Covid-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network

Shui Hua Wang, Vishnu Varthanan Govindaraj, Juan Manuel Górriz*, Xin Zhang, Yu Dong Zhang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

272 Citations (Scopus)

Abstract

(Aim) COVID-19 is an infectious disease spreading to the world this year. In this study, we plan to develop an artificial intelligence based tool to diagnose on chest CT images. (Method) On one hand, we extract features from a self-created convolutional neural network (CNN) to learn individual image-level representations. The proposed CNN employed several new techniques such as rank-based average pooling and multiple-way data augmentation. On the other hand, relation-aware representations were learnt from graph convolutional network (GCN). Deep feature fusion (DFF) was developed in this work to fuse individual image-level features and relation-aware features from both GCN and CNN, respectively. The best model was named as FGCNet. (Results) The experiment first chose the best model from eight proposed network models, and then compared it with 15 state-of-the-art approaches. (Conclusion) The proposed FGCNet model is effective and gives better performance than all 15 state-of-the-art methods. Thus, our proposed FGCNet model can assist radiologists to rapidly detect COVID-19 from chest CT images.

Original languageEnglish
Pages (from-to)208-229
Number of pages22
JournalInformation Fusion
Volume67
DOIs
Publication statusPublished - Mar 2021
Externally publishedYes

Keywords

  • Batch normalization
  • Convolutional neural network
  • Deep feature fusion
  • Dropout
  • Graph convolutional network
  • Multiple-way data augmentation
  • Rank-based average pooling

Fingerprint

Dive into the research topics of 'Covid-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network'. Together they form a unique fingerprint.

Cite this