[introductory/intermediate] Convolutional Neural Networks and Their Applications to COVID-19 Diagnosis
This lecture will briefly introduce convolutional neural networks (CNNs) and their application to COVID-19. Traditional convolution, pooling, and fully connected layers shall be introduced. The neuroscience mechanism under CNN shall be discussed. Several typical convolutional neural networks shall be analyzed and compared, including pretrained models, graph convolutional networks, attention neural networks, etc. State-of-the-art CNN-based algorithms for COVID-19 will be analyzed.
- Part I: ImageNet and ILSVRC, Convolutional neural network, Convolution layers, pooling layer, Drop out; Batch normalization; data augmentation
- Part II: Neuroscientific basis, Random search, Bayesian Optimization, LeNet, Transfer learning, AlexNet, VGG, GoogleNet, ResNet, DenseNet
- Part III: Background of COVID-19, chest imaging, graph convolutional network, attention neural network, web apps of COVID-19 diagnosis
- Deng, J., W. Dong, R. Socher, L. J. Li, L. Kai, and F.-F. Li (2009). ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition. 248-255.
- Ioffe, S. and C. Szegedy (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167.
- Krizhevsky, A., I. Sutskever, and G. E. Hinton (2012). ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems. 1097-1105.
- Simonyan, K. and A. Zisserman (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
- Szegedy, C., W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich (2015). Going deeper with convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.
- He, K., X. Zhang, S. Ren, and J. Sun (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770-778.
- Goodfellow, I., Y. Bengio, A. Courville, and Y. Bengio (2016). Deep learning, MIT Press, Cambridge.
- Kipf, T. N., & Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.
- Huang, Gao, et al. (2017). Densely connected convolutional networks. CVPR. Vol. 1. No. 2.
- Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). CBAM: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV) (pp. 3-19).
- Wang, S., et al. (2021), Covid-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network, Information Fusion, 67: 208-229.
Linear Algebra and Calculus, Probability and Statistics, Basics of Image Processing, Pattern Recognition, and Computer Vision.
Prof. Yu-Dong Zhang serves as Professor with School of Computing and Mathematical Sciences, University of Leicester, UK. His research interests include deep learning and medical image analysis. He is the Fellow of IET (FIET), and Senior Member of IEEE, IES, and ACM. He was the 2019 recipient of Web of Science Highly Cited Researcher. He is included in “Top Scientist” in Guide2Research. He is the author of over 300 peer-reviewed articles, including more than 50 ESI Highly Cited Papers, and 4 ESI Hot Papers.