Evaluation of Poor Prognosis in rRT-PCR Positive Covid-19 Cases with Using Deep Transfer Learning Network

Year 2022, , 505 - 521, 18.07.2022

İsmail Şalk , Özlem Polat , Mürşit Hasbek

https://doi.org/10.47495/okufbed.1024845

Abstract

The infection called Covid-19 caused by the new type of coronavirus (SARS-CoV-2) is an epidemic and deadly disease that spreads rapidly all over the world. Early detection of Covid-19 will enable the patient to receive appropriate treatment and increase the chance of survival. In this study, it is aimed to investigate the detection of poor prognosis from chest CT images in Covid-19 patients who died and healed using deep learning. For this purpose, a dataset containing a total of 5997 CT images were used and images were classified using the Inception-V3. In order to evaluate the classifier ROC curves are drawn, AUC and accuracy values are used as performance metrics. Inception-V3 model was run 10 times, and a maximum classification performance of 97,55% and an average of 97,01% was achieved. The classification results prove that Inception-V3 can classify CT images with a high accuracy rate for evaluation of Covid-19 prognosis.

Keywords

Covid-19, Convolutional neural networks, Transfer learning, Classification, Inception-V3

Derin Transfer Öğrenme Ağı Kullanılarak rRT-PCR Pozitif Covid-19 Olgularında Kötü Prognozun Değerlendirilmesi

Abstract

Yeni tip koronavirüsün (SARS-CoV-2) neden olduğu Covid-19 olarak isimlendirilen enfeksiyon, tüm dünyada hızla yayılan salgın ve ölümcül bir hastalıktır. Covid-19'un erken teşhisi, hastanın uygun tedavi almasını sağlayacak ve hayatta kalma şansını artıracaktır. Bu çalışmada derin öğrenme kullanılarak ölen ve iyileşen Covid-19 hastalarında göğüs BT görüntülerinden kötü prognoz tespitinin araştırılması amaçlanmıştır. Bu amaçla toplam 5997 CT görüntüsünü içeren bir veri seti kullanılmıştır; ve görüntüler Inception-V3 kullanılarak sınıflandırılmıştır. Sınıflandırıcıyı değerlendirmek için ROC eğrileri çizilir, performans ölçütleri olarak AUC ve doğruluk değerleri kullanılır. Inception-V3 modeli 10 kez çalıştırılmış ve maksimum %97,55 ve ortalama %97,01 sınıflandırma performansı elde edilmiştir. Sınıflandırma sonuçları, Inception-V3'ün CT görüntülerini Covid-19 prognozunun değerlendirilmesi için yüksek doğrulukla sınıflandırabildiğini kanıtlamaktadır.

Keywords

Covid-19, Konvolüsyonel sinir ağları, Transfer öğrenme, Sınıflama, Inception-V3

References

• Baraboshkin, E.E., Ismailova, L.S., Orlov, D.M., Zhukovskaya, E.A., Kalmykov, G.A., Khotylev, O.V., Baraboshkin, E.Y. and Koroteev, D.A. Deep convolutions for in-depth automated rock typing. Computers & Geosciences 2020; 135: 104330.
• Chollet, F. Keras. 2015. https://keras.io
• Covid-19 Guide. https://hsgm.saglik.gov.tr/depo/birimler/goc_sagligi/covid19/rehber/COVID-19_Rehberi20200414_eng_v4_002_14.05.2020.pdf, (last accessed date: 15.11.2021)
• Del Valle, D.M., Kim-Schulze, S., Huang, H.H., Beckmann, N.D., Nirenberg, S., Wang, B., Lavin, Y., Swartz, T.H., Madduri, D., Stock, A., Marron, T.U., Xie, H., Patel, M., Tuballes, K., Van Oekelen, O., Rahman, A., Kovatch, P., Aberg, J.A., Schadt, E., Jagannath, S., Mazumdar, M. et al., 2020, “An inflammatory cytokine signature predicts COVID-19 severity and survival”. Nature Medicine, 26(10), 1636-1643.
• Fawcett, T. An introduction to ROC analysis. Pattern Recognition Letters 2006; 27(8): 861-874.
• Goodfellow, I., Bengio, Y. and Courville, A. Deep Learning. MIT Press. 2016.
• Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S. and Lew, M.S. Deep learning for visual understanding: A review. Neurocomputing 2016; 187: 27-48.
• Kirienko, M., Ninatti, G., Cozzi, L., Voulaz, E., Gennaro, N., Barajon, I., Ricci, F., Carlo-Stella, C., Zucali, P., Sollini, M., Balzarini, L. and Chiti, A. Computed tomography (CT)-derived radiomic features differentiate prevascular mediastinum masses as thymic neoplasms versus lymphomas. La Radiologia Medica 2020; 125(10): 951-960.
• LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W. and Jackel, L.D. Backpropagation applied to handwritten zip code recognition. Neural Computation 1989; 1(4): 541-551.
• Liao, D., Zhou, F., Luo, L., Xu, M., Wang, H., Xia, J., Gao, Y., Cai, L., Wang, Z., Yin, P., Wang, Y., Tang, L., Deng, J., Mei, H. and Hu, Y. Haematological characteristics and risk factors in the classification and prognosis evaluation of COVID-19: a retrospective cohort study. Lancet Haematology 2020; 7(9): e671-e678.
• Martin, A., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mane, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P. Et al. TensorFlow: Large-scale machine learning on heterogeneous system (software available from: tensorflow.org), 2015.
• Nair, V. and Hinton, G.E. Rectified linear units improve restricted Boltzmann machines. In Proc.: 27th International Conference on Machine Learning (ICML'10), June 21-24, Haifa, Israel, 2010. 807–814.
• Park, H.J., Lee, S.M., Song, J.W., Lee, S.M., Oh, S.Y., Kim, N. and Seo, J.B. Texture-based automated quantitative assessment of regional patterns on initial CT in patients with idiopathic pulmonary fibrosis: Relationship to decline in forced vital capacity. American Journal of Roentgenology 2016; 207(5): 976-983.
• Shi, S., Qin, M., Shen, B., Cai, Y., Liu, T., Yang, F., Gong, W., Liu, X., Liang, J., Zhao, Q., Huang, H., Yang, B. and Huang, C. Association of cardiac injury with mortality in hospitalized patients with COVID-19 in Wuhan, China. JAMA Cardiology 2020; 5(7): 802-810.
• Simpson, S., Kay, F.U., Abbara, S., Bhalla, S., Chung, J.H., Chung, M., Henry, T.S., Kanne, J.P., Kligerman, S., Ko, J.P. and Litt, H. Radiological society of North America expert consensus statement on reporting chest CT findings related to COVID-19: Endorsed by the society of thoracic radiology, the American college of radiology, and RSNA. Journal of Thoracic Imaging 2020; 35(4): 219-227.
• Smith, A.R. Color gamut transform pairs. ACM SIGGRAPH Computer Graphics 1978; 12(3): 12-19.
• Szegedy, C., Ioffe, S., Vanhoucke, V. and Alemi, A. Inception-v4, Inception-ResNet and the impact of residual connections on learning. arXiv 2016, arXiv:1602.07261.
• Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V. and Rabinovich, A. Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition 2015a; 1-9.
• Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. and Wojna, Z. Rethinking the inception architecture for computer vision. arXiv, 2015b; arXiv:1512.00567.
• Wu, C., Chen, X., Cai, Y., Xia, J., Zhou, X., Xu, S., Huang, H., Zhang, L., Zhou, X., Du, C., Zhang, Y., Song, J., Wang, S., Chao, Y., Yang, Z., Xu, J., Zhou, X., Chen, D., Xiong, W., Xu, L., Zhou, F., Jiang, J., Bai, C., Zheng, J. and Song, Y. Risk factors associated with acute respiratory distress syndrome and death in patients with coronavirus disease 2019 pneumonia in Wuhan, China. JAMA Internal Medicine 2020; 180(7): 934-943.
• Wu, X., Hui, H., Niu, M., Li, L., Wang, L., He, B., Yang, X., Li, L., Li, H., Tian, J. and Zha, Y. Deep learning-based multi-view fusion model for screening 2019 novel coronavirus pneumonia: A multicentre study. European Journal of Radiology 2020; 128: 109041.
• Zeiler, M.D. Adadelta: An adaptive learning rate method. ArXiv 2012; arXiv:1212.5701.
• Zhang, K., Liu, X., Shen, J., Li, Z., Sang, Y., Wu, X., Zha, Y., Liang, W., Wang, C., Wang, K., Ye, L., Gao, M., Zhou, Z., Li, L., Wang, J., Yang, Z., Cai, H., Xu, J., Yang, L., Cai, W., Xu, W., Wu, S., Zhang, W., Jiang, S., Zheng, L., Zhang, X., Wang, L., Lu, L., Li, J., Yin, H., Wang, W., Li, O., Zhang, C. et al. Clinically applicable AI system for accurate diagnosis, quantitative measurements, and prognosis of COVID-19 pneumonia using computed tomography. Cell 2020; 181(6): 1423-1433.
• Zhang, Y., Li, M., Han, S., Ren, Q. and Shi, J. Intelligent identification for rock-mineral microscopic images using ensemble machine learning algorithms. Sensors 2019; 19(18): 3914.
• Zhou, F., Yu, T., Du, R., Fan, G., Liu, Y., Liu, Z., Xiang, J., Wang, Y., Song, B., Gu, X., Guan, L., Wei, Y., Li, H., Wu, X., Xu, J., Tu, S., Zhang, Y., Chen, H. and Cao, B. Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study. Lancet 2020; 395(10229): 1054-1062.