Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Apr 20;13(8):1484.
doi: 10.3390/diagnostics13081484.

COVID-19 Diagnosis in Computerized Tomography (CT) and X-ray Scans Using Capsule Neural Network

Andronicus A Akinyelu  1   2 , Bubacarr Bah  1   3
Affiliations

COVID-19 Diagnosis in Computerized Tomography (CT) and X-ray Scans Using Capsule Neural Network

Andronicus A Akinyelu et al. Diagnostics (Basel). .

Abstract

This study proposes a deep-learning-based solution (named CapsNetCovid) for COVID-19 diagnosis using a capsule neural network (CapsNet). CapsNets are robust for image rotations and affine transformations, which is advantageous when processing medical imaging datasets. This study presents a performance analysis of CapsNets on standard images and their augmented variants for binary and multi-class classification. CapsNetCovid was trained and evaluated on two COVID-19 datasets of CT images and X-ray images. It was also evaluated on eight augmented datasets. The results show that the proposed model achieved classification accuracy, precision, sensitivity, and F1-score of 99.929%, 99.887%, 100%, and 99.319%, respectively, for the CT images. It also achieved a classification accuracy, precision, sensitivity, and F1-score of 94.721%, 93.864%, 92.947%, and 93.386%, respectively, for the X-ray images. This study presents a comparative analysis between CapsNetCovid, CNN, DenseNet121, and ResNet50 in terms of their ability to correctly identify randomly transformed and rotated CT and X-ray images without the use of data augmentation techniques. The analysis shows that CapsNetCovid outperforms CNN, DenseNet121, and ResNet50 when trained and evaluated on CT and X-ray images without data augmentation. We hope that this research will aid in improving decision making and diagnostic accuracy of medical professionals when diagnosing COVID-19.

Keywords: COVID-19 diagnosis; CT scans; capsule neural network; machine learning; medical imaging.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
The proposed CapsNet architecture (CapsNetCovid).
Figure 2
Figure 2
Samples of standard and augmented CT images used for training.
Figure 3
Figure 3
Samples of standard and augmented X-ray images used for training.
Figure 4
Figure 4
CapsNetCovid training and validation performance.
Figure 5
Figure 5
CapsNet ROC curves for CT images.
Figure 6
Figure 6
CNN training and validation performance.
Figure 7
Figure 7
DenseNet121 training and validation performance.
Figure 8
Figure 8
ResNet50 training and validation performance.
Figure 9
Figure 9
CNN ROC curves for CT images.
Figure 10
Figure 10
DesNet121 ROC curves for CT images.
Figure 11
Figure 11
ResNet50 ROC curves for CT images.
Figure 12
Figure 12
CapsNet training and validation performance for X-ray images.
Figure 13
Figure 13
CapsNet ROC curves for X-ray images.
Figure 14
Figure 14
CNN training and validation performance for X-ray images.
Figure 15
Figure 15
DenseNet121 training and validation performance for X-ray images.
Figure 16
Figure 16
ResNet50 training and validation performance for X-ray images.
Figure 17
Figure 17
CNN ROC curves for X-ray images.
Figure 18
Figure 18
DesNet121 ROC curves for X-ray images.
Figure 19
Figure 19
ResNet50 ROC curves for X-ray images.
See this image and copyright information in PMC

References

    1. Akinyelu A.A., Blignaut P. COVID-19 diagnosis using deep learning neural networks applied to CT images. Front. Artif. Intell. 2022;5:919672. doi: 10.3389/frai.2022.919672. - DOI - PMC - PubMed
    1. Sabour S., Frosst N., Hinton G.E. Dynamic routing between capsules. arXiv. 20171710.09829
    1. LaLonde R., Bagci U. Capsules for object segmentation. arXiv. 20181804.04241
    1. AbouEl-Magd L.M., Darwish A., Snasel V., Hassanien A.E. A pre-trained convolutional neural network with optimized capsule networks for chest X-rays COVID-19 diagnosis. Cluster Comput. 2022;26:1389–1403. doi: 10.1007/s10586-022-03703-2. - DOI - PMC - PubMed
    1. Chawla N.V., Bowyer K.W., Hall L.O., Kegelmeyer W.P. SMOTE: Synthetic minority over-sampling technique. J. Artif. Intell. Res. 2002;16:321–357. doi: 10.1613/jair.953. - DOI

LinkOut - more resources