A five-layer deep convolutional neural network with stochastic pooling for chest CT-based COVID-19 diagnosis

Till August 17, 2020, COVID-19 has caused 21.59 million confirmed cases in more than 227 countries and territories, and 26 naval ships. Chest CT is an effective way to detect COVID-19. This study proposed a novel deep learning model that can diagnose COVID-19 on chest CT more accurately and swiftly. Based on traditional deep convolutional neural network (DCNN) model, we proposed three improvements: (i) We introduced stochastic pooling to replace average pooling and max pooling; (ii) We combined conv layer with batch normalization layer and obtained the conv block (CB); (iii) We combined dropout layer with fully connected layer and obtained the fully connected block (FCB). Our algorithm achieved a sensitivity of 93.28% ± 1.50%, a specificity of 94.00% ± 1.56%, and an accuracy of 93.64% ± 1.42%, in identifying COVID-19 from normal subjects. We proved using stochastic pooling yields better performance than average pooling and max pooling. We compared different structure configurations and proved our 3CB + 2FCB yields the best performance. The proposed model is effective in detecting COVID-19 based on chest CT images.

[1]  H. Kunishima,et al.  Development of a protective device for RT-PCR testing SARS-CoV-2 in COVID-19 patients , 2020, Infection Control & Hospital Epidemiology.

[2]  Yi Chen,et al.  Fruit category classification via an eight-layer convolutional neural network with parametric rectified linear unit and dropout technique , 2018, Multimedia Tools and Applications.

[3]  Sidan Du,et al.  Multi-objective path finding in stochastic networks using a biogeography-based optimization method , 2016, Simul..

[4]  Ming Yang,et al.  Sensorineural hearing loss identification via nine-layer convolutional neural network with batch normalization and dropout , 2018, Multimedia Tools and Applications.

[5]  Angham G. Hadi,et al.  A Review on COVID-19: Origin, Spread, Symptoms, Treatment, and Prevention , 2020 .

[6]  Aijun Liu,et al.  Tea Category Identification using Computer Vision and Generalized Eigenvalue Proximal SVM , 2017, Fundam. Informaticae.

[7]  Yu-Dong Zhang,et al.  Chinese Sign Language Fingerspelling via Six-Layer Convolutional Neural Network with Leaky Rectified Linear Units for Therapy and Rehabilitation , 2019, J. Medical Imaging Health Informatics.

[8]  Sidan Du,et al.  Application of stationary wavelet entropy in pathological brain detection , 2018, Multimedia Tools and Applications.

[9]  Jwan K. Alwan,et al.  Role of biological Data Mining and Machine Learning Techniques in Detecting and Diagnosing the Novel Coronavirus (COVID-19): A Systematic Review , 2020, Journal of Medical Systems.

[10]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Zhiwen Yu,et al.  KNN-BLOCK DBSCAN: Fast Clustering for Large-Scale Data , 2021, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[12]  Jie Liu,et al.  Classification of cerebral microbleeds based on fully-optimized convolutional neural network , 2018, Multimedia Tools and Applications.

[13]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[14]  Yudong Zhang,et al.  A Pathological Brain Detection System based on Extreme Learning Machine Optimized by Bat Algorithm. , 2017, CNS & neurological disorders drug targets.

[15]  Ming Yang,et al.  A pathological brain detection system based on kernel based ELM , 2016, Multimedia Tools and Applications.

[16]  Sengul Dogan,et al.  An automated Residual Exemplar Local Binary Pattern and iterative ReliefF based COVID-19 detection method using chest X-ray image , 2020, Chemometrics and Intelligent Laboratory Systems.

[17]  Xiang Yu,et al.  Abnormality Diagnosis in Mammograms by Transfer Learning Based on ResNet18 , 2019, Fundam. Informaticae.

[18]  Q. Tao,et al.  Correlation of Chest CT and RT-PCR Testing in Coronavirus Disease 2019 (COVID-19) in China: A Report of 1014 Cases , 2020, Radiology.

[19]  Luis Peñarrubia,et al.  Multiple assays in a real-time RT-PCR SARS-CoV-2 panel can mitigate the risk of loss of sensitivity by new genomic variants during the COVID-19 outbreak , 2020, International Journal of Infectious Diseases.

[20]  Ning Cui,et al.  Preliminary CT findings of coronavirus disease 2019 (COVID-19) , 2020, Clinical Imaging.

[21]  Shuihua Wang,et al.  RGB-D image-based detection of stairs, pedestrian crosswalks and traffic signs , 2014, J. Vis. Commun. Image Represent..

[22]  Xin Liu,et al.  Fast density peak clustering for large scale data based on kNN , 2020, Knowl. Based Syst..

[23]  Huimin Lu,et al.  Multiple Sclerosis Detection Based on Biorthogonal Wavelet Transform, RBF Kernel Principal Component Analysis, and Logistic Regression , 2016, IEEE Access.

[24]  Oge Marques,et al.  Dropout vs. batch normalization: an empirical study of their impact to deep learning , 2020, Multimedia Tools and Applications.

[25]  Ming Yang,et al.  Classification of Alzheimer’s Disease Based on Eight-Layer Convolutional Neural Network with Leaky Rectified Linear Unit and Max Pooling , 2018, Journal of Medical Systems.

[26]  A. Polimeni,et al.  Coronavirus Disease (COVID-19): A Machine Learning Bibliometric Analysis. , 2020, In vivo.

[27]  L. Xia,et al.  Coronavirus Disease 2019 (COVID-19): Role of Chest CT in Diagnosis and Management. , 2020, AJR. American journal of roentgenology.

[28]  Sidan Du,et al.  Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average Pooling , 2017, IEEE Access.

[29]  Yudong Zhang,et al.  A Pathological Brain Detection System Based on Radial Basis Function Neural Network , 2016 .