Makine Öğrenmesi Algoritmalarıyla Akciğer Tomografi Görüntülerinden COVID-19 Tespiti

Öz

Koronavirüs (COVID-19), solunum yolu enfeksiyonuna neden olan ve insandan insana geçebilen bulaşıcı bir virüstür. Bu virüs dünyada kısa sürede etkili olmuş ve bir salgına dönüşmüştür. Bu tür bulaşıcı hastalıkların erken teşhisi ve gerekli tedavinin erken süreçte başlatılması gerekmektedir. COVID-19 hastalığı tespiti için akciğer görüntülerinden ve ağız yoluyla alınan tükrük ile tespit edilmektedir. COVID-19 hastasını RT-PCR (Reverse Transcription- Polymerase Chain Reaction) ile tespit etmek için yaklaşık 4-6 saat sürmektedir. Pandeminin büyüklüğüne bakıldığında çok ta hızlı sayılmamaktadır. Aynı zamanda test kitinin de bir maliyeti bulunmaktadır. Ekonomik olarak güçlü olmayan ülkeler RT-PCR kitlerine erişmekte sorun yaşamaktadır. Pandemi döneminde zorlu süreçlerden bir tanesi her raporu manuel olarak incelemek için, birden fazla radyoloji uzmanı gerekmektedir. Bu çalışmada makine öğrenmesi algoritmaları ile farklı kategorilerdeki akciğer tomografisi görüntülerinden COVID-19 olan görüntü tespit edilmiştir. Orange Data Mining Veri analizi programında makine öğrenmesi algoritması olan K-En Yakın Komşuluk, Yapay Sinir Ağları, Rastgele Orman ve Destek Vektör algoritmaları ile Akciğer veri setinden COVİD-19 hastalığına ait görüntüler sınıflandırılmış, en iyi sonucu Destek Vektör Algoritması ile elde edilmiştir.

Anahtar Kelimeler

• Yapay Zeka ile hastalık teşhisi
• Covid-19 teşhisi
• Makine öğrenmesi Algoritmaları
• KNN Algoritması
• SVM Algoritması
• Rastgele Orman Algoritması

COVID-19 Detection from Lung Tomography Images with Machine Learning Algorithms

Abstract

Coronavirus (COVID-19) is a contagious virus that causes respiratory tract infection and can be passed from person to person. This virus became effective in the world in a short time and turned into an epidemic. Early diagnosis of such infectious diseases and the necessary treatment should be initiated in the early period. For the detection of COVID-19 disease, it is detected by lung images and oral saliva. It takes approximately 4-6 hours to detect a COVID-19 patient by RT-PCR (Reverse Transcription- Polymerase Chain Reaction). Considering the size of the pandemic, it is not considered very fast. At the same time, the test kit has a cost. Countries that are not economically strong have problems accessing RT-PCR kits. One of the challenging processes during the pandemic period is to manually review each report, requiring multiple radiologists. In this study, the images with COVID-19 were detected from different categories of lung tomography images with machine learning algorithms. In the Orange Data Mining data analysis program, the images of the COVID-19 disease from the Lung data set were classified with the machine learning algorithm K-Nearest Neighborhood, Artificial Neural Networks, Random Forest and Support Vector algorithms, and the best result was obtained with the Support Vector Algorithm.

Keywords

• Disease diagnosis with artificial intelligence
• Covid-19 diagnosis
• Machine learning Algorithms
• KNN Algorithm
• SVM Algorithm
• Random Forest Algorithm

References

1. Sohrabi, C., Alsafi, Z., O'neill, N., Khan, M., Kerwan, A., Al-Jabir, A., ... & Agha, R. (2020). World Health Organization declares global emergency: A review of the 2019 novel coronavirus (COVID-19). International journal of surgery, 76, 71-76.
2. Knight, T. E. (2020). Severe acute respiratory syndrome coronavirus 2 and coronavirus disease 2019: a clinical overview and primer. Biopreservation and Biobanking, 18(6), 492-502.
3. Lai, C.-C., Shih, T.-P., Ko, W.-C., Tang, H.-J., & Hsueh, P.-R. (2020). Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and coronavirus disease-2019 (COVID-19): The epidemic and the challenges. International Journal of Antimicrobial Agents, 55(3), 105924. https://doi.org/10.1016/j.ijantimicag.2020.105924
4. Wikimedia Commons, 3D medical animation corona virus.jpg, https://commons.wikimedia.org/wiki/File:3D_medical_animation_corona_virus.jpg, [Ziyaret Tarihi: 15 Mayıs 2021].
5. Toğaçar, M., Ergen, B., & Cö1mert, Z., (2020), COVID-19 detection using deep learning models to exploit Social Mimic Optimization and structured chest X-ray images using fuzzy color and stacking approaches”. Computers in Biology and Medicine, 1-12, 2020.
6. Franquet, T. (2011). Imaging of pulmonary viral pneumonia. Radiology, 260(1), 18-39.
7. Öztürk, T., Talo, M., Yıldırım, E. A., Baloğlu, U. B., Yıldırım, Ö., & Acharya, U. Automated detection of COVID-19 cases using deep neural networks with X-ray images, Computers in Biology and Medicine,1-11, 2020.
8. Tolksdorf, K., Buda, S., Schuler, E., Wieler, L. H., ve Haas, W., 2020, Influenza-associated pneumonia as reference to assess seriousness of coronavirus disease (COVID-19). Euro Surveill, 25(11). doi:10.2807/1560-7917.ES.2020.25.11.2000258

9. Grasselli, G., Pesenti, A., & Cecconi, M. (2020). Critical care utilization for the COVID-19 outbreak in Lombardy, Italy: early experience and forecast during an emergency response. Jama, 323(16), 1545-1546.
10. Mei, X., Lee, H. C., Diao, K. Y., Huang, M., Lin, B., Liu, C., Xie, Z., Ma, Y., Robson, P. M., Chung, M., Bernheim, A., Mani, V., Calcagno, C., Li, K., Li, S., Shan, H., Lv, J., Zhao, T., Xia, J., Long, Q., … Yang, Y., 2020, Artificial intelligence-enabled rapid diagnosis of patients with COVID-19, Nature medicine, 26(8), 1224–1228. https://doi.org/10.1038/s41591-020-0931-3
11. Gozes, O., & Siegel, E. (2020). Rapid AI development cycle for coronavirus, pandemic: Initial results for automated detection & patient monitoring, using deep learning CT image analysis. arXiv preprint arXiv:2003.05037.
12. Li, L., Qin, L., Xu, Z., Yin, Y., Wang, X., Kong, B., ... & Xia, J. (2020). Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT. Radiology.
13. Ucar F., Korkmaz D., 2020, COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images, Medical Hypotheses, 2020 Jul;140:109761. DOI: 10.1016/j.mehy.2020.109761.
14. Zheng, C., Deng, X., Fu, Q., Zhou, Q., Feng, J., Ma, H., Liu, W., ve Wang, X., 2020, Deep Learning-based Detection for COVID-19 from Chest CT using Weak Label, MedRxiv, 2020.03.12.20027185. https://doi.org/10.1101/2020.03.12.20027185
15. Rahimzadeh, M., Attar, A., 2020, A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50 V2, Informatics in Medicine Unlocked 19, 100360, https://doi.org/10.1016/j.imu.2020.100360
16. Alom, M. Z., Rahman, M. M., Nasrin, M. S., Taha, T. M., & Asari, V. K., 2020, COVID_MTNet: COVID-19 detection with multi-task deep learning approaches. arXiv preprint arXiv:2004.03747.
17. Salman, F. M., Abu-Naser, S. S., Alajrami, E., Abu-Nasser, B. S., ve Alashqar, B. A., 2020, Covid-19 detection using artificial intelligence.
18. Jaiswal, A., Gianchandani, N., Singh, D., Kumar, V., ve Kaur, M., 2020, Classification of the COVID-19 infected patients using DenseNet201 based deep transfer learning. Journal of Biomolecular Structure and Dynamics, 1-8.
19. Butt, C., Gill, J., Chun, D., Babu, B. A., 2020, Deep learning system to screen coronavirus disease 2019 pneumonia, Applied Intelligence, 1–7, Advance online publication. https://doi.org/10.1007/s10489-020-01714-
20. Wang, S., Zha, Y., Li, W., Wu, Q., Li, X., Niu, M., . . . Yu, H., 2020, A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis. European Respiratory Journal, 56(2).
21. Pathak, Y., Shukla, P. K., Tiwari, A., Stalin, S., ve Singh, S., 2020, Deep transfer learning based classification model for COVID-19 disease. Irbm.
22. Song, Y., Zheng, S., Li, L., Zhang, X., Zhang, Xiaodong., Huang, Z., Chen, J., Wang, R., Zhao, H., Zha, Y., Shen, J., Chong, Y., ve Yang, Y., 2021, “Deep learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19) with CT images”. IEEE/ACM Transactions on Computational Biology and Bioinformatics 1-1. doi: 10.1109/TCBB.2021.3065361.
23. Ozyurt, F., Tuncer, T., ve Subasi, A., 2021, An Automated COVID-19 Detection Based on Fused Dynamic Exemplar Pyramid Feature Extraction and Hybrid Feature Selection Using Deep Learning, Computers in Biology and Medicine 132:104356. doi: 10.1016/j.compbiomed.2021.104356.
24. Apostolopoulos, I. D., Aznaouridis, S. I., ve Tzani, M. A., 2020, Extracting possibly representative COVID-19 biomarkers from X-Ray images with deep learning approach and image data related to pulmonary diseases. Journal of Medical and Biological Engineering, 40, 462-469.
25. Serte, S., ve Demirel, H., 2021, Deep learning for diagnosis of COVID-19 using 3D CT scans. Computers in biology and medicine, 132, 104306.
26. Kılınç, D., Borandağ, E., Yücalar, F., Tunali, V., Şimşek, M., ve Özçift, A., 2016, KNN Algoritması ve R Dili ile Metin Madenciliği Kullanılarak Bilimsel Makale Tasnifi. Marmara Fen Bilimleri Dergisi, 28(3). doi:10.7240/mufbed.69674
27. Nicholson, C., 2020, A Beginner's Guide to Neural Networks and Deep Learning. Retrieved from, https://wiki.pathmind.com/neural-network
28. Hsu, C. W., Chang, C. C., ve Lin, C. J., 2010, A Practical Guide to Support Vector Classification.
29. Hatipoğlu, E., 2018, Machine Learning — Prediction Algorithms — Decision Tree —Random Forest — Part 5. Retrieved from https://medium.com/@ekrem.hatipoglu/machine-learning-prediction-algorithms-decision-tree-random-forest-part-5-2970905c021e
30. Zeiler, M. D., & Fergus, R., 2014, September, Visualizing and understanding convolutional networks. In European conference on computer vision (pp. 818-833). Springer, Cham.
31. Ullah, I., Hussain, M., Qazi, E.-H., Aboalsamh, H., 2018, An automated system for epilepsy detection using EEG brain signals based on deep learning approach, Expert Syst. Appl. 107, 61–71.
32. Qassim, H., Verma, A., & Feinzimer, D., 2018, Compressed residual-VGG16 CNN model for big data places image recognition. In 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC) (pp. 169-175). IEEE.
33. Taş, B., 2019, Roc Eğrisi ve Eğri Altında Kalan Alan (Auc), https://bernatas.medium.com/roc-e%C4%9Frisi-ve-e%C4%9Fri-alt%C4%B1nda-kalan-alan-auc-97b058e8e0cf
34. Narkhede, S., 2018, Understanding auc-roc curve. Towards Data Science, 26, 220-227.
35. Brownlee, J., 2020, What is a Confusion Matrix in Machine Learning, https://machinelearningmastery.com/confusion-matrix-machine-learning/