TY - JOUR
T1 - An explainable framework for diagnosis of COVID-19 pneumonia via transfer learning and discriminant correlation analysis
AU - Lu, Siyuan
AU - Wu, Di
AU - Zhang, Zheng
AU - Wang, Shui Hua
N1 - Publisher Copyright:
© 2021 Association for Computing Machinery.
PY - 2021/10
Y1 - 2021/10
N2 - The new coronavirus COVID-19 has been spreading all over the world in the last six months, and the death toll is still rising. The accurate diagnosis of COVID-19 is an emergent task as to stop the spreading of the virus. In this paper, we proposed to leverage image feature fusion for the diagnosis of COVID-19 in lung window computed tomography (CT). Initially, ResNet-18 and ResNet-50 were selected as the backbone deep networks to generate corresponding image representations from the CT images. Second, the representative information extracted from the two networks was fused by discriminant correlation analysis to obtain refined image features. Third, three randomized neural networks (RNNs): extreme learning machine, Schmidt neural network and random vector functional-link net, were trained using the refined features, and the predictions of the three RNNs were ensembled to get a more robust classification performance. Experiment results based on five-fold cross validation suggested that our method outperformed state-of-the-art algorithms in the diagnosis of COVID-19.
AB - The new coronavirus COVID-19 has been spreading all over the world in the last six months, and the death toll is still rising. The accurate diagnosis of COVID-19 is an emergent task as to stop the spreading of the virus. In this paper, we proposed to leverage image feature fusion for the diagnosis of COVID-19 in lung window computed tomography (CT). Initially, ResNet-18 and ResNet-50 were selected as the backbone deep networks to generate corresponding image representations from the CT images. Second, the representative information extracted from the two networks was fused by discriminant correlation analysis to obtain refined image features. Third, three randomized neural networks (RNNs): extreme learning machine, Schmidt neural network and random vector functional-link net, were trained using the refined features, and the predictions of the three RNNs were ensembled to get a more robust classification performance. Experiment results based on five-fold cross validation suggested that our method outperformed state-of-the-art algorithms in the diagnosis of COVID-19.
KW - COVID-19
KW - Computed tomography
KW - Extreme learning machine
KW - Random vector functional-link net
KW - Randomized neural network
KW - ResNet
KW - Schmidt neural network
UR - http://www.scopus.com/inward/record.url?scp=85122619581&partnerID=8YFLogxK
U2 - 10.1145/3449785
DO - 10.1145/3449785
M3 - Article
AN - SCOPUS:85122619581
SN - 1551-6857
VL - 17
JO - ACM Transactions on Multimedia Computing, Communications and Applications
JF - ACM Transactions on Multimedia Computing, Communications and Applications
IS - 3s
M1 - 3449785
ER -