[35] Koo H J, Lim S, Choe J, Choi S H, Sung H, Do K H. Radiographic and CT features of viral pneumonia. RadioGraphics, 2018, 38(3): 719-739. DOI: 10.1148/rg.2018170048.
[1] 魏华鹏, 邓盈盈, 唐帆, 潘兴甲, 董未名. 基于卷积神经网络和Transformer的视觉风格迁移的比较研究[J]. 计算机科学技术学报, 2022, 37(3): 601-614.
[2] Shao-Jie Qiao, Guo-Ping Yang, Nan Han, Hao Chen, Fa-Liang Huang, Kun Yue, Yu-Gen Yi, Chang-An Yuan. 基数估计器:利用垂直扫描卷积神经网络处理SQL[J]. 计算机科学技术学报, 2021, 36(4): 762-777.
[3] Yang Liu, Ruili He, Xiaoqian Lv, Wei Wang, Xin Sun, Shengping Zhang. 婴儿的年龄和性别容易被识别吗?[J]. 计算机科学技术学报, 2021, 36(3): 508-519.
[4] Zhang-Jin Huang, Xiang-Xiang He, Fang-Jun Wang, Qing Shen. 基于卷积神经网络的实时多阶段斑马鱼头部姿态估计框架[J]. 计算机科学技术学报, 2021, 36(2): 434-444.
[5] 梁盾, 郭元晨, 张少魁, 穆太江, 黄晓蕾. 车道检测-新结果和调查研究[J]. 计算机科学技术学报, 2020, 35(3): 493-505.
[6] Jin-Gong Jia, Yuan-Feng Zhou, Xing-Wei Hao, Feng Li, Christian Desrosiers, Cai-Ming Zhang. 双流时间卷积神经网络用于基于骨架的人体动作识别[J]. 计算机科学技术学报, 2020, 35(3): 538-550.
[7] Rui-Song Zhang, Wei-Ze Quan, Lu-Bin Fan, Li-Ming Hu, Dong-Ming Yan. 基于通道和像素相关性的计算机生成图像与自然图像鉴别[J]. 计算机科学技术学报, 2020, 35(3): 592-602.
[8] Robail Yasrab. SRNET:用于解析奇点的基于浅跳跃连接的卷积神经网络[J]. 计算机科学技术学报, 2019, 34(4): 924-938.
[9] Ri-Sheng Liu, Cai-Sheng Mao, Zhi-Hui Wang, Hao-Jie Li. 基于灵活稀疏结构控制和自适应优化算法的模糊图像盲复原[J]. 计算机科学技术学报, 2019, 34(3): 609-621.
[10] Han Liu, Hang Du, Dan Zeng, Qi Tian. 基于超像素分类和语义分割的云检测算法[J]. 计算机科学技术学报, 2019, 34(3): 622-633.
[11] Dong-Di Zhao, Fan Li, Kashif Sharif, Guang-Min Xia, Yu Wang. 深度卷积神经网络的空间高效量化[J]. 计算机科学技术学报, 2019, 34(2): 305-317.
[12] Tie-Ke He, Hao Lian, Ze-Min Qin, Zhen-Yu Chen, Bin Luo. 一种用于罚金判定的主题模型[J]. , 2018, 33(4): 756-767.
[13] Bei-Ji Zou, Yun-Di Guo, Qi He, Ping-Bo Ouyang, Ke Liu, Zai-Liang Chen. 基于块匹配三维滤波和卷积神经网络的图像去噪[J]. , 2018, 33(4): 838-848.
[14] Zhi-Feng Xie, Yu-Chen Guo, Shu-Han Zhang, Wen-Jun Zhang, Li-Zhuang Ma. 基于深度卷积网络的多重曝光运动估计[J]. , 2018, 33(3): 487-501.
[15] Nai-Ming Yao, Hui Chen, Qing-Pei Guo, Hong-An Wang. 使用一种基于Depth-Patch的深度神经网络的非正面人脸表情识别[J]. , 2017, 32(6): 1172-1185.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] . Online First Under Construction [J]. 计算机科学技术学报, 0, (): 1 .
[2] Zhi-Neng Chen, Chong-Wah Ngo, Wei Zhang, Juan Cao, Yu-Gang Jiang. 网络视频人脸—姓名关联:大规模数据库,基准实验和开放性问题[J]. , 2014, 29(5): 785 -798 .
[3] Fei Xia, De-Jun Jiang, Jin Xiong, Ning-Hui Sun. PCM内存系统研究综述[J]. , 2015, 30(1): 121 -144 .
[4] Jian-Qiu Xu, Ralf Hartmut Güting, Yu Zheng, Ouri Wolfson. 具有运动方式的移动对象研究综述[J]. 计算机科学技术学报, 2019, 34(4): 709 -726 .
[5] André Brinkmann, Kathryn Mohror, Weikuan Yu, Philip Carns, Toni Cortes, Scott A. Klasky, Alberto Miranda, Franz-Josef Pfreundt, Robert B. Ross, Marc-André Vef. 高性能计算专用文件系统[J]. 计算机科学技术学报, 2020, 35(1): 4 -26 .
[6] Yu-Tong Lu, Peng Cheng, Zhi-Guang Chen. Tianhe-2数据存储与管理系统设计与实现[J]. 计算机科学技术学报, 2020, 35(1): 27 -46 .
[7] Reza Jafari Ziarani, Reza Ravanmehr. 推荐系统中的意外效应:系统文献综述[J]. 计算机科学技术学报, 2021, 36(2): 375 -396 .
[8] Bo-Han Li, Yi Liu, An-Man Zhang, Wen-Huan Wang, Shuo Wan. 实体消解中分块技术的综述[J]. 计算机科学技术学报, 2020, 35(4): 769 -793 .
[9] Lie-Huang Zhu, Bao-Kun Zheng, Meng Shen, Feng Gao, Hong-Yu Li, Ke-Xin Shi. 比特币系统的数据安全和隐私综述[J]. 计算机科学技术学报, 2020, 35(4): 843 -862 .
[10] 梁盾, 郭元晨, 张少魁, 穆太江, 黄晓蕾. 车道检测-新结果和调查研究[J]. 计算机科学技术学报, 2020, 35(3): 493 -505 .
版权所有 © 《计算机科学技术学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn
总访问量: