SavedAdd your journal

Journals / Bilgisayar Bilimleri / 2021 / Cilt: IDAP-2021 : 5th International Artificial Intelligence and Data Processing symposium Sayı: Special Özel Sayı

A CNN Based Method for Detecting Covid-19 from CT Images

CT Görüntülerinden Covid-19 Tespiti için CNN Tabanlı Bir Yöntem

Buket Kaya(FIRAT ÜNİVERSİTESİ)0000-0001-9505-181X
Muhammed Önal(FIRAT UNIVERSITY)0000-0001-5335-867X
Pages
1–10
Publication Date
2021-10-20
🏛️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)

Results show that the used model attains provide highly satisfying results and can be used for any image classification.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:COVID-19 outbreak first emerged on December 31, 2019 in Wuhan, China.
📊
Key Findings & Data:The Novel Coronavirus Disease is caused by the SAR-CoV-2 virus, which causes respiratory symptoms such as fever, cough, and shortness of breath.
💡
Conclusion & Impact:Results show that the used model attains provide highly satisfying results and can be used for any image classification.
🔬Design:Lab & Field Experiment
📍Scope:2019 Verileri
⚙️Variables:CNN · 2019-nCoV · SARS-CoV-2

Abstract

COVID-19 outbreak first emerged on December 31, 2019 in Wuhan, China. The Novel Coronavirus Disease is caused by the SAR-CoV-2 virus, which causes respiratory symptoms such as fever, cough, and shortness of breath. While scientists continue their fight against SARS-CoV-2 (2019-nCoV), one of the deadliest viruses in the last century, with tests to help diagnosis and prognosis, drug and vaccine discovery, Information Technologies mostly continues to work on early diagnosis, prognosis and prediction. The aim is to reveal systems with low margin of error that will alleviate the workload of healthcare professionals, as well as early diagnosis and initiation of treatment.Deep Learning and Computer vision is the most commonly used. Two class (covid, non-covid) classification solution, using the Artificial Intelligence Techniques, have been examined in this paper. CNN architecture, has been created to develop an model to disease detection process of COVID-19(2019-nCoV) virus infected patients from CT images consisting of NON-COVID and COVID classes. We have proposed the classifying of CT images using the 2 Convolutions and pool layers with the model which shortening the time for classification and achieved an accuracy of nearly 95.77%. Results show that the used model attains provide highly satisfying results and can be used for any image classification.

Özet

COVID-19 salgını ilk olarak 31 Aralık 2019'da Çin'in Wuhan kentinde ortaya çıktı. Yeni Koronavirüs Hastalığına ateş, öksürük ve nefes darlığı gibi solunum semptomlarına neden olan SAR-CoV-2 virüsü neden olur. Bilim insanları, son yüzyılın en ölümcül virüslerinden biri olan SARS-CoV-2 (2019-nCoV) ile tanı ve prognoza yardımcı olacak testler, ilaç ve aşı keşfi ile mücadelelerini sürdürürken, Bilgi Teknolojileri de çoğunlukla erken teşhis konusunda çalışmalarını sürdürüyor. Amaç, sağlık çalışanlarının iş yükünü hafifletecek, erken teşhis ve tedaviye başlamayı sağlayacak, hata payı düşük sistemleri ortaya çıkarmaktır. Bu makalede, Yapay Zeka Teknikleri kullanılarak iki sınıflı (covid, covid olmayan) sınıflandırma çözümü incelenmiştir. CNN mimarisi, COVID-19(2019-nCoV) virüsü ile enfekte hastaların, KOVİD OLMAYAN ve COVID sınıflarından oluşan BT görüntülerinden hastalık tespit sürecine bir model geliştirmek için oluşturulmuştur. Sınıflandırma süresini kısaltan ve yaklaşık %95.77 doğruluk sağlayan model ile BT görüntülerinin 2 Konvolüsyon ve havuz katmanları kullanılarak sınıflandırılmasını önerdik. Sonuçlar, kullanılan modelin oldukça tatmin edici sonuçlar verdiğini ve herhangi bir görüntü sınıflandırması için kullanılabileceğini göstermektedir.

🔖

Cite This Article

Kaya, B., Önal, M. (2021). A CNN Based Method for Detecting Covid-19 from CT Images. Bilgisayar Bilimleri, Cilt: IDAP-2021 : 5th International Artificial Intelligence and Data Processing symposium Sayı: Special Özel Sayı, 1–10. https://doi.org/10.53070/bbd.990793

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (18)

  1. https://covid19.who.int/, last accessed on 9 Jun 21.
  2. Rajkumar RP. COVID-19 and mental health: a review of the existing literature. Asian J Psychiatry 2020;52. https://doi.org/10.1016/j.ajp.2020.102066 102066.
  3. Luo M, Guo L, Yu M, Jiang W, Wang H. The psychological and mental impact of coronavirus disease 2019 (COVID-19) on medical staff and general public – a systematic review and meta-analysis. Psychiatry Res 2020;291. https://doi.org/10.1016/j.psychres.2020.113190 113190.
  4. URL:https://radiologyassistant.nl/chest/covid-19/covid19-imaging-findings, last accessed on 19 Oct 20.
  5. Fraiwan L, Hassanin O, Fraiwan M, Khassawneh B, Ibnian AM, Alkhodari M. Automatic identification of respiratory diseases from stethoscopic lung sound signals using ensemble classifiers. Biocybern Biomed Eng 2021;41(1):1–14. https://doi.org/10.1016/j.bbe.2020.11.003.
  6. Chen, X., Xiang, S., Liu, C. L., & Pan, C. H., Vehicle detection in satellite images by hybrid deep convolutional neural networks, IEEE Geoscience and remote sensing letters, 11 (10), 1797-1801, 2014.
  7. Özkan, İ. & Ülker, E., “Derin Öğrenme ve Görüntü Analizinde Kullanılan Derin Öğrenme Modelleri”, Gaziosmanpaşa Bilimsel Araştırma Dergisi, 6(3), 85-104, 2017.
  8. Ravì, D., Wong, C., Deligianni, F., Berthelot, M., Andreu Perez, J.,Lo,B., & Yang, G.Z., “Deep learning for health informatics”. IEEE Journal of Biomedical and health informatics, 21(1), 4-21, 2016.
  9. L. Deng and D. Yu, “Deep Learning: Methods and Applications,” Found. Trends® Signal Process., vol. 7, no. 3–4, pp. 197–387, 2014.
  10. Nurettin Öner, İsmail Ağırbaş, Bilgisayar Tomografisi ve Manyetik Rezonans Görüntülemenin Sağlıkta Teknoloji Değerlendirme ve Maliyet-Fayda Analizi ile Değerlendirilmesi, Sağ. Perf. Kal. Derg (8), 147-163, 2014
  11. Zhou, S. K., Greenspan, H., and Shen, D., "Deep Learning for Medical Image Analysis", 1. Ed., Academic Press, London; San Diego, 458 (2017).
  12. Shen, D., Wu, G., and Suk, H.-I., "Deep learning in medical image analysis", Annual Review Of Biomedical Engineering, 19 (1): 221–248 (2017).
  13. Internet: Deep Learning, "What is the effect of adjusting BatchSize on the training effect?" https://www.programmersought.com/article/2840518935/
  14. Frid-Adar,M.,Diamant, I.,Klang E.,Amitai,M.,Goldberger J.,Greenspan H.,GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification.Neurocomputing. 321-331,2018.
  15. Internet: ujjwalkarn, "An Intuitive Explanation of Convolutional Neural Networks”, https://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/ (2018).
  16. Sabour, S., Frosst, N., and Hinton, G. E., "Dynamic routing between capsules", ArXiv:1710.09829 [Cs], (2017).
  17. Rajkumar RP. COVID-19 and mental health: a review of the existing literature. Asian J Psychiatry 2020;52. https://doi.org/10.1016/j.ajp.2020.102066 102066.
  18. Luo M, Guo L, Yu M, Jiang W, Wang H. The psychological and mental impact of coronavirus disease 2019 (COVID-19) on medical staff and general public – a systematic review and meta-analysis. Psychiatry Res 2020;291. https://doi.org/10.1016/j.psychres.2020.113190 113190.