Journals / Düzce Üniversitesi Bilim ve Teknoloji Dergisi / 2021 / Cilt: 9 - Sayı: 6

Comparison of Lightweight and Traditional CNN Architectures in COVID-19 Detection from Lung X-Ray Images

Akciğer X-Ray Görüntülerinden COVID-19 Tespitinde Hafif ve Geleneksel Evrişimsel Sinir Ağ Mimarilerinin Karşılaştırılması

Pages
26–39
Publication Date
2022-11-06
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The most successful results were obtained with DenseNet121 and MobileNet networks, and classification was performed with 92.16% and 91.78% accuracy rates, respectively.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The corona virus epidemic, which affects the respiratory system and causes death in advanced cases, has been going on for about two years Although each country's method of fighting the epidemic is different, the common and valid method is the detection and isolation of the disease.
📊
Key Findings & Data:The most critical step for detection and isolation is the correct and fast diagnosis of COVID-19.
💡
Conclusion & Impact:The most successful results were obtained with DenseNet121 and MobileNet networks, and classification was performed with 92.16% and 91.78% accuracy rates, respectively.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Evrişimsel sinir ağları · Koronavirüs · COVID-19

Abstract

The corona virus epidemic, which affects the respiratory system and causes death in advanced cases, has been going on for about two years Although each country's method of fighting the epidemic is different, the common and valid method is the detection and isolation of the disease. The most critical step for detection and isolation is the correct and fast diagnosis of COVID-19. Virus-specific findings in lung X-ray images shows that these data can be used in the diagnosis of the disease. The aim of the related study is to multi classify by processing X-Ray images of COVID-19 and other lung diseases with machine learning methods. In this way, it is aimed to provide support to the personnel who are not experts in their fields, who will be helped for diagnosis and isolation during the crisis, at the decision stage through mobile devices. For this purpose: The data set consisting of 11,293 X-Ray images of COVID-19, Normal, Lung Opacity, Other Pneumonia labels was classified using the MobileNetV2, NASNetMobile, Xception and DenseNet121 CNN networks and the results were compared. The most successful results were obtained with DenseNet121 and MobileNet networks, and classification was performed with 92.16% and 91.78% accuracy rates, respectively.

Özet

Solunum sistemine etki eden ve ileri vakalarda ölüme neden olan korona virüs salgını yaklaşık iki yıldır devam etmektedir. Her ülkenin salgın ile mücadele yöntemi farklı olmasına rağmen ortak izlenen metot ise hastalığın tespiti ve izolasyonudur. Tespit ve izolasyon için en kritik adım ise COVID-19 tanısının doğru ve hızlı konulmasıdır. Akciğer X-Ray görüntülerinde virüse özgü bulgulara rastlanılması, bu verilerin hastalık teşhisinde kullanılabileceğini göstermektedir. İlgili çalışmanın amacı, makine öğrenmesi yöntemleri ile COVID-19 ve diğer akciğer hastalıklarına ait X-Ray görüntülerini işleyerek çoklu sınıflandırma yapmaktır. Bu sayede kriz anında tanı koyma ve izolasyon için yardım alınacak alanında uzman olmayan personele mobil cihazlar vasıtasıyla karar aşamasında destek sağlanması hedeflenmektedir. Bu amaçla: COVID-19, Normal, Akciğer Opasitesi, Diğer Pnömoni etiketlerine ait 11,293 X-Ray görüntüsünden oluşan veri seti MobileNetV2, NASNetMobile, Xception ve DenseNet121 CNN ağları kullanılarak sınıflandırılmış ve sonuçlar karşılaştırılmıştır. En başarılı sonuçlar DenseNet121 ve MobileNet ağları ile elde edilmiş olup sırası ile %92,16 ve %91,78 doğruluk oranıyla sınıflandırma gerçekleştirilmiştir.

🔖

Cite This Article

ERYILMAZ, F., KARACAN, H. (2022). Comparison of Lightweight and Traditional CNN Architectures in COVID-19 Detection from Lung X-Ray Images. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, Cilt: 9 - Sayı: 6, 26–39. https://ajindex.com/articles/649828

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (14)

  1. J.-M. Qu, B. Cao, and R.-C. Chen, COVID-19: The Essentials of Prevention and Treatment, 1st ed., Amsterdam, Holland: Elsevier Science, 2020, ch. 1, pp 1-6
  2. Z. Allam, Surveying the Covid-19 Pandemic and Its Implications, 1st ed., Amsterdam, Holland: Elsevier Science 2020, ch. 1, pp. 1–7
  3. T.-M. Chen, J. Rui, Q.-P. Wang, Z.-Y. Zhao, J.-A. Cui, and L. Yin, “A mathematical model for simulating the phase-based transmissibility of a novel coronavirus,” Infectious Diseases of Poverty, vol. 9, no. 1, pp. 24, 2020
  4. World Health Organization. (2021, November 4). Naming the coronavirus disease (COVID-19) and the virus that causes it [Online]. Available:
  5. J. Zheng, “Sars-cov-2: an emerging coronavirus that causes a global threat,” International Journal of Biological Sciences, vol. 16, no. 10, pp. 1678, 2020
  6. Karthik, R. Menaka, and H. M, “Learning distinctive filters for COVID-19 detection from chest X-ray using shuffled residual CNN,” Applied Soft Computing, vol. 99, pp. 106744, 2021
  7. M. M. A. Monshi, J. Poon, V. Chung, and F. M. Monshi, “CovidXrayNet: Optimizing data augmentation and CNN hyperparameters for improved COVID-19 detection from CXR,” Computers in Biology and Medicine, vol. 133, pp. 104375, 2021
  8. World Health Orginazation. (2021, August 28). Coronavirus(COVID-19) Dashboard [Online]. Available:
  9. L. Wang, Z. Q. Lin, and A. Wong, “COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images,” Scientific Reports, vol. 10, no. 1, pp. 19549, 2020
  10. Y. Bouchareb et al., “Artificial intelligence-driven assessment of radiological images for COVID-19,” Computers in Biology and Medicine, vol. 136, pp. 104665, 2021
  11. N.-A.- Alam, M. Ahsan, M. A. Based, J. Haider, and M. Kowalski, “COVID-19 detection from chest X-ray images using feature fusion and deep learning,” Sensors (Basel), vol. 21, no. 4, pp. 1480, 2021
  12. Z. Wang et al., “Automatically discriminating and localizing COVID-19 from community-acquired pneumonia on chest X-rays,” Pattern Recognition, vol. 110, pp. 107613, 2021
  13. M. J. Horry et al., “COVID-19 detection through transfer learning using multimodal imaging data,” IEEE Access, vol. 8, pp. 149808–149824, 2020
  14. G. D. Rubin et al., “The role of chest imaging in patient