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
. 2024 Jan 29:6:1235204.
doi: 10.3389/frai.2023.1235204. eCollection 2023.

COVID-19 lateral flow test image classification using deep CNN and StyleGAN2

Vishnu Pannipulath Venugopal  1 , Lakshmi Babu Saheer  1 , Mahdi Maktabdar Oghaz  1
Affiliations

COVID-19 lateral flow test image classification using deep CNN and StyleGAN2

Vishnu Pannipulath Venugopal et al. Front Artif Intell. .

Abstract

Introduction: Artificial intelligence (AI) in healthcare can enhance clinical workflows and diagnoses, particularly in large-scale operations like COVID-19 mass testing. This study presents a deep Convolutional Neural Network (CNN) model for automated COVID-19 RATD image classification.

Methods: To address the absence of a RATD image dataset, we crowdsourced 900 real-world images focusing on positive and negative cases. Rigorous data augmentation and StyleGAN2-ADA generated simulated images to overcome dataset limitations and class imbalances.

Results: The best CNN model achieved a 93% validation accuracy. Test accuracies were 88% for simulated datasets and 82% for real datasets. Augmenting simulated images during training did not significantly improve real-world test image performance but enhanced simulated test image performance.

Discussion: The findings of this study highlight the potential of the developed model in expediting COVID-19 testing processes and facilitating large-scale testing and tracking systems. The study also underscores the challenges in designing and developing such models, emphasizing the importance of addressing dataset limitations and class imbalances.

Conclusion: This research contributes to the deployment of large-scale testing and tracking systems, offering insights into the potential applications of AI in mitigating outbreaks similar to COVID-19. Future work could focus on refining the model and exploring its adaptability to other healthcare scenarios.

Keywords: SARS-CoV-2; StyleGAN2; convolutional neural network; deep learning; lateral flow test; transfer learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Healgen rapid antigen test device.
Figure 2
Figure 2
Examples of negative image (up) and positive image samples (down).
Figure 3
Figure 3
CNN architecture.
Figure 4
Figure 4
Model A experiment results for 224X224 resolution (top), 200 × 200 resolution (middle), and 128 × 128 resolution (bottom).
Figure 5
Figure 5
Model B experiment results for 224 × 224 resolution (top), 200 × 200 resolution (middle), and 128 × 128 resolution (bottom).
Figure 6
Figure 6
Model C experiment results comparing accuracy and loss of training and validation data for model C.
Figure 7
Figure 7
Model D experiment results for 224 × 224 resolution (top), 200 × 200 resolution (middle), and 128 × 128 resolution (bottom).
Figure 8
Figure 8
Model E experiment results for 224 × 224 resolution (top), 200 × 200 resolution (middle), and 128 × 128 resolution (bottom).
Figure 9
Figure 9
Fake images generated by StyleGAN2-ADA at kimg 161 (top) and StyleGAN2-ADA at kimg 640 (bottom).
Figure 10
Figure 10
Model DR experiment results comparing accuracy and loss of training and validation data for model DR.
Figure 11
Figure 11
Accurately validated positive RATD image using Web App.
Figure 12
Figure 12
Model DR output with complex images.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Aggarwal P., Mishra N. K., Fatimah B., Singh P., Gupta A., Joshi S. D., et al. . (2022). COVID-19 image classification using deep learning: advances, challenges and opportunities. Comput. Biol. Med. 144:105350. 10.1016/j.compbiomed.2022.105350 - DOI - PMC - PubMed
    1. Alazab M., Awajan A., Mesleh A., Abraham A., Jatana V., Alhyari S., et al. . (2020). COVID-19 prediction and detection using deep learning. Int. J. Comput. Inf. Syst. Ind. Manag. Appl. 12, 168–181.
    1. Alhaj T. A., Idris I., Elhaj F. A., Elhassan T. A., Remli M. A., Siraj M. M., et al. . (2022). Preliminary stages for COVID-19 detection using image processing. Diagnostics 12:3171. 10.3390/diagnostics12123171 - DOI - PMC - PubMed
    1. Appari N. V. L., Kanojia M. G. (2022). Soft computing and image processing techniques for COVID-19 prediction in lung CT scan images. Int. J. Hybrid Intell. Syst. 18, 111–131. 10.3233/HIS-220009 - DOI
    1. Arumugam S., Ma J., Macar U., Han G., McAulay K., Ingram D., et al. . (2021). Adaptable automated interpretation of rapid diagnostic tests using few-shot learning. medRxiv. [Preprint]. 10.1101/2021.06.23.21258927 - DOI