Transfer Öğrenme Mimarileri Kullanılarak Bilgisayarlı Tomografi Görüntülerinden Covid-19'un Yüksek Doğrulukla Sınıflandırılması

Year 2022, , 457 - 466, 30.09.2022

Farid Alareqi , Mehmet Zeki Konyar

https://doi.org/10.24012/dumf.1129870

Cited By: 1

Abstract

Covid-19 virüsü 2019 yılından beri milyonlarca kişinin ölümüne neden olmuştur. Enfekte vaka oranını mümkün oldukça düşük tutmak amacıyla, virüsü tespit etmek ve hasta kişileri teşhis etmek için, çeşitli testler kullanılmıştır. Yapay zekâ, PCR testi gibi geleneksel yöntemlerden daha iyi performans göstererek, tıbbi görüntülerde virüsü tespit etmede kullanılan yöntemlerden biri olarak etkinliğini kanıtlamıştır. Bu çalışmada, halka açık iki farklı veri seti üzerinde derin öğrenme yaklaşımı ile Covid-19 sınıflandırması yapmak üzere VGG19, ResNet50, EfficientNetB0, DenseNet201 ve Xception transfer öğrenme mimarileri kullanılmıştır. Önerilen çalışmada daha yüksek doğruluklar elde etmek için modellerin hiper parametreleri üzerinde ince ayarlar yapılmıştır. Önerilen modellerin kullanılmasıyla en iyi sınıflandırma doğrulukları, birinci veri setinde VGG19 ile %98.04 ve ikinci veri setinde ResNet50 ile %99.62 olarak elde edilmiştir. Her iki veri setinin test kümelerinde VGG19 ve DenseNet201 modelleri güncel literatür yöntemleriyle kıyaslanabilir doğruluklara erişmiştir. İkinci veri setinin sınıflandırma sonuçları, bu makalede kullanılan modellerin ortalama %99.51 ile diğer literatür yöntemlerinden daha yüksek doğruluklara ulaştığını göstermiştir.

Keywords

Covid-19, DenseNet201, Derin öğrenme, Transfer Öğrenme, VGG19

Supporting Institution

Kocaeli Üniversitesi Bilimsel Araştırma Projeleri Koordinasyon Birimi

Project Number

2021-2751

Thanks

Bu çalışma Kocaeli Üniversitesi Yazılım Mühendisliği Bölümü Yazılım Teknolojileri Araştırma Laboratuvarı’nda (STAR Lab.) gerçekleştirilmiştir.

References

• F. Al-Areqi, M. Z. Konyar, “Effectiveness evaluation of different feature extraction methods for classification of covid-19 from computed tomography images: A high accuracy classification study”, Biomedical Signal Processing and Control, vol 76, 103662, 2022.
• A. Widders, A. Broom, and J. Broom, “SARS-CoV-2: The viral shedding vs infectivity dilemma” Infection, disease & health, vol. 25, no 3, pp. 210–215, 2020.
• A Ozyigit, “Understanding Covid-19 transmission: The effect of temperature and health behavior on transmission rates”, Infection, disease & health, vol. 25, no 4, pp. 233–238, 2020.
• M. A. Shereen et. al. “COVID-19 infection: Origin, transmission, and characteristics of human coronaviruses”, Journal of advanced research, vol. 24, pp. 91–98, 2020.
• J. Cui, F. Li and Z. L. Shi, “Origin and evolution of pathogenic coronaviruses”, Nature reviews. Microbiology, vol. 17, no. 3, pp. 181–192. 2019.
• S. J. Dancer, “Covid-19 exposes the gaps in infection prevention and control”, Infection, disease & health, vol. 25, no. 4, pp. 223–226, 2020.
• W. Wang, et al., “Detection of SARS-CoV-2 in Different Types of Clinical Specimens” JAMA, vol. 323, no. 18, pp. 1843–1844, 2020.
• S. JavadiMoghaddam and H. Gholamalinejad, “A novel deep learning based method for COVID-19 detection from CT image” Biomedical signal processing and control, vol. 70, 102987, 2021.
• H. M. Balaha, E. M. El-Gendy and M. M Saafan, “CovH2SD: A COVID-19 detection approach based on Harris Hawks Optimization and stacked deep learning”, Expert systems with applications, vol. 186, 115805, 2021.
• K. U. Ahamed, et al., “A deep learning approach using effective preprocessing techniques to detect COVID-19 from chest CT-scan and X-ray images”, Computers in biology and medicine, vol. 139, 105014, 2021.
• N. A. Baghdadi, et al., “An automated diagnosis and classification of COVID-19 from chest CT images using a transfer learning-based convolutional neural network”, Computers in biology and medicine, 144, 105383. 2022.
• C. Zheng, et al., “Deep learning-baseddetection for COVID-19 from chest CT using weak label”, MedRxiv, 2020.
• X. Xu, et al., “A deep learning system to screen novel coronavirus disease 2019 pneumonia”, Engineering, vol. 6, no 10, pp. 1122–1129, 2020.
• Y. Song, et al., “Deep learning enables accurate diagnosis ofnovel coronavirus (COVID-19) with CT images”, IEEE/ACM Trans. Comput. Biol.Bioinform. vol. 18, no. 6, pp. 2775–2780, 2021.
• S. Wang, et al., “A deep learning algorithm using CT images to screen for Corona VirusDisease (COVID-19)”, European radiology, vol. 31, no. 8, pp. 6096–6104, 2021.
• N. Alsharman and I. Jawarneh, “GoogleNet CNN neural network towards chest CTcoronavirus medical image classification”, J. Comput. Sci. vol. 16, no. 5, pp. 620–625, 2020.
• Neha, K., Joshi, K. P., Jyothi, N. A., & Kumar, J. V. (2021). Preliminary Detection of COVID-19 Using Deep Learning and Machine Learning Techniques on Radiological Data. Indian Journal of Computer Science and Engineering, 79-88.
• M. Maftouni, “Large COVID-19 CT scan slice dataset”, Available:https://www.kaggle.com/datasets/maedemaftouni/large-covid19-ct-slice-dataset (Accessed on: March. 28, 2022).
• A. Z. Bin-Aziz, ‘CT Scans for COVID-19 Classification’, Available: https://www.kaggle.com/datasets/azaemon/preprocessed-ct-scans-for-covid19 (Accessed on: March. 28, 2022).
• O. S. Lih, et al., “Comprehensive electrocardiographic diagnosis based on deep learning”, Artificial intelligence in medicine, vol. 103, 101789, 2020.
• J. Dekhtiar, et al., “Deep learning for big data applications in CAD and PLM – Research review, opportunities and case study”, Computers in Industry, vol. 100, 227–243, 2018.
• M. Rahimzadeh and A. Attar, “Detecting and counting pistachios based on deep learning”, Iran J Comput Sci, vol. 5, pp. 69–81, 2022
• R. Yamashita, et al. “Convolutional neural networks: an overview and application in radiology”, Insights Imaging, vol. 9, pp. 611–629, 2018.
• I. Goodfellow, Y. Bengio, and A. Courville, “Deep learning”, MIT press, 2016.
• F. Al-Areqi and M. Z. Konyar, “Comparative Analysis of Machine Learning and Deep Learning Based Covid-19 Classification Methods”, International Marmara Sciences Congress (Imascon 2022 Spring), İzmit, Turkiye, 13-14 May 2022.
• K. Simonyan, A. Zisserman, “Very deep convolutional networks for large-scale image recognition”, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 2015.
• K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Dec. 2016.
• M. Tan, Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks”, 36th International Conference on Machine Learning, ICML 2019, June 2019.
• G. Huang, Z. Liu, L. Van Der Maaten, K. Q. Weinberger, “Densely connected convolutional networks”, 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Jan. 2017.
• F. Chollet, “Xception: Deep learning with depthwise separable convolutions”, 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Jan. 2017.
• M. Abadi et al., “{TensorFlow}: A System for {Large-Scale} Machine Learning”, In 12th USENIX symposium on operating systems design and implementation (OSDI 16), pp. 265-283, 2016.
• F. Chollet, et al., “Keras: Deep Learning for humans”. Avaliable: https://github.com/fchollet/keras. (Accessed on: March. 28, 2022).
• Yang, X., He, X., Zhao, J., Zhang, Y., Zhang, S., & Xie, P. (2020). COVID-CT-dataset: a CT scan dataset about COVID-19. arXiv preprint arXiv:2003.13865.