X-Ray Görüntülerinden COVID-19 Tespiti için Derin Öğrenme Temelli Bir Yaklaşım

SARS-CoV-2 virüsü kaynaklı COVID-19 hastalığının yayılma seyrinin kontrol altına alınmasında erken tespiti önemli rol oynamaktadır. Ters transkripsiyon-polimeraz zincir reaksiyonu (RT-PCR) koronavirüsün teşhisinde sıklıkla kullanılmaktadır. Ancak testler hastalığın her evresinde doğru sonuç verememektedir ve sonuçların çıkması için geçen süre hastalığın yayılması sürecini kolaylaştırmaktadır. Erken evrelerde COVID-19 tanısı koymak için X-ışını (X-Ray) Bilgisayarlı Tomografi (BT) gibi daha az temasa bağlı ve daha hızlı sonuç verebilecek tıbbi radyolojik görüntüleme yöntemleri kullanılmaktadır. Radyolojik görüntüler üzerinden hastalık tespitinde derin öğrenme yaklaşımlarının kullanımı son yıllarda çok ilgi görmektedir. Bu çalışmada akciğer radyolojik görüntülerinden COVID-19’un hızlı ve doğru teşhisi amacıyla derin öğrenme temelli bir yaklaşım kullanılmıştır. Yaklaşımın başarım incelemesi açık kaynaklı bir COVID-19 veri kümesi üzerinde gerçekleştirilmiştir.

Anahtar Kelimeler:

COVID-19, Derin Öğrenme, Evrişimsel Sinir Ağları(CNN), Akciğer X-Ray

A Deep Learning-Based Approach for Detection of COVID-19 from X-Ray Images

COVID-19 is a disease caused by the SARS-CoV-2 virus. Early detection and diagnosis of COVID-19 play an important role in controlling the spread of the disease. Reverse transcription-polymerase chain reaction (RT-PCR) is frequently used in the diagnosis of coronavirus. However, tests cannot give accurate results at every stage of the disease. The time taken for test results facilitates the spread of the disease. Medical radiological imaging methods such as X-ray (X-Ray) and Computed Tomography (CT) are used to diagnose COVID-19 in the early stages, which are less contact-dependent and can provide faster results. The use of deep learning approaches in disease detection through radiological images very popular in recent years. In this study, a deep learning-based approach was used for rapid and accurate diagnosis of COVID-19 from lung radiological images. The performance of the approach was examined on an open-source COVID-19 dataset.

Keywords:

COVID-19, Deep Learning, Convolutional Neural Network(CNN), Chest X-Rays,

PDF

___

Aparna, G., Gowri, S., Bharathi, R., S, V. J., J, J., & P, A. (2021). COVID-19 Prediction using X-Ray Images. 2021 5th International Conference on Trends in Electronics and Informatics (ICOEI) (pp. 903-908). IEEE.
Apostolopoulos, I. D., Aznaouridis, S., & Tzani, M. (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.
Bustin, S. (2000). Absolute quantification of mRNA using real-time reverse transcription polymerase chain reaction assays. Journal of molecular endocrinology.
Chowdhury, M. E., Rahman, T., Khandakar, A., Mazhar, R., Kadir, M. A., Mahbub, Z. B., . . . Islam, T. I. (2020). Can AI help in screening Viral and COVID-19 pneumonia? IEEE Access, 132665-132676.
Ciresan, D. C., Meier, U., Masci, J., Gambardella, L. M., & Schmidhuber, J. (2011). Flexible, High Performance Convolutional Neural Networks for Image Classification. International Joint Conference on Artificial Intelligence IJCAI-2011, (pp. 1237-1242). Barcelona.
Condaragiu, S., & Ciocoiu, I. B. (2021). Evaluation of Convolutional Neural Networks for COVID-19 Detection from Chest X-Ray Images. 2021 International Symposium on Signals, Circuits and Systems, (pp. 1-4).
COVID-19 Bilgilendirme Platformu. (2021, Kasım 22). Retrieved from T.C. Sağlık Bakanlığı COVID-19 Bilgilendirme Platformu: https://covid19.saglik.gov.tr/TR-66300/covid-19-nedir-.html
COVID-19 Coronavirus Pandemic. (2021, Kasım 29). Retrieved from Worldometers: https://www.worldometers.info/coronavirus/
Ghadezadeh, M., & Asadi, F. (2021). Deep Learning in the Detection and Diagnosis of COVID-19 Using Radiology Modalities: A Systematic Review. Hindawi Journal of Healthcare Engineering.
Harsono, I. W., Liawatimena, S., & Cenggoro, T. W. (2020). Lung nodule detection and classification from Thorax CT-scan using RetinaNet with transfer learning. Journal of King Saud University - Computer and Information Sciences.
Hussain, M. G., & Ye, S. (2021). Recognition of COVID-19 Disease Utilizing X-Ray Imaging of the Chest Using CNN. 2021 International Conference on Computing, Electronics & Communications Engineering (iCCECE), (pp. 71-76).
İnik, Ö., & Ülker, E. (2017). Derin Öğrenme ve Görüntü Analizinde Kullanılan Derin Öğrenme Modelleri. Gaziosmanpaşa Bilimsel Araştırma Dergisi, 85-104.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems 25 (NIPS 2012).
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep Learning. Nature, 436-44.
Liu, J. (2021). Review of Deep Learning-based Approaches for COVID-19 Detection. 2021 2nd International Conference on Computing and Data Science (CDS) (pp. 366-371). Stanford, CA, USA: IEEE.
Lu, M. T., Lu, M. T., Lu, M. T., Lu, M. T., Aerts, H. J., & Hoffmann, U. (2019). Deep Learning to Assess Long-term Mortality From Chest Radiographs. JAMA Netw Open vol. 2,7, 7416.
Mahmud, M., Kaiser, M. S., Hussain, A., & Vassanelli, S. (2018). Applications of Deep Learning and Reinforcement Learning to Biological Data. IEEE transactions on neural networks and learning systems, 29(6), 2063-2079.
Mahmud, M., Kaiser, M. S., McGinnity, T. M., & Hussain, A. (2021). Deep Learning in Mining Biological Data. Cognitive computation, 1–33.
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.
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.
Özbay, E., & Özbay, F. A. (2021). Covid-19 Detection from CT images with Deep Learning and Classification Approaches. Dicle University Journal of Engineering: Vol. 12.
Panwar, H., Gupta, P., Siddiqui, M. K., & Morales-Menendez, R. (2020). Application of deep learning for fast detection of COVID-19 in X-Rays. Chaos, Solitons and Fractals.
Rahman, T., Chowdhury, M., & Khandakar, A. (2021). COVID-19 Radiography Database. Retrieved from Kaggle: https://www.kaggle.com/tawsifurrahman/covid19-radiography-database
Rahman, T., Khandakar, A., Qiblawey, Y., Tahir, A., Kiranyaz, S., Kashem, S. B., . . . Chowdhury, M. E. (2021). Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images. Computers in Biology and Medicine,132, 104319.
Simonyan, K., & Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. Computer Science.
Şeker, A., Diri, B., & Balık, H. H. (2017). Derin Öğrenme Yöntemleri Ve Uygulamaları Hakkında Bir İnceleme. Gazi Mühendislik Bilimleri Dergisi (GMBD), 47-64.
Yılmaz, A. (2021). Çok kanallı CNN mimarisi ile X-Ray görüntülerinden COVID-19 tanısı. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi , 1761-1774.
Yılmaz, A., & Kaya, U. (2019). Derin Öğrenme.
Yılmaz, E. (2016). Fetal State Assessment from Cardiotocogram Data Using Artificial Neural Networks. Journal of Medical and Biological Engineering 36(6).