Derin öğrenme tabanlı yaklaşımlarla akciğer röntgen görüntüleri üzerinden COVID-19 ve bakteri kaynaklı zatürrenin otomatik teşhisi

Yıl 2024, Cilt: 14 Sayı: 4, 1161 - 1176, 15.12.2024

Ömer Faruk Nasip

https://doi.org/10.17714/gumusfenbil.1487192

Öz

COVID-19 tüm dünyada yüksek ölüm oranına neden olan virüs kaynaklı bir hastalıktır. Virüsle enfekte olan hastalar kuru öksürük, nefes darlığı, ateş ve diğer semptomların yanı sıra belirgin radyografik görsel özelliklere sahiptir. Bununla birlikte benzer semptomları içeren bir başka hastalık ise zatürredir. COVID-19 ve zatürrenin doğru teşhisi, hekimlerin hastalara uygun tedavilerle müdahale etmesine yardımcı olmak için büyük önem taşımaktadır. Ters Transkripsiyon - Polimeraz Zincir Reaksiyonu (RT-PCR) testi, COVID-19 teşhisi için rutin olarak kullanılmasına rağmen maliyetli, zaman alıcı ve yanlış sonuçlara eğilimlidir. Bu nedenle teşhis için düşük maliyetli, hızlı ve başarılı sonuç veren tıbbi görüntüleme tabanlı bilgisayar destekli çalışmalar önemli bir alternatiftir. Bu çalışmada, COVID-19 hastaları, bakteri kaynaklı zatürre hastaları ve sağlıklı bireylerin akciğer röntgen görüntüleri üzerinden otomatik olarak teşhis edilmesini amaçlayan derin öğrenme tabanlı üç farklı yaklaşım önerilmiştir. İlk yaklaşımda öğrenme aktarımı, ikinci yaklaşımda öznitelik çıkarımı ve üçüncü yaklaşımda ise öznitelik seçimi yöntemi uygulanmıştır. Önceden eğitilmiş evrişimli derin sinir ağları Vgg19, ResNet50 ve DenseNet201 öğrenme aktarımı ve öznitelik çıkarımı amacıyla kullanılmıştır. Öznitelik çıkarımı ve öznitelik seçimi yaklaşımında sınıflandırıcı olarak Destek Vektör Makinesi tercih edilmiştir. Çalışmada Kaggle tarafından erişime sunulan ve herkese açık üç farklı akciğer röntgen görüntüsü veri tabanından elde edilen her bir sınıfa ait 1500 adet olmak üzere toplamda 4500 adet röntgen görüntüsü kullanılmıştır. Öğrenme aktarımı yaklaşımında ResNet50 ile %99.2, öznitelik çıkarımı yaklaşımında DenseNet201 ile %98.7, öznitelik seçimi yaklaşımında ise ResNet50 ile %98.3 doğruluk elde edilmiştir. Bunun yanı sıra önerilen öznitelik seçimi yaklaşımı sayesinde sınıflandırma doğruluğunda belirgin bir düşüş yaşanmadan sınıflandırma hızı yaklaşık beş kat artmıştır.

Anahtar Kelimeler

Derin öğrenme, COVID-19, Zatürre

Automatic diagnosis of COVID-19 and bacterial pneumonia from lung x-ray images with deep learning-based approaches

Öz

COVID-19 is a virus-induced disease that causes a high mortality rate around the world. Patients infected with the virus have distinct radiographic visual features as well as dry cough, shortness of breath, fever, and other symptoms. However, another disease with similar symptoms is pneumonia. Accurate diagnosis of COVID-19 and pneumonia is of great importance to help physicians treat patients with appropriate treatments. Although Reverse Transcription - Polymerase Chain Reaction (RT-PCR) testing is routinely used for COVID-19 diagnosis, it is costly, time-consuming, and prone to false results. For this reason, medical imaging-based computer-aided studies that provide low-cost, fast and successful results for diagnosis are an important alternative. In this study, three different deep learning-based approaches are proposed, aiming to automatically diagnosis COVID-19 patients, bacterial pneumonia patients and healthy individuals through lung X-ray images. In the first approach, the learning transfer method was applied, in the second approach, feature extraction, and in the third approach, the feature selection method was applied. Pre-trained convolutional deep neural networks Vgg19, ResNet50 and DenseNet201 were used for learning transfer and feature extraction. Support Vector Machine was preferred as the classifier in the feature extraction and feature selection approach. A total of 4500 x-ray images, 1500 of each class obtained from three different publicly available lung x-ray image databases made available by Kaggle, were used in the study. In the learning transfer approach, 99.2% accuracy was achieved with ResNet50, in the feature extraction approach, 98.7% accuracy was achieved with DenseNet201, and in the feature selection approach, 98.3% accuracy was achieved with ResNet50. In addition, thanks to the proposed feature selection approach, the classification speed increased approximately five times without a significant decrease in classification accuracy.

Anahtar Kelimeler

Deep learning, COVID-19, Pnomoni

Kaynakça

• AbdElhamid, A.A., AbdElhalim, E., Mohamed, M.A., & Khalifa, F. (2022). Multi-classification of chest x-rays for Covid-19 diagnosis using deep learning algorithms. Applied Sciences, 12(4):2080. https://doi.org/10.3390/app12042080
• Abiyev, R. H., & Ismail, A. (2021). Covid-19 and pneumonia diagnosis in x-ray images using convolutional neural networks. Mathematical Problems in Engineering, 2021, 14 pages. https://doi.org/10.1155/2021/3281135
• Agchung. (2023, December 21). https://github.com/agchung
• Aggarwal, S., Gupta, S., Alhudhaif, A., Koundal, D., Gupta, R., & Polat, K. (2022). Automated Covid-19 detection in chest X-ray images using fine-tuned deep learning architectures. Expert Systems, 39(3), https://doi.org/10.1111/exsy.12749
• Apostolopoulos, I. D., & Mpesiana, T. A. (2020). Covid-19: automatic detection from X-ray images utilizing transfer learning with convolutional neural networks. Physical and Engineering Sciences in Medicine, 43(2), 635–640. https://doi.org/10.1007/s13246-020-00865-4
• Azimi-Pour, M., Eskandari-Naddaf, H., & Pakzad, A. (2020). Linear and non-linear SVM prediction for fresh properties and compressive strength of high volume fly ash self-compacting concrete. Construction and Building Materials, vol 230. https://doi.org/10.1016/j.conbuildmat.2019.117021
• Chen, C. W., Tsai, Y. H., Chang, F.R., & Lin, W.C. (2020). Ensemble feature selection in medical datasets: Combining filter, wrapper, and embedded feature selection results. Expert Systems, 37(5). https://doi.org/10.1111/exsy.12553
• Chest X-ray (Covid-19 & Pneumonia). (2023, December 21). https://www.kaggle.com/prashant268/chest-xray-covid19-pneumonia
• Chest X-Ray Images (Pneumonia). (2023, December 21). https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia
• Chowdhury, M., Rahman, T., Khandakar, A., Mazhar, R., Kadir, M., Mahbub, Z., Islam, K., Khan, M. S., Iqbal, A., Al-Emadi, N., Reaz, M.B.I., & Islam, M. (2020). Can AI help in screening viral and Covid-19 pneumonia?. IEEE Access. 8. 132665 -132676. doi: 10.1109/ACCESS.2020.3010287
• Classification of COVID viral bacterial pneumonia. (2023, December 21). https://www.kaggle.com/sriramthakur/classification-of-covid-viral-bacterial-pneumonia
• CoronaHack-Chest X-Ray-Dataset. (2023, December 21). https://www.kaggle.com/datasets/praveengovi/coronahack-chest-xraydataset
• COVID-19 Detection X-Ray Dataset. (2023, December 21). https://www.kaggle.com/datasets/darshan1504/covid19-detection-xray-dataset
• COVID-19 Radiography Database. (2023, December 21). https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database
• Covid-19 Image Dataset (2023, December 21). https://www.kaggle.com/datasets/pranavraikokte/covid19-image-dataset
• Covid-chestxray-dataset. (2023, December 21). https://github.com/ieee8023/covid-chestxray-dataset
• Gopatoti, A., & Vijayalakshmi, P. (2022). CXGNet: A tri-phase chest X-ray image classification for Covid-19 diagnosis using deep CNN with enhanced grey-wolf optimizer. Biomedical Signal Processing and Control, Vol. 77, 103860, ISSN 1746-8094. https://doi.org/10.1016/j.bspc.2022.103860.
• Haryanto, T., Wasito, I., & Suhartanto, H. (2017). Convolutional neural network (CNN) for gland images classification. 11th International Conference on Information & Communication Technology and System (ICTS), pp. 55-60. doi: 10.1109/ICTS.2017.8265646.
• He, K., Zhang, X., Ren, S., & Sun J. (2015). Deep residual learning for image recognition. arXiv:1512.03385v1. https://doi.org/10.48550/arXiv.1512.03385
• Huang, G., Liu, Z., Maaten, L.V.D., & Weinberger, K.Q. (2017). Densely connected convolutional networks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2261-2269. doi: 10.1109/CVPR.2017.243
• Kaggle. (2023, December 5). https://www.kaggle.com
• Kaissis, G.A., Makowski, M.R., Rückert, D., & Braren, R.F. (2020). Secure, privacy-preserving and federated machine learning in medical imaging. Nature Machine Intelligence 2, 305-311.https://doi.org/10.1038/s42256-020-0186-1
• Kanne, J.P., Little, B.P., Chung, J.H., Elicker, B.M., & Ketai, L.H. (2020). Essentials for radiologists on Covid-19: An Update-Radiology Scientific Expert Panel. Radiology, 296(2). https://doi.org/10.1148/radiol.2020200527
• Kaya, M., & Eris, M. (2023). D3SENet: A hybrid deep feature extraction network for Covid-19 classification using chest X-ray images. Biomedical Signal Processing and Control, Vol. 82, 104559, ISSN 1746-8094. https://doi.org/10.1016/j.bspc.2022.104559
• Kilicarslan, S., Adem, K., & Celik, M. (2020). Diagnosis and classification of cancer using hybrid model based on ReliefF and convolutional neural network. Medical Hypotheses, 137, 109577. https://doi.org/10.1016/j.mehy.2020.109577
• Korot, E., Guan, Z., Ferraz, D., Wagner, S.K., Zhang, G., Liu, X., Faes, L., Pontikos, N., Finlayson, S.G., Khalid, H., Moraes, G., Balaskas, K., Denniston, A.K., & Keane, P.A. (2021). Code-free deep learning for multi-modality medical image classification. Nature Machine Intelligence 3, 288-298. https://doi.org/10.1038/s42256-021-00305-2
• Loey, M., Smarandache, F., & Khalifa, N.E. (2020). Within the lack of chest Covid-19 X-ray dataset: A novel detection model based on GAN and deep transfer learning. Symmetry, 12(4), 651. https://doi.org/10.3390/sym12040651
• Marmanis, D., Datcu, M., Esch, T., & Stilla, U. (2016). Deep learning Earth observation classification using ImageNet pretrained networks. IEEE Geoscience and Remote Sensing Letters, 13(1), pp. 105-109. doi: 10.1109/LGRS.2015.2499239
• Marques, G., Agarwal, D., & de la Torre Díez, I. (2020). Automated medical diagnosis of COVID-19 through EfficientNet convolutional neural network. Applied soft computing, 96, 106691. https://doi.org/10.1016/j.asoc.2020.106691
• Chen, N., Zhou, M., Dong, X., Qu, J., Gong, F., Han, Y., Qiu, Y., Wang, J., Liu, Y., Wei, Y., Xia, J., Yu, T., Zhang, X., & Zhang, L. (2020). Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study. Lancet (London, England), 395(10223), 507–513. https://doi.org/10.1016/S0140-6736(20)30211-7
• Narin, A. & Isler, Y. (2021). Detection of new coronavirus disease from chest x-ray images using pre-trained convolutional neural networks. Journal of the Faculty of Engineering and Architecture of Gazi University, 36(4):2095-2107. https://doi.org/10.17341/gazimmfd.827921
• Narin, A., Kaya, C., & Pamuk, Z. (2021). Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks. Pattern Analysis and Applications : PAA, 24(3), 1207–1220. https://doi.org/10.1007/s10044-021-00984-y
• Nasip, Ö.F., & Zengin, K. (2018). Deep learning based bacteria classification. 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Ankara, Turkey, pp. 1-5. doi: 10.1109/ISMSIT.2018.8566685
• Omuya, E.O., Okeyo, G.O., & Kimwele, M.W. (2021). Feature selection for classification using principal component analysis and information gain. Expert Systems with Applications, 174(11):114765. https://doi.org/10.1016/j.eswa.2021.114765
• Ozturk, T., Talo, M., Yildirim, E.A., Baloglu, U.B., Yildirim, O., & 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. https://doi.org/10.1016/j.compbiomed.2020.103792
• Pławiak, P. & Tadeusiewicz, R. (2014). Approximation of phenol concentration using novel hybrid computational intelligence methods. International Journal of Applied Mathematics and Computer Science, 24, 165-181. doi: 10.2478/amcs-2014-0013
• Pneumonia & COVID-19 Image Dataset. (2023, December 21). https://www.kaggle.com/gibi13/pneumonia-covid19-image-dataset
• Priyadarsini, R.P., Valarmathi, M.L., & Sivakumari, S. (2010). Gain ratio based feature selection method for privacy preservation. ICTACT Journal on Soft Computing 01(04):201-205. doi: 10.21917/ijsc.2011.0031
• Rahaman, M.M., Li, C., Yao, Y., Kulwa, F., Rahman, M.A., Wang, Q., Qi, S., Kong, F., Zhu, X., & Zhao, X. (2020). Identification of Covid-19 samples from chest X-Ray images using deep learning: A comparison of transfer learning approaches. Journal of X-ray Science and Technology, 28(5), 821–839. https://doi.org/10.3233/XST-200715
• Saeys, Y., Inza, I., & Larranaga, P. (2007). A review of feature selection techniques in bioinformatics. Bioinformatics, 23(19):2507-17. https://doi.org/10.1093/bioinformatics/btm344
• Sethy, P.K., Behera, S.K., Ratha, P.K., & Biswas, P. (2020). Detection of coronavirus disease (Covid-19) based on deep features and support vector machine. International Journal of Mathematical, Engineering and Management Sciences, 5(4), 643-651. https://doi.org/10.33889/IJMEMS.2020.5.4.052
• Simonyan, K. & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv. https://doi.org/10.48550/arXiv.1409.1556
• Singh, D., Kumar, V., Kaur, M., & Kumari, R. (2022). Early diagnosis of Covid-19 patients using deep learning-based deep forest model. Journal of Experimental & Theoretical Artificial Intelligence. https://doi.org/10.1080/0952813X.2021.2021300.
• Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., & Liu, C. (2018). A survey on deep transfer learning. arXiv. https://doi.org/10.48550/arXiv.1808.01974
• Tiwari, S. & Jain, A. (2021). Convolutional capsule network for Covid-19 detection using radiography images. International Journal of Imaging Systems and Technology, 31(2):525-539. https://doi.org/10.1002/ima.22566
• Toraman, S., Alakus, T.B., & Turkoglu, I. (2020). Convolutional capsnet: A novel artificial neural network approach to detect Covid-19 disease from X-ray images using capsule networks. Chaos, Solitons & Fractals, Vol. 140, 110122, ISSN 0960-0779. https://doi.org/10.1016/j.chaos.2020.110122
• 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, Vol. 140, 109761, ISSN 0306-9877. https://doi.org/10.1016/j.mehy.2020.109761
• Wang, L., Lin, Z.Q., & 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, 19549. https://doi.org/10.1038/s41598-020-76550-z
• Wang, L., Johnson, D., & Lin, Y. (2021). Using EEG to detect driving fatigue based on common spatial pattern and support vector machine. Turkish Journal of Electrical Engineering & Computer Sciences; 29(3): 1429-1444. https://doi.org/10.3906/elk-2008-83
• WHO COVID-19 Dashboard. (2024, February 10). https://covid19.who.int
• Wong, H.Y.F., Lam, H.Y.S, Fong, A.H., Leung, S.T., Chin, T.W., Lo, C.S.Y., Lui, M.M., Lee, J.C.Y., Chiu, K.W., Chung, T.W., Lee, E.Y.P., Wan, E.Y.F., Hung, I.F.N., Lam, T.P.W., Kuo, M.D., & Ng, M.Y. (2020). Frequency and distribution of chest radiographic findings in patients positive for Covid-19. Radiology. 296(2), E72–E78. https://doi.org/10.1148/radiol.2020201160
• Zhao, B., Huang, B., & Zhong, Y. (2017). Transfer learning with fully pretrained deep convolution networks for land-use classification. IEEE Geoscience and Remote Sensing Letters, 14(9), pp. 1436-1440. doi: 10.1109/LGRS.2017.2691013
• Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., & He, Q. (2020). A comprehensive survey on transfer learning. Proceedings of the IEEE, pp. 1-34. doi: 10.1109/JPROC.2020.3004555