COVID-19 Pneumonia Classification Based on NeuroWavelet Capsule Network

Abstract

Since it was first reported, coronavirus disease 2019, also known as COVID-19, has spread expeditiously around the globe. COVID-19 must be diagnosed as soon as possible in order to control the disease and provide proper care to patients. The chest X-ray (CXR) has been identified as a useful diagnostic tool, but the disease outbreak has put a lot of pressure on radiologists to read the scans, which could give rise to fatigue-related misdiagnosis. Automatic classification algorithms that are reliable can be extremely beneficial; however, they typically depend upon a large amount of COVID-19 data for training, which are troublesome to obtain in the nick of time. Therefore, we propose a novel method for the classification of COVID-19. Concretely, a novel neurowavelet capsule network is proposed for COVID-19 classification. To be more precise, first, we introduce a multi-resolution analysis of a discrete wavelet transform to filter noisy and inconsistent information from the CXR data in order to improve the feature extraction robustness of the network. Secondly, the discrete wavelet transform of the multi-resolution analysis also performs a sub-sampling operation in order to minimize the loss of spatial details, thereby enhancing the overall classification performance. We examined the proposed model on a public-sourced dataset of pneumonia-related illnesses, including COVID-19 confirmed cases and healthy CXR images. The proposed method achieves an accuracy of 99.6%, sensitivity of 99.2%, specificity of 99.1% and precision of 99.7%. Our approach achieves an up-to-date performance that is useful for COVID-19 screening according to the experimental results. This latest paradigm will contribute significantly in the battle against COVID-19 and other diseases.

Keywords: COVID-19; capsule network; chest X-ray; convolutional neural network; pneumonia; wavelet.

Figure 1

Our proposed neurowavelet capsule network for COVID-19 classification (NW-CapsNet).

Figure 2

Data description of different pneumonia diseases, including COVID-19.

Figure 3

Comparison report of our model and selected pre-trained models. (a) Sensitivity result of the pre-trained models, including our proposed NW-CapsNet model. (b) Specificity result showing that our proposed model outperforms the selected pre-trained models.

Figure 4

Training and validation curves for the proposed model. (a) Accuracy curve showing the performance of our proposed NW-CapsNet model. (b) The loss curve of our proposed NW-CapsNet model showing the stability of our model.

Figure 5

Training and validation curves for the proposed model with different down-sampling operations. (a) Accuracy curves showing the influence of the choice of down-sampling operation on the overall performance of the model. (b) The loss curves for our proposed model showing the influence of the choice of down-sampling operation.

Figure 6

Effect of down-sampling operation on the performance of the proposed model. (a) Precision–recall curves of our two stage experiments showing the influence of down-sampling operation on the model performance. (b) ROC curve of our two stage experiments showing the influence of down-sampling operation on the model performance.

Figure 7

Performance comparison with state-of-the-art models. (a) Precision–recall curves of our proposed NW-CapsNet model in comparison to some state-of-the-art COVID-19 methods. (b) ROC curve of our proposed NW-CapsNet model in comparison to some state-of-the-art COVID-19 methods.

Figure 8

Performance comparison with state-of-the-art models. (a) Precision–recall curves of our proposed NW-CapsNet model in comparison to some selected pre-trained deep learning models. (b) ROC curve of our proposed NW-CapsNet model in comparison to some selected pre-trained deep learning models.