COVID-Nets: Deep CNN Architectures for Detecting COVID-19 Using Chest CT Scans
作者： Martinetz T , Barth E , Alshazly H , Alshazly H , Linse C
DOI: 10.1101/2021.04.19.21255763
关键词: Chest ct 、 Deep cnn 、 Coronavirus disease 2019 (COVID-19) 、 Pattern recognition 、 Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) 、 Sensitivity (control systems) 、 Convolutional neural network 、 Residual 、 Binary classification 、 Artificial intelligence 、 Computer science
摘要: This paper introduces two novel deep convolutional neural network (CNN) architectures for automated detection of COVID-19. The first model, CovidResNet, is inspired by the residual (ResNet) architecture. second CovidDenseNet, exploits power densely connected networks (DenseNet). proposed are designed to provide fast and accurate diagnosis COVID-19 using computed tomography (CT) images multi-class binary classification tasks. utilized in a experimental study on SARS-CoV-2 CT-scan dataset, which contains 4173 CT 210 subjects structured subject-wise manner three different classes. First, we train test differentiate COVID-19, non-COVID-19 viral infections, healthy. Second, with scenarios: vs. healthy, other pneumonia, pneumonia Our models achieve up 93.96% accuracy, 99.13% precision, 94% sensitivity, 97.73% specificity, 95.80% F1-score classification, 83.89% 80.36% 82% 92% 81% three-class results reveal validity effectiveness detection. also outperform baseline ResNet DenseNet while being more efficient.
sci-hub.st 参考文章(58)
Geoffrey E. Hinton, Vinod Nair, Rectified Linear Units Improve Restricted Boltzmann Machines international conference on machine learning. pp. 807- 814 ,(2010)
Philipp Fischer, Thomas Brox, None, U-Net: Convolutional Networks for Biomedical Image Segmentation medical image computing and computer assisted intervention. pp. 234- 241 ,(2015) , 10.1007/978-3-319-24574-4_28
M Sai Praneeth, Xudong Peng, Alice Li, Shahrzad Hosseini Vajargah, Going deeper with convolutions computer vision and pattern recognition. pp. 1- 9 ,(2015) , 10.1109/CVPR.2015.7298594
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei, ImageNet: A large-scale hierarchical image database computer vision and pattern recognition. pp. 248- 255 ,(2009) , 10.1109/CVPR.2009.5206848
Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, Li Fei-Fei, ImageNet Large Scale Visual Recognition Challenge International Journal of Computer Vision. ,vol. 115, pp. 211- 252 ,(2015) , 10.1007/S11263-015-0816-Y
Ilya Sutskever, Geoffrey E. Hinton, Alex Krizhevsky, ImageNet Classification with Deep Convolutional Neural Networks neural information processing systems. ,vol. 25, pp. 1097- 1105 ,(2012)
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep Residual Learning for Image Recognition computer vision and pattern recognition. pp. 770- 778 ,(2016) , 10.1109/CVPR.2016.90
Christian Szegedy, Sergey Ioffe, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift arXiv: Learning. ,(2015)
Karen Simonyan, Andrew Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition international conference on learning representations. ,(2015)
Fausto Milletari, Nassir Navab, Seyed-Ahmad Ahmadi, V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation international conference on 3d vision. pp. 565- 571 ,(2016) , 10.1109/3DV.2016.79