A Deep Learning-Based System to Assist Radiologists in Detecting COVID-19 Disease from Chest Computed Tomography Images

Year 2023, Volume: 13 Issue: 1, 72 - 96, 15.03.2023

Oğuzhan Katar , Erkan Duman

https://doi.org/10.31466/kfbd.1168320

Abstract

The COVID-19 pandemic has had a significant negative impact on the world in various ways. In an effort to mitigate the negative effects of the pandemic, this study proposes a deep learning approach for the automatic detection of COVID-19 from chest computed tomography (CT) images. This would enable healthcare professionals to more efficiently identify the presence of the virus and provide appropriate care and support to infected individuals. The proposed deep learning approach is based on binary classification and utilizes members of the pre-trained EfficientNet model family. These models were trained on a dataset of real patient images, called the EFSCH-19 dataset, to classify chest CT images as positive or negative for COVID-19. The results of the predictions made on the test images showed that all models achieved accuracy values of over 98%. Among these models, the EfficientNet-B2 model performed the best, with an accuracy of 99.75%, sensitivity of 99.50%, specificity of 100%, and an F1 score of 99.75%. In addition to the high accuracy achieved in the classification of chest CT images using the proposed pre-trained deep learning models, the gradient-weighted class activation mapping (Grad-CAM) method was also applied to further understand and interpret the model's predictions.

Keywords

COVID-19, Computed Tomography, EfficientNet, Classification, Grad-CAM

Göğüs Bilgisayarlı Tomografi Görüntülerinden COVID-19 Hastalığını Tespit Etmede Radyologlara Yardımcı Derin Öğrenme Tabanlı Bir Sistem

Abstract

COVID-19 pandemisinin dünya üzerinde çeşitli şekillerde önemli bir olumsuz etkisi oldu. Pandeminin olumsuz etkilerini azaltmak amacıyla bu çalışma, göğüs bilgisayarlı tomografi (BT) görüntülerinden COVID-19'un otomatik tespiti için bir derin öğrenme yaklaşımı önermektedir. Bu, sağlık uzmanlarının virüsün varlığını daha verimli bir şekilde tanımlamasını ve enfekte bireylere uygun bakım ve destek sağlamasını sağlayacaktır. Önerilen derin öğrenme yaklaşımı ikili sınıflandırmaya dayanmaktadır ve önceden eğitilmiş EfficientNet model ailesinin üyelerini kullanmaktadır. Bu modeller, göğüs BT görüntülerini COVID-19 için pozitif veya negatif olarak sınıflandırmak için EFSCH-19 veri seti adı verilen gerçek hasta görüntülerinden oluşan bir veri seti üzerinde eğitildi. Test görüntülerinde yapılan tahminlerin sonuçları, tüm modellerin %98'in üzerinde doğruluk değerlerine ulaştığını gösterdi. Bu modeller arasında EfficientNet-B2 modeli %99,75 doğruluk, %99,50 duyarlılık, %100 özgüllük ve %99,75 F1 skoru ile en iyi performansı gösterdi. Önerilen önceden eğitilmiş derin öğrenme modelleri kullanılarak göğüs BT görüntülerinin sınıflandırılmasında elde edilen yüksek doğruluğa ek olarak, modelin tahminlerini daha iyi anlamak ve yorumlamak için gradyan ağırlıklı sınıf aktivasyon eşleşme (Grad-CAM) yöntemi de uygulandı.

Keywords

COVID-19, Bilgisayarlı Tomografi, EfficientNet, Sınıflandırma, Grad-CAM

References

• Tekin, A. (2021). Tarihten Günümüze Epidemiler, Pandemiler ve Ekonomik Sonuçları. Süleyman Demirel Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 40, 330-355.
• Issever, H., Issever, T., and Oztan, G. (2020). COVID-19 epidemiyolojisi. Sağlık Bilimlerinde İleri Araştırmalar Dergisi, 3(S1), 1-13.
• Ahmad, T., Khan, M., Musa, T. H., Nasir, S., Hui, J., Bonilla-Aldana, D. K., and Rodriguez-Morales, A. J. (2020). COVID-19: Zoonotic aspects. Travel medicine and infectious disease, 36, 101607.
• Hua, J., and Shaw, R. (2020). Corona virus (Covid-19)“infodemic” and emerging issues through a data lens: The case of china. International journal of environmental research and public health, 17(7), 2309.
• Madabhavi, I., Sarkar, M., and Kadakol, N. (2020). COVID-19: a review. Monaldi Archives for Chest Disease, 90(2).
• Wadman, M. (2021). SARS-CoV-2 infection confers greater immunity than shots. Science, 373(6559), 1067-1068.
• Giri, B., Pandey, S., Shrestha, R., Pokharel, K., Ligler, F. S., and Neupane, B. B. (2021). Review of analytical performance of COVID-19 detection methods. Analytical and bioanalytical chemistry, 413(1), 35-48.
• Corman, V. M., Landt, O., Kaiser, M., Molenkamp, R., Meijer, A., Chu, D. K., and Drosten, C. (2020). Detection of 2019 novel coronavirus (2019-nCoV) by real-time RT-PCR. Eurosurveillance, 25(3), 2000045.
• Wu, F., Zhao, S., Yu, B., Chen, Y. M., Wang, W., Song, Z. G., and Zhang, Y. Z. (2020). A new coronavirus associated with human respiratory disease in China. Nature, 579(7798), 265-269.
• Zali, A., Sohrabi, M. R., Mahdavi, A., Khalili, N., Taheri, M. S., Maher, A., and Hanani, K. (2021). Correlation between low-dose chest computed tomography and RT-PCR results for the diagnosis of COVID-19: A report of 27,824 cases in tehran, Iran. Academic Radiology, 28(12), 1654-1661.
• Kommoss, F. K., Schwab, C., Tavernar, L., Schreck, J., Wagner, W. L., Merle, U., and Longerich, T. (2020). The pathology of severe COVID-19-related lung damage: Mechanistic and therapeutic implications. Deutsches Ärzteblatt International, 117(29-30), 500.
• Ghaderzadeh, M., and Asadi, F. (2021). Deep learning in the detection and diagnosis of COVID-19 using radiology modalities: a systematic review. Journal of healthcare engineering, 2021.
• Ng, M. Y., Lee, E. Y., Yang, J., Yang, F., Li, X., Wang, H., and Kuo, M. D. (2020). Imaging profile of the COVID-19 infection: radiologic findings and literature review. Radiology: Cardiothoracic Imaging, 2(1).
• Fields, B. K., Demirjian, N. L., Dadgar, H., and Gholamrezanezhad, A. (2021, July). Imaging of COVID-19: CT, MRI, and PET. In Seminars in Nuclear Medicine, 51(4), 312-320.
• Gundel, S., Setio, A. A., Ghesu, F. C., Grbic, S., Georgescu, B., Maier, A., and Comaniciu, D. (2021). Robust classification from noisy labels: Integrating additional knowledge for chest radiography abnormality assessment. Medical Image Analysis, 72, 102087.
• Chartrand, G., Cheng, P. M., Vorontsov, E., Drozdzal, M., Turcotte, S., Pal, C. J., and Tang, A. (2017). Deep learning: a primer for radiologists. Radiographics, 37(7), 2113-2131.
• Arsalan, M., Owais, M., Mahmood, T., Choi, J., and Park, K. R. (2020). Artificial intelligence-based diagnosis of cardiac and related diseases. Journal of Clinical Medicine, 9(3), 871.
• Owais, M., Arsalan, M., Choi, J., Mahmood, T., and Park, K. R. (2019). Artificial intelligence-based classification of multiple gastrointestinal diseases using endoscopy videos for clinical diagnosis. Journal of clinical medicine, 8(7), 986.
• Mainak, B., Venkatanareshbabu, K., Luca, S., Damodar, R. E., Elisa, C. G., Tato, M. R., and Andrew, N. (2019). State-of-the-art review on deep learning in medical imaging. Frontiers in Bioscience-Landmark, 24(3), 380-406.
• Chin, C. L., Lin, B. J., Wu, G. R., Weng, T. C., Yang, C. S., Su, R. C., and Pan, Y. J. (2017, November). An automated early ischemic stroke detection system using CNN deep learning algorithm. 8th International conference on awareness science and technology (pp. 368-372).
• Yildirim, K., Bozdag, P. G., Talo, M., Yildirim, O., Karabatak, M., and Acharya, U. R. (2021). Deep learning model for automated kidney stone detection using coronal CT images. Computers in biology and medicine, 135, 104569.
• Khan, S., Islam, N., Jan, Z., Din, I. U., and Rodrigues, J. J. C. (2019). A novel deep learning based framework for the detection and classification of breast cancer using transfer learning. Pattern Recognition Letters, 125, 1-6.
• Bogu, G. K., and Snyder, M. P. (2021). Deep learning-based detection of COVID-19 using wearables data. MedRxiv.
• Pahar, M., Klopper, M., Warren, R., and Niesler, T. (2021). COVID-19 cough classification using machine learning and global smartphone recordings. Computers in Biology and Medicine, 135, 104572.
• Wang, L., Lin, Z. Q., and Wong, A. (2020). Covid-net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. Scientific Reports, 10(1), 1-12.
• Luz, E., Silva, P., Silva, R., Silva, L., Guimarães, J., Miozzo, G., and Menotti, D. (2022). Towards an effective and efficient deep learning model for COVID-19 patterns detection in X-ray images. Research on Biomedical Engineering, 38(1), 149-162.
• Song, Y., Zheng, S., Li, L., Zhang, X., Zhang, X., Huang, Z., and Yang, Y. (2021). Deep learning enables accurate diagnosis of novel coronavirus (COVID-19) with CT images. IEEE/ACM Transactions on computational biology and bioinformatics, 18(6), 2775-2780.
• Bozkurt, F. (2022). A deep and handcrafted features‐based framework for diagnosis of COVID‐19 from chest x‐ray images. Concurrency and Computation: Practice and Experience, 34(5), e6725.
• Marques, G., Agarwal, D., and de la Torre Díez, I. (2020). Automated medical diagnosis of COVID-19 through EfficientNet convolutional neural network. Applied soft computing, 96, 106691.
• Wang, S., Kang, B., Ma, J., Zeng, X., Xiao, M., Guo, J., and Xu, B. (2021). A deep learning algorithm using CT images to screen for Corona Virus Disease (COVID-19). European radiology, 31(8), 6096-6104.
• Comert, S. S., and Kiral, N. (2020). Radiological Findings of COVID-19 Pneumonia/COVID-19 Pnomonisinin Radyolojik Bulgulari. Southern Clinics of Istanbul Eurasia, 31(SI), 16-23.
• Tan, M., and Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. International conference on machine learning (pp. 6105-6114).
• Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pp. 248-255
• Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A., and Fei-Fei, L. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115(3), 211-252.
• Collins, T. J. (2007). ImageJ for microscopy. Biotechniques, 43(S1), S25-S30.
• Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE international conference on computer vision (pp. 618-626).
• Ismael, A. M., and Şengür, A. (2021). Deep learning approaches for COVID-19 detection based on chest X-ray images. Expert Systems with Applications, 164, 114054.
• Ozturk, T., Talo, M., Yildirim, E. A., Baloglu, U. B., Yildirim, O., and Acharya, U. R. (2020). Automated detection of COVID-19 cases using deep neural networks with X-ray images. Computers in biology and medicine, 121, 103792.
• Shah, V., Keniya, R., Shridharani, A., Punjabi, M., Shah, J., and Mehendale, N. (2021). Diagnosis of COVID-19 using CT scan images and deep learning techniques. Emergency radiology, 28(3), 497-505.
• Rahimzadeh, M., Attar, A., and Sakhaei, S. M. (2021). A fully automated deep learning-based network for detecting covid-19 from a new and large lung ct scan dataset. Biomedical Signal Processing and Control, 68, 102588.
• Gupta, A., Gupta, S., and Katarya, R. (2021). InstaCovNet-19: A deep learning classification model for the detection of COVID-19 patients using Chest X-ray. Applied Soft Computing, 99, 106859.
• Katar, O., and Duman, E. (2021). Deep Learning Based Covid-19 Detection With A Novel CT Images Dataset: EFSCH-19. Avrupa Bilim ve Teknoloji Dergisi, (29), 150-155.
• Gupta, K., and Bajaj, V. (2023). Deep learning models-based CT-scan image classification for automated screening of COVID-19. Biomedical Signal Processing and Control, 80, 104268.
• Zhou, T., Lu, H., Yang, Z., Qiu, S., Huo, B., and Dong, Y. (2021). The ensemble deep learning model for novel COVID-19 on CT images. Applied soft computing, 98, 106885.
• Yang, X., He, X., Zhao, J., Zhang, Y., Zhang, S., and Xie, P. (2020). COVID-CT-dataset: a CT scan dataset about COVID-19. arXiv preprint arXiv:2003.13865.
• URL-1: https://www.arcgis.com/apps/dashboards/bda7594740fd40299423467b48e9ecf6, (Date Accessed: 27 August 2022).
• URL-2: https://keras.io/api/applications/, (Date Accessed: 24 December 2022).