Abstract

Research Article

Applications of convolutional neural networks in chest X-ray analyses for the detection of COVID-19

Patrick Ting*, Anish Kasam and Kevin Lan

Published: 20 January, 2022 | Volume 6 - Issue 1 | Pages: 001-007

Throughout global efforts to defend against the spread of COVID-19 from late 2019 up until now, one of the most crucial factors that has helped combat the pandemic is the development of various screening methods to detect the presence of COVID-19 as conveniently and accurately as possible. One of such methods is the utilization of chest X-Rays (CXRs) to detect anomalies that are concurrent with a patient infected with COVID-19. While yielding results much faster than the traditional RT-PCR test, CXRs tend to be less accurate. Realizing this issue, in our research, we investigated the applications of computer vision in order to better detect COVID-19 from CXRs. Coupled with an extensive image database of CXRs of healthy patients, patients with non-COVID-19 induced pneumonia, and patients positive with COVID-19, convolutional neural networks (CNNs) prove to possess the ability to easily and accurately identify whether or not a patient is infected with COVID-19 in a matter of seconds. Borrowing and adjusting the architectures of three well-tested CNNs: VGG-16, ResNet50, and MobileNetV2, we performed transfer learning and trained three of our own models, then compared and contrasted their differing precisions, accuracies, and efficiencies in correctly labeling patients with and without COVID-19. In the end, all of our models were able to accurately categorize at least 94% of the CXRs, with some performing better than the others; these differences in performance were largely due to the contrasting architectures each of our models borrowed from the three respective CNNs.

Read Full Article HTML DOI: 10.29328/journal.abse.1001015 Cite this Article Read Full Article PDF

Keywords:

Convolutional neural networks; Neural networks; Chest X-ray images; ResNet 50; MobileNet V2; Artificial intelligence; VGG16; Artificial intelligence in medicine

References

  1. Chung AG. Agchung/Figure1-COVID-Chestxray-Dataset. GitHub. github.com/agchung/Figure1-COVID-chestxray-dataset
  2. Cohen JP. COVID-19 Image Data Collection: Prospective Predictions Are the Future. ArXiv. 2020; 2006; 11988:
  3. Cohen JP. ieee8023/Covid-Chestxray-Dataset. GitHub. github.com/ieee8023/covid-chestxray-dataset
  4. ​​Fei-Fei L. Image Net. image-net.org/about.php
  5. He K. Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  6. Howard A, Zhu M, Chen B, Kalenichenko D, Wang W, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv. 2017; 1704: 04861.
  7. Islam N, Ebrahimzadeh S, Salameh JP, Kazi S, Fabiano N, et al. Thoracic imaging tests for the diagnosis of COVID-19. Cochrane Database Syst Rev. 2021; Art. No.: CD013639. https://pubmed.ncbi.nlm.nih.gov/32997361/
  8. Kc K. Evaluation of deep learning-based approaches for COVID-19 classification based on chest X-ray images. Signal, image and Video Processing. 2021; 1-8.
  9. Kelly CJ, Karthikesalingam A, Suleyman M, et al. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 2019; 17: 195.
  10. Chowdhury MEH. Can AI Help in Screening Viral and COVID-19 Pneumonia? in IEEE Access. 2020; 8: 132665-132676.
  11. Mooney P. Chest X-Ray Images (Pneumonia). Kaggle. 2018. kaggle.com/paultimothymooney/chest-xray-pneumonia
  12. Patel P. Chest X-Ray (Covid-19 & Pneumonia). Kaggle. 2020. https://www.kaggle.com/prashant268/chest-xray-covid19-pneumonia
  13. Srudeep PA. An Overview on MobileNet: An Efficient Mobile Vision CNN. Medium. 2020. com/@godeep48/an-overview-on-mobilenet-an-efficient-mobile-vision-cnn-f301141db94d  
  14. Peng J, Kang S, Ning Z, Deng H, Shen J, et al. Residual Convolutional Neural Network for Predicting Response of Transarterial Chemoembolization in Hepatocellular Carcinoma from CT Imaging. Eur Radiol. 2019; 30: 413-424.https://pubmed.ncbi.nlm.nih.gov/31332558/  
  15. Rubin GD, Ryerson CJ, Haramati LB, Sverzellati N, Kanne JP, et al. The Role of Chest Imaging in Patient Management during the COVID-19 Pandemic: A Multinational Consensus Statement from the Fleischner Society. Chest. 2020; 158: 106-116.https://pubmed.ncbi.nlm.nih.gov/32275978/
  16. Sahinbas K, Catak FO. Transfer learning-based convolutional neural network for COVID-19 detection with X-ray images. Data Science for COVID-19. 2021: 451–466. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8138118/
  17. Sekeroglu B, Ozsahin I. Detection of COVID-19 from Chest X-Ray Images Using Convolutional Neural Networks. SLAS Technol. 2020; 25: 553-565.
  18. Senthilraja M. Application of Artificial Intelligence to Address Issues Related to the COVID-19 Virus. SLAS Technol. 2021; 26: 123-126. https://pubmed.ncbi.nlm.nih.gov/33390088/
  19. Shaikh F. Advanced Architectures: Deep Learning Architectures. Analytics Vidhya. 2020. analyticsvidhya.com/blog/2017/08/10-advanced-deep-learning-architectures-data-scientists/
  20. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv: 2014; 1409: 1556.
  21. Sitaula C, Hossain MB. Attention-based VGG-16 model for COVID-19 chest X-ray image classification. Appl Intell. 2020; 1-14. https://pubmed.ncbi.nlm.nih.gov/34764568/
  22. Thakur R. Step by step VGG16 implementation in Keras for beginners. Towards Data Science – Medium. 2019. https://towardsdatascience.com/step-by-step-vgg16-implementation-in-keras-for-beginners-a833c686ae6c
  23. VGG16 - Convolutional Network for Classification and Detection. 2021. neurohive.io/en/popular-networks/vgg16/  
  24. Wang L, Lin ZQ, Wong A. COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images. Sci Rep. 2020; 10: 19549.
  25. Wang W, Li Y, Zou T, Wang X, You J, Luo Y. A Novel Image Classification Approach via Dense-MobileNet Models. Mobile Information Systems. 2020; 2020: 7602384.
  26. Wood D. Coronavirus World Map: We've Now Passed. The 180 Million Mark For Infections. NPR. 2021. www.npr.org/sections/goatsandsoda/2020/03/30/822491838/coronavirus-world-map-tracking-the-spread-of-the-outbreak 

Figures:

Figure 1

Figure 1

Figure 1

Figure 2

Figure 1

Figure 3

Figure 1

Figure 4

Figure 1

Figure 5

Figure 1

Figure 6

Figure 1

Figure 7

Figure 1

Figure 8

Figure 1

Figure 9

Figure 1

Figure 10

Figure 1

Figure 11

Similar Articles

Recently Viewed

Read More

Most Viewed

Read More

Help ?