TY - JOUR
T1 - Diagnosis of COVID-19 Pneumonia via a Novel Deep Learning Architecture
AU - Zhang, Xin
AU - Lu, Siyuan
AU - Wang, Shui Hua
AU - Yu, Xiang
AU - Wang, Su Jing
AU - Yao, Lun
AU - Pan, Yi
AU - Zhang, Yu Dong
N1 - Publisher Copyright:
© 2022, Institute of Computing Technology, Chinese Academy of Sciences.
PY - 2022/4
Y1 - 2022/4
N2 - 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.
AB - 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.
KW - AlexNet
KW - COVID-19
KW - convolutional neural network
KW - deep learning
KW - pneumonia
UR - http://www.scopus.com/inward/record.url?scp=85105864585&partnerID=8YFLogxK
U2 - 10.1007/s11390-020-0679-8
DO - 10.1007/s11390-020-0679-8
M3 - Article
AN - SCOPUS:85105864585
SN - 1000-9000
VL - 37
SP - 330
EP - 343
JO - Journal of Computer Science and Technology
JF - Journal of Computer Science and Technology
IS - 2
ER -