Bilgisayarlı Tomografi Görüntülerinden COVID-19 Teşhisi İçin Geliştirilen Transfer Öğrenim Modelinin Performansının Artırılması

Abstract

COVID-19 pnömonisinin erken aşamada hızlı ve doğru teşhisi, pandemiyle mücadelede bir önlem olarak büyük önem taşımaktadır. Gerçek zamanlı ters transkriptaz-polimeraz zincir reaksiyonu (RT-PCR) testi, COVID-19'u belirlemek için altın bir standart gibi görünse bile, kullanılabilirliği ve doğruluğu hala bir zorluktur. Bu nedenle, hastalığın yayılmasını kontrol etmek için alternatif teşhis teknikleri gereklidir. Radyodiyagnostik yöntemler arasında, bilgisayarlı tomografi (BT) tekniği COVID-19 pnömonisini doğru bir şekilde teşhis etmek için en güçlü adaylardan biridir. Bu çalışmada, gerekli tedavinin uygulanmasını ve önlemlerin alınmasını hızlandırmaya yardımcı olmak için göğüs BT taramalarından COVID-19'u yüksek doğruluk ve hassasiyetle tespit etmek üzere uyarlanmış, aktarımı öğrenmeye dayalı güvenilir bir CNN modelinin geliştirilmesi amaçlanmıştır. CNN modelinin eğitim sürecinde kullanılan CT görüntüleri veri seti “SARS-CoV-2 CT-Scan Veri Seti”nden elde edilmiştir. Bu veri kümesi, pozitif COVID-19 vakası için 1252 CT görüntüsü ve COVID-19 olmayan vaka için 1230 CT görüntüsü, toplamda 2482 CT görüntüsü içerir, tüm veriler Sao Paulo, Brezilya'daki hastanelerdeki gerçek hastalardan toplanmıştır. ResNet18, ResNet50, VGG16, AlexNet ve SqueezeNet1_1 mimarileri, transfer öğrenimi ile COVID-19 sınıflarını belirlemek için yeniden eğitildi. En yüksek sınıflandırma performans parametreleri ResNet50 mimarisi için elde edilmiş ve % 99,80 doğruluk,% 99,61 kesinlik ve% 100,00 duyarlılık olarak hesaplanmıştır. CT görüntülerinin önemli alanlarını vurgulamak ve nedensellik ve anlaşılırlığı geliştirmek için aktivasyon haritaları oluşturuldu. Geliştirilen transfer öğrenme modeli, triyajı hızlandırmak ve hastalık kontrolü için kritik zamandan tasarruf etmek ve radyoloğun ilk tanılarını doğrulamasına yardımcı olmak için CT görüntülerinden COVID-19 vakalarının güvenilir klinik teşhisinde kullanılabilir.

Keywords

• Corona virüsü (COVID-19)
• Derin öğrenme
• Evrişimsel sinir ağı
• Transfer öğrenimi
• Bilgisayarlı tomografi

Boosting Performance of Transfer Learning Model for Diagnosis of COVID-19 from Computer Tomography Scans

Abstract

Early-stage rapid and accurate diagnosis of COVID-19 pneumonia is of great importance as a measure to the fight against the pandemic. Even if real-time reverse transcription-polymerase chain reaction (RT-PCR) test seems like a gold standard for determining COVID-19, the availability and the accuracy is still a challenge. Thus, alternative diagnostic techniques are required for controlling the spreading of the disease. Amongst the radiodiagnostic methods, the computer tomography (CT) technique is one of the most powerful candidates for screening COVID-19 pneumonia accurately. In this study, it is aimed to develop a reliable transfer learning-based CNN model tailored to detect the COVID-19 from chest CT scans with high accuracy and sensitivity to help to accelerate the application of the required treatment and taking of measures. The CT scan dataset used in the training process of the CNN model was obtained from “SARS-CoV-2 CT-Scan Dataset”. This dataset contains 1252 CT scans for positive COVID-19 case and 1230 CT scans for the non-COVID-19 case, 2482 CT scans in total, all data have been collected from real patients from hospitals in Sao Paulo, Brazil. ResNet18, ResNet50, VGG16, AlexNet, and SqueezeNet1_1 architectures were re-trained to extract COVID-19 classes by transfer learning. The highest classification performance parameters were obtained for ResNet50 architecture and were calculated as 99.80% accuracy, 99.61 % precision, and 100.00% sensitivity. The activation maps were created to highlight the crucial areas of the CT images and improve causality and intelligibility. The developed transfer learning model can be utilized for reliable clinical diagnosis of COVID-19 cases from CT images to accelerate the triaging and save critical time for disease control as well as assisting the radiologist to validate their initial diagnosis.

Keywords

• Corona virus (COVID-19)
• Deep learning
• Convolutional neural network (CNN)
• Transfer learning
• Computer tomography

References

1. [1] C. Butt, J. Gill, D. Chun, and B. A. Babu, “Deep learning system to screen coronavirus disease 2019 pneumonia,” Appl. Intell., 1-7, 2020.
2. [2] T. Singhal, “A review of coronavirus disease-2019 (COVID-19),” Indian J Pediatr, 1-6, 2020.
3. [3] S. H. Ebrahim, Q. A. Ahmed, E. Gozzer, P. Schlagenhauf, and Z. A. Memish, “Covid-19 and community mitigation strategies in a pandemic,” BMJ, 2020.
4. [4] Coronavirus disease 2019 (COVID-19) Situation Report – 51, WHO, [Online].Available: https://www.who.int/docs/default-source/coronaviruse/situation-reports/20200311-sitrep-51-covid 19.pdf?sfvrsn=1ba62e57_10. Accessed 07 June 2020.
5. [5] Resource estimation for contact tracing, quarantine and monitoring activities for COVID-19 cases in the EU/EEA European Centre for Disease Prevention and Control (ECDC):Stockholm, [Online]. Available:https://www.ecdc.europa.eu/en/publications-data/resource-estimation-contact-tracing-quarantine-and-monitoring-activities-covid-19.pdf. Accessed 07 June 2020
6. [6] L. Wang and A. Wong, “COVID-Net: A tailored deep convolutional neural network design for detection of COVID-19 cases from chest radiography images,” arXiv 2020 preprint arXiv:2003.09871.
7. [7] T. Ai, Z. Yang, H. Hou, C. Zhan, C. Chen, W. Lv, Q. Tao, Z. Sun, and L. Xia, “Correlation of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in China: a report of 1014 cases,” Radiology, 200642, 2020.
8. [8] N. Chen, M. Zhou , X. Dong, J. Qu, F. Gong , Y. Han, et al., "Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study," The Lancet, 395, 507-513, 2020.

9. [9] S. Wang , B. Kang, J. Ma , X. Zeng , M. Xiao, J. Guo, et al., "A deep learning algorithm using CT images to screen for Corona Virus Disease (COVID-19)," MedRxiv, 2020.
10. [10] J. P. Kanne, B. P. Little, J.H. Chung, B.M. Elicker, L.H. Ketai, “Essentials for radiologists on COVID-19: an update—radiology scientific expert panel,” Radiology, 2020.
11. [11] J. Zhang, Y. Xie, Y. Li, C. Shen, and Y. Xia, “COVID-19 screening on chest x-ray images using deep learning based anomaly detection,” arXiv 2020,preprint arXiv:2003.12338.
12. [12] O. Gozes , M. Frid-Adar , H. Greenspan , P. D. Browning, et al., “Rapid AI development cycle for the coronavirus (COVID-19) pandemic: Initial results for automated detection & patient monitoring using deep learning CT image analysis,” arXiv 2020,preprint arXiv:2003.05037.
13. [13] T. Ozturk, M. Talo, E. A. Yildirim, U. B. Baloglu, O. Yildirim, and U. R. Acharya, “Automated detection of COVID-19 cases using deep neural networks with X-ray images,” Comput. Biol., 103792, 2020.
14. [14] E. Soares, P. Angelov, S. Biaso, M. H. Froes, D. K. Abe, “SARS-CoV-2 CT-scan dataset: A large dataset of real patients CT scans for SARS-CoV-2 identification,” medRxiv, 2020.
15. [15] A. Bernheim , X. Mei , M. Huang , Y. Yang , Z. A. Fayad , N. Zhang, et al., “Chest CT findings in coronavirus disease-19 (COVID-19): relationship to duration of infection,” Radiology, 200463, 2020.
16. [16] W. Zhao, Z. Zhong, X. Xie, Q. Yu, and J. Liu, “Relation between chest CT findings and clinical conditions of coronavirus disease (COVID-19) pneumonia: a multicenter study,” Am J Roentgenol, 214(5), 1072-1077, 2020.
17. [17] F. Shan , Y. Gao, J. Wang, W. Shi, N. Shi, et al., “Lung infection quantification of COVID-19 in CT images with deep learning,” arXiv 2020,preprint arXiv:2003.04655.
18. [18] R. M. Elavarasan and R. Pugazhendhi, “Restructured society and environment: A review on potential technological strategies to control the COVID-19 pandemic,” Sci Total Environ., 138858, 2020.
19. [19] Fastai [Online].Available: https://www.fast.ai/ Accessed 07 June 2020.
20. [20] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE conference on computer vision and pattern recognition, 2016, 770-778.
21. [21] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv 2014 Sep: preprint arXiv:1409.1556.
22. [22] F. N. Iandola, S. Han, M.W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size,” arXiv 2016, preprint arXiv:1602.07360.
23. [23] ImageNET [Online].Available: http://www.image-net.org/papers/imagenet_cvpr09.bi Accessed 07 June 2020.
24. [24] I. Loshchilov and F. Hutter, “SGDR: Stochastic gradient descent with warm restarts,” arXiv 2016, preprint arXiv:1608.03983.
25. [25] A. Holzinger, G. Langs, H. Denk, K. Zatloukal, and H. Müller, “Causability and explainability of artificial intelligence in medicine,” Wires Data Min Knowl., 9, 1312, 2019.
26. [26] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-CAM: Visual explanations from deep networks via gradient-based localization,” in Proc. IEEE international conference on computer vision, 2017, 618-626.
27. [27] Y. Bengio, A. Courville, and P. Vincent, “Representation learning: A review and new perspectives,” IEEE Trans Pattern Anal Mach Intell, 35, 1798-1828, 2013.
28. [28] A. Mahendran and A. Vedaldi, "Salient deconvolutional networks," in Proc. Computer Vision – ECC V, 2016, 120-135.
29. [29] T. Fawcett, “An introduction to ROC analysis,” Pattern Recognit Lett., 27, 861-864, 2006.