| Abstract: | Convolution Neural Networks (CNN) can quickly diagnose COVID-19 patients by analyzing computed tomography (CT) images of the lung, thereby effectively preventing the spread of COVID-19. However, the existing CNN-based COVID-19 diagnosis models do consider the problem that the lung images of COVID-19 patients in the early stage and incubation period are extremely similar to those of the non-COVID-19 population. Which reduces the model’s classification sensitivity, resulting in a higher probability of the model misdiagnosing COVID-19 patients as non-COVID-19 people. To solve the problem, this paper first attempts to apply triplet loss and center loss to the field of COVID-19 image classification, combining softmax loss to design a jointly supervised metric loss function COVID Triplet-Center Loss (COVID-TCL). Triplet loss can increase inter-class discreteness, and center loss can improve intra-class compactness. Therefore, COVID-TCL can help the CNN-based model to extract more discriminative features and strengthen the diagnostic capacity of COVID-19 patients in the early stage and incubation period. Meanwhile, we use the extreme gradient boosting (XGBoost) as a classifier to design a COVID-19 images classification model of CNN-XGBoost architecture, to further improve the CNN-based model’s classification effect and operation efficiency. The experiment shows that the classification accuracy of the model proposed in this paper is 97.41%, and the sensitivity is 97.61%, which is higher than the other 7 reference models. The COVID-TCL can effectively improve the classification sensitivity of the CNN-based model, the CNN-XGBoost architecture can further improve the CNN-based model’s classification effect. |
