AlexNet-based classification of chest X-Ray images

Abstract

COVID-19 pandemic first broke out in December 2019 and has been affecting the world ever since. The number of COVID-19 patients is increasing rapidly in the world day by day, and it is known that the diagnosis of this disease is important for disease treatment. Chest X-ray images that are clinical adjuncts are widely used in the diagnosis of COVID-19 disease. In the study, machine learning-based models are developed using these images to reduce the workload of expert. In the data set used in the study, there are images obtained from a total of 137 COVID-19, 90 normal, and 90 pneumonia subjects. Here, 1000 image features are extracted for each image using AlexNet deep learning architecture. Afterward, the classifiers used in the study are trained using these image features. From the results, Accuracy (%), Sensitivity (%), Specificity (%), Precision (%), F1 score (%), and Matthews Correlation Coefficient (Matthews Correlation Coefficient, MCC) values of Cubic SVM that is the most successful classifier are equal to 95.27, 94.95, 97.76, 94.65, 94.79, and 0.9250, respectively.

Keywords

• COVID-19
• feature extraction
• deep learning
• AlexNet
• machine learning
• disease diagnosis

Göğüs X-Ray görüntülerinin AlexNet tabanlı sınıflandırılması

Abstract

COVID-19 salgını Aralık 2019’da ilk kez ortaya çıkmış ve o zamandan beri dünyayı etkisi altına almaktadır. Gün geçtikçe dünyada COVID-19 hasta sayısı hızla artmaktadır ve bu hastalığın teşhisinin, hastalık tedavi süreci için önemli olduğu bilinmektedir. COVID-19 hastalığının teşhisinde klinik yardımcı olan göğüs X-Ray görüntüleri yaygın olarak kullanılmaktadır. Bu çalışmada, uzmanların iş yükünü azaltmak amacıyla, bu görüntüler kullanılarak makine öğrenmesi tabanlı modeller geliştirilmiştir. Çalışmada kullanılan veri setinde toplam 137 COVID-19, 90 normal ve 90 pnömoni kişilerden alınan görüntüler bulunmaktadır. Burada, AlexNet derin öğrenme mimarisi kullanılarak her görüntü için 1000 görüntü özelliği çıkartılmıştır. Sonrasında, bu görüntü özellikleri kullanılarak çalışmada kullanılan sınıflandırıcılar eğitilmiştir. Sonuçlardan, en başarılı sınıflandırıcı olan kübik destek vektör makinesi (Cubic Support Vector Machine, Cubic SVM) sınıflandırıcısının Doğruluk (%), Duyarlık (%), Özgüllük (%), Kesinlik (%), F1 skoru (%) ve Matthews Korelasyon Katsayısı (Matthews Correlation Coefficient, MCC) değerlerinin sırasıyla 95.27, 94.95, 97.76, 94.65, 94.79 ve 0.9250’ye eşit olduğu görülmüştür.

Keywords

• COVID-19
• özellik çıkartma
• derin öğrenme
• AlexNet
• makine öğrenmesi
• hastalık teşhisi

References

1. Alkan A, Günay M. (2012) Identification of EMG signals using discriminant analysis and SVM classifier. Expert systems with Applications 39(1):44-47.
2. Akben SB. (2018) Predicting the success of wart treatment methods using decision tree based fuzzy informative images. Biocybernetics and Biomedical Engineering 38(4): 819-827.
3. Ai T, Yang Z, Hou H, Zhan C, Chen C, Lv W, Xia L (2020) Correlation of chest CT and RT-PCR testing for coronavirus disease 2019 (COVID-19) in China: a report of 1014 cases. Radiology 296(2): E32-E40.
4. Booth AL, Abels E, McCaffrey P (2021) Development of a prognostic model for mortality in COVID-19 infection using machine learning. Modern Pathology 34(3):522-531.
5. Dataset (2021) https://www.kaggle.com/pranavraikokte/covid19-image-dataset, COVID-19 Image Dataset, Pranav Raikote.
6. Dünya Sağlık Örgütü (WHO) (2021) WHO Announces COVID-19 Outbreak a Pandemic. https://www.euro.who.int/en/health-topics/healthemergencies/coronavirus-covid19/news/news/2020/3/who-announces-covid19-outbreak-a-pandemic. Accessed 07.08.2021
7. Hadi AG, Kadhom M, Hairunisa N, Yousif E, Mohammed SA (2020) A review on COVID-19: origin, spread, symptoms, treatment, and prevention. Biointerface Research in Applied Chemistry 10(6): 7234-7242.
8. Guo G, Wang H, Bell D, Bi Y, Greer K. (2003) KNN model-based approach in classification. In OTM Confederated International Conferences" On the Move to Meaningful Internet Systems" Springer, Berlin, Heidelberg. pp.986-996.

9. Jadon S (2021) COVID-19 detection from scarce chest x-ray image data using few-shot deep learning approach. In Medical Imaging 2021: Imaging Informatics for Healthcare, Research, and Applications 11601:116010X.
10. Kassania SH, Kassanib PH, Wesolowskic MJ, Schneidera KA, Detersa R (2021) Automatic detection of coronavirus disease (COVID-19) in X-ray and CT images: a machine learning based approach. Biocybernetics and Biomedical Engineering 41(3):867-879.
11. Khuzani AZ, Heidari M, Shariati SA (2021) COVID-Classifier: An automated machine learning model to assist in the diagnosis of COVID-19 infection in chest x-ray images. Scientific Reports 11(1):1-6.
12. Krizhevsky A, Sutskever I, Hinton GE. (2012) Imagenet classification with deep convolutional neural networks. Advances in Neural İnformation Processing Systems 25:1097-1105.
13. Kwekha-Rashid AS, Abduljabbar HN, Alhayani B (2021) Coronavirus disease (COVID-19) cases analysis using machine-learning applications. Applied Nanoscience 1-13.
14. Lu S, Lu Z, Zhang YD. (2019) Pathological brain detection based on AlexNet and transfer learning. Journal of Computational Science 30: 41-47.
15. Ludvigsson JF (2020) Systematic review of COVID‐19 in children shows milder cases and a better prognosis than adults. Acta Paediatrica 109(6):1088-1095.
16. Maguolo G, Nanni L. (2021) A critic evaluation of methods for covid-19 automatic detection from x-ray images. Information Fusion 76:1-7.
17. Muhammad LJ, Algehyne EA, Usman SS, Ahmad A, Chakraborty C, Mohammed IA. (2021) Supervised machine learning models for prediction of COVID-19 infection using epidemiology dataset. SN computer Science 2(1):1-13.
18. Palaz F, Kalkan AK, Tozluyurt A, Ozsoz M. (2021) CRISPR-based tools: Alternative methods for the diagnosis of COVID-19. Clinical Biochemistry 89:1.
19. Polikar R. (2012) Ensemble learning. Ensemble machine learning, Springer, Boston, MA.
20. Rasheed J, Hameed AA, Djeddi C, Jamil A, Al-Turjman F. (2021) A machine learning-based framework for diagnosis of COVID-19 from chest X-ray images. Interdisciplinary Sciences: Computational Life Sciences 13(1):103-117.
21. Rish I. (2001) An empirical study of the naive Bayes classifier. In IJCAI 2001 workshop on empirical methods in artificial intelligence 3(22): 41-46.
22. Tar E, Küçükoğlu S. (2021) COVID-19 ve Yenidoğan Sağlığı. N. Ulutaşdemir, İ. Kahriman (Ed), COVID-19 Pandemisinde Çocuk Sağlığı içinde, https://iksadyayinevi.com/wp-content/uploads/2021/05/COVID-19-PANDEMISINDE-COCUK-SAGLIGI.pdf
23. Worldometer (2021) COVID-19 Coronavırus Pandemıc. https://www.worldometers.info/coronavirus/ Accessed 07.08.2021 Zimmermann P, Curtis N. (2020) Coronavirus infections in children including COVID-19: An overview of the epidemiology, clinical features, diagnosis, treatment and prevention options in children. Pediatr Infect Dis J. 39(5):355- 368.