Development of an Effective Deep Learning Model for COVID-19 Detection from CT Images

Abstract

Coronavirus Disease (COVID-19) is an RNA-type virus that is spreading worldwide. COVID-19, which was first seen in Wuhan, China, in December 2019, quickly began to be seen in all countries of the world. Symptoms such as respiratory tract infections, fever, cough and shortness of breath are common in the diagnosis of the disease. The detection of the disease is done in the first stage by applying the Polymerase Chain Reaction (PCR) test. The long duration of laboratory examinations has led researchers to different methods. In this study, a model that can help radiologists detect the disease through Computed Tomography (CT) images was designed. This system, based on deep learning, aims to detect the disease by classification method through COVID-19 positive and negative chest tomography images. The data set used in the study consists of a total of 5000 images. Experimental studies have been conducted on Convolutional Neural Network (CNN) models such as AlexNet, Densenet201, GoogleNet, ResNet-50, Vgg-16, EfficientNet and the proposed CNN model. With the designed CNN model, COVID-19 was predicted with a success rate of 99.20%. An effective and successful model is proposed for COVID-19 detection from CT images.

Keywords

• Deep Learning
• Image Classification
• COVID-19
• Computed Tomography

Kaynakça

1. Selçuk EB. Pandemic Spread Process in the World and Turkey. Inonu University Faculty of Medicine Department of Family Medicine. 2020;12(3):87-91.
2. Akyol, AD. Sars Severe Acute Respıratory Syndrome. Ege University Faculty of Nursing Journal.2005; 21(2):107-123.
3. Nemli, SA. Middle East Respiratory Syndrome-Coronavirus (MERS-CoV). Kocatepe Medical Journal. 2016; 17:77-83.
4. Ökçün S, Kurnaz M, Koçkaya G, Acar A. Overvıew Of Covıd-19 Dıagnosıs Methods: Rapid Review. Eurasian Journal Of Health Technology Assessment. 2020; 4(2):10-35.
5. İnik Ö, Ceyhan A, Balcıoğlu E, Ülker E. A new method for automatic counting of ovarian follicles on whole slide histological images based on convolutional neural network. Computers in biology and medicine. 2019; 112:103350.
6. Celik M, İnik Ö. Development of hybrid models based on deep learning and optimized machine learning algorithms for brain tumor Multi-Classification. Expert Systems with Applications. 2024;238: 122159.
7. İnik Ö, Ülker E. Optimization of deep learning based segmentation method. Soft Computing. 2022; 26(7): 3329-3344.
8. Çelik M, İnik Ö. Multiple Classification Of Brain Tumors For Early Detection Using A Novel Convolutional Neural Network Model. Eskişehir Osmangazi University Faculty of Engineering and Architecture Journal. 2023; 31(1) 491-500.

9. İnik Ö, Balcıoğlu E, Ceyhan A, Ülker E. Using Convolution Neural Network for Classification of Different Tissue Images in Histological Sections. Annals of the Faculty of Engineering Hunedoara. 2019; 17.1: 101-104..
10. İnik O, İnik Ö, Öztaş T, Demir Y, Yüksel A. Prediction of Soil Organic Matter with Deep Learning. Arabian Journal for Science and Engineering. 2023; 1-21.
11. İnik Ö, Uyar K, Ülker E. Gender classification with a novel convolutional neural network (CNN) model and comparison with other machine learning and deep learning CNN models. Journal Of Industrial Engineering Research. 2018; 57-63.
12. Nasip ÖF, Zengin K. Deep learning based bacteria classification. In. Tokat, Türkiye: 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT). 2018; 1-5.
13. Singhal T. A Review of Coronavirus Disease-2019 (COVID-19). The Indian Journal of Pediatrics. 2020; 281–286.
14. Kaya B, Önal M. Segmentation of Lung CT Images for COVID-19 Detection. European Journal of Science and Technology. 2021; 28:1296-1303.
15. Çalışkan A. Detection Of Coronavirus Disease Using Wavelet Convolutional Neural Network Method. Kahramanmaraş Sütçü İmam University Journal of Engineering Sciences. 2023; 26(1):203-212.
16. Hemdan EE, Shouman MA, Karar ME. COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images. 2020;2003.11055.
17. Bozkurt F. COVID-19 Detection from Chest X-Ray Images Using Deep Learning Techniques. European Journal of Science and Technology. 2021;(24):149-156.
18. JavadiMoghaddam S, Gholamalinejad H. A Novel Deep Learning Based Method For COVID-19 Detection From CT İmage. Biomedical Signal Processing and Control V70, (2021).
19. Oğuz Ç. Determination Of COVİD 19 Possible Cases By Using Deep Learning Techniques. Master's Thesis, Ataturk University Institute of Science, Erzurum.2021.
20. Panahi AH, Rafiei A, Rezaee A. FCOD: Fast COVID-19 Detector based on deep learning techniques. Informatics in Medicine Unlocked. 2020; (22):100506.
21. Urut S, Özdağ R. COVID-19 Forecasting And Feature Detection Using Recurrent Neural Networks. Uluslararası Bilişim Kongresi. 2022; 523-530.
22. Ceylan T, İnik Ö. COVID-19 Detection on Radiological Images with Deep Learning. 3rd International Conference on Applied Engineering and Natural Sciences. 2022;1807-1811.
23. Çelik M, İnik Ö. Detection of Monkeypox Among Different Pox Diseases with Different Pre-Trained Deep Learning Models. Journal of the Institute of Science and Technology. 2023;13(1): 10-21.
24. Pacal I. A Vision Transformer-based Approach for Automatic COVID-19 Diagnosis on Chest X-ray Images. Journal of the Institute of Science and Technology. 2023; 13(2):778-791.
25. Doğan Y. COVID-19 Detection with Deep Learning Methods Under Cross-Dataset Evaluation. Gazi Universty Journal of Science Part C: Desıgn And Technology. 2023; 11(3) 813-823.
26. Tüfekçi P, Gezici B. Detection of COVID-19 and Viral Pneumonia from Chest X-Ray Images with DeepLearning. Afyon Kocatepe University Journal of Science and Engineering. 2023; 23(1), 89-100.
27. Yilmaz A. Artificial Intelligence, ISBN 978-605-9118-80-4, Irem Soylu, Istanbul. Kodlab; 2022.
28. İnik Ö, Ülker E. Deep Learning and Deep Learning Models Used in Image Analysis. Gaziosmanpasa Journal of Scientific Research. 2017; 6(3): 85-104.
29. Talan T, Aktürk C. Theoretical and Applied Research in Computer Science. Istanbul: Efe Academy Publications; 2021.
30. Doğan F, Türkoğlu İ. The Comparison Of Leaf Classification Performance Of Deep Learning Algorithms. Sakarya University Journal Of Computer And Information Sciences. 2018; (1):10–21.
31. Büyükarıkan B, Ülker E. Fruit Classification With Convolution Neural Network Models Using Illumination Attribute. Uludag University Faculty of Engineering Journal. 2020; (25), 81-100.
32. Obuchowski NA. Receiver Operating Characteristic Curves And Their Use İn Radiology. Radiology. 2003; 229(1):3-8. mathworks.com [internet]. 2023 [cited 2023 november22].Available from:https://www.mathworks.com/products/new_products/release2023a.html/