Artık evrişimli sinir ağı kullanılarak göğüs röntgeni görüntülerinde pnömoni tespiti

Yıl 2024, , 1719 - 1732, 20.05.2024

İpek İnal Atik

https://doi.org/10.17341/gazimmfd.1271385

Öz

Pnömoni hastalığı akciğer dokusunun iltihaplanması neticesinde ortaya çıkan bir göğüs hastalığıdır. Pnömoni her yaşta görülebilmekle birlikte iki yaş altı ve altmış beş yaş üstü kişilerde oldukça tehlikelidir. Dünya Sağlık Örgütü verilerine göre dünyadaki tüm ölümlerin yaklaşık yüzde %7’si kadarının pnömoni nedeniyle olduğu belirtilmektedir. Hastalıktan kaynaklı ölüm oranlarının azaltılmasında hastalığın erken teşhisi ve tedavisi önemli bir etkendir. Çalışmada üç boyutlu (3D) göğüs röntgen görüntülerinden pnömoni tespiti için etkin bir evrişimli sinir ağı (ESA) modeli önerilmiştir. Önerilen model, ön eğitimli ResNet ile transfer öğrenme yaklaşımı kullanılarak tasarlanmıştır. Modelde artık blok bağlantılar ile derin öğrenme mimarisindeki bazı katmanlar atlanarak performansı arttırılmıştır. Önerilen yöntemin performansı basit bir ESA modeli, önerilen modelden artık blokların çıkarıldığı ESA modeli ve yaygın olarak kullanılan ön eğitimli ağlardan olan ResNet-18 ile karşılaştırılmıştır. Yapılan analizlere göre önerilen yöntemin doğruluk, özgüllük, hassasiyet, kesinlik ve F-1 skoru değerleri sırasıyla %98,42; %97,52; %99,35; %97,47 ve %98,90 olarak elde edilmiştir. Analizlerden elde edilen sonuçlar incelendiğinde, önerilen yöntemin göğüs röntgen görüntülerinden pnömoni tespitinde başarılı olduğunu ortaya koymaktadır.

Anahtar Kelimeler

göğüs röntgen görüntü, pnömoni, sınıflandırma, ESA, artık blok

Kaynakça

• 1. Gereige R. S., and Laufer P. M., Pneumonia, Pediatr Rev., 34 (10), 438–456, 2013.
• 2. Prayle A., Atkinson M. and Smyth A., Pneumonia in the developed world, Paediatric Respiratory Reviews., 12 (1), 60–69, 2011.
• 3. Ruuskanen O., Lahti E., Jennings L. C. and Murdoch D. R., Viral pneumonia, The Lancet, 377 (9773), 1264–1275, 2011.
• 4. GM H., Gourisaria M. K., Rautaray S. S. and Pandey M., Pneumonia detection using CNN through chest X-ray, Journal of Engineering Science and Technology, 16 (1), 861–876, 2021.
• 5. Khoiriyah S. A., Basofi A. and Fariza A., Convolutional Neural Network for Automatic Pneumonia Detection in Chest Radiography, The 2020 International Electronics Symposium (IES), Surabaya, Indonesia, 476–480, 29-30 Eylül, 2020.
• 6. Asnaoui K., Chawki Y. and Idri A., Automated methods for detection and classification pneumonia based on x-ray images using deep learning, Artificial intelligence and blockchain for future cybersecurity applications, Springer, 257–284, 2021.
• 7. Baltruschat, I. M., Nickisch, H., Grass M., Knopp T. and Saalbach A., Comparison of deep learning approaches for multi-label chest X-ray classification, Scientific Reports, 9 (1), 1–10, 2019.
• 8. Ferreira J. R., Cardenas D., Moreno R. A., Sá Rebelo M., Krieger J. E. and Gutierrez M. A., Multi-view ensemble convolutional neural network to improve classification of pneumonia in low contrast chest x-ray images. 42nd annual international conference of the IEEE engineering in Medicine & Biology Society, Sydney, 1238–1241, 20-24 Temmuz, 2020.
• 9. Demir F., DeepCoroNet: A deep LSTM approach for automated detection of COVID-19 cases from chest X-ray images, Applied Soft Computing, 103, 107160, 2021.
• 10. Wang X., Peng Y., Lu L., Lu Z., Bagheri M. and Summers R., ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases, IEEE CVPR 2017, Honolulu, USA, 2097-2106, 21-26 Temmuz, 2017.
• 11. Yao L., Poblenz E., Dagunts D., Covington B., Bernard D. and Lyman K., Learning to diagnose from scratch by exploiting dependencies among labels, arXiv preprint arXiv:1710.10501, 2017.
• 12. Rajpurkar P., Irvin J., Zhu K., Yang B., Mehta H., Duan T., Ding D., Bagul A., Langlotz C. and Shpanskaya K., Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning, arXiv preprint arXiv:1711.05225, 2017.
• 13. Kaymak S., Almezhghwi K. and Shelag A., Classification of diseases on chest X-rays using deep learning, The International Conference on Theory and Applications of Fuzzy Systems and Soft Computing, Warsaw, Poland, 516–523, 26-27 Ağustos, 2018.
• 14. Rubin J., Sanghavi D., Zhao C., Lee K., Qadir A. and Xu-Wilson M., Large scale automated reading of frontal and lateral chest x-rays using dual convolutional neural networks[J]. arXiv preprint arXiv:1804.07839, 2018.
• 15. Gülgün O. D., Hamza E., Classification performance comparisons of deep learning models in pneumonia diagnosis using chest x-ray images, Turkish Journal of Engineering, 4 (3), 129–141, 2020.
• 16. Ucar F., Korkmaz D., COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images, Medical Hypotheses, 140, 109761–109761, 2020.
• 17. Varshni D., Thakral K., Agarwal L., Nijhawan R. and Mittal A., Pneumonia detection using CNN based feature extraction, 2019 IEEE international conference on electrical, computer and communication technologies, Tamil Nadu, India, 1–7, 20-22 Şubat, 2019.
• 18. Sirazitdinov I., Kholiavchenko M., Mustafaev T., Yixuan Y., Kuleev R. and Ibragimov B., Deep neural network ensemble for pneumonia localization from a large-scale chest x-ray database, Computers & Electrical Engineering, 78, 388–399, 2019.
• 19. Rahman T., Chowdhury M. E., Khandakar A., Islam K. R., Islam K. F., Mahbub Z. B., Kadir M. A. and Kashem S., Transfer learning with deep convolutional neural network (CNN) for pneumonia detection using chest X-ray, Applied Sciences, 10 (9), 3233, 2020.
• 20. Jain R., Nagrath P., Kataria G., Kaushik V. S. and Hemanth D. J., Pneumonia detection in chest X-ray images using convolutional neural networks and transfer learning, Measurement, 165, 108046, 2020.
• 21. Račić L., Popović T. and Šandi S., Pneumonia detection using deep learning based on convolutional neural network, 25th International Conference on Information Technology (IT), Žabljak, 1–4, 28-29 September, 2021.
• 22. Atik I., COVID-19 Case Forecast with Deep Learning BiLSTM Approach: The Turkey Case, Int. J. Mech. Eng., 7 (1), 6307–6314, 2022.
• 23. Atik I., Performance comparison of regression learning methods: COVID-19 case prediction for Turkey, Int. J. Mech. Eng., 7 (1), 6297–6306, 2022.
• 24. [Atik I., A New CNN-Based Method for Short-Term Forecasting of Electrical Energy Consumption in the Covid-19 Period: The Case of Turkey, IEEE Access, 10, 22586–22598, 2022.
• 25. Atik I., Performance Comparison of Pre-Trained Convolutional Neural Networks in Flower Image Classification, Eur. J. Sci. Technol., 35, 315–321, 2022.
• 26. Atik I., A Hybrid Prediction Approach Based on ANN and NAR Neural Networks for Annual Electric Energy Demand in Turkey, UPB Sci Bull Ser. C, 83 (4), 311–330, 2021.
• 27. Acikgoz H., Korkmaz D. and Dandil B., Classification of Hotspots in Photovoltaic Modules with Deep Learning Methods, Turkish Journal of Science & Technology, 17 (2), 211-221, 2022.
• 28. Gökdemir A., Calhan A., Deep learning and machine learning based anomaly detection in internet of things environments, Journal of the Faculty of Engineering and Architecture of Gazi University, 37 (4), 1945–1956, 2022.
• 29. Karasulu B., Yücalar F., Borandag E., A hybrid approach based on deep learning for gender recognition using human ear images, Journal of the Faculty of Engineering and Architecture of Gazi University, 37 (3), 1579–1594, 2022.
• 30. Şafak E., Barıscı N., Real-time fire and smoke detection for mobile devices using deep learning, Journal of the Faculty of Engineering and Architecture of Gazi University, 38 (4), 2179–2190, 2023.
• 31. Çubukçu E. A., Demir V., Sevimli M. F., Akım Verilerinin Makine Öğrenmesi Teknikleriyle Tahmin Edilmesi, Gazi Mühendis. Bilim. Derg., 8 (2), 257–272, 2022.
• 32. Atik I., Analysis of Biodegradable and Non-Biodegradable Materials Using Selected Deep Learning Algorithms, International Journal of Computer, 43 (1), 48–59, 2022.
• 33. Kaggle data set. https://www.kaggle.com/datasets. Erişim tarihi: 06 Aralık 2021.
• 34. Bi Q., Qin K., Zhang H., Li Z. and Xu K., RADC-Net: A residual attention-based convolution network for aerial scene classification, Neurocomputing, 377, 345–359, 2020.
• 35. He K., Zhang X., Ren S. and Sun J., Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, Nevada, 770–778, 26 Haziran- 1 Temmuz, 2016.
• 36. Atik I., Classification of Electronic Components Based on Convolutional Neural Network Architecture, Energies, 15 (7), 2347, 2022.
• 37. Szegedy C., Ioffe S., Vanhoucke V. and Alemi A., Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, Proceedings of the AAAI Conference on Artificial Intelligence, California USA, 31 (1), 4278-4284, 7-8 Haziran, 2017.
• 38. Rasekh M., Karami H., Wilson A. D. and Gancarz M., Classification, and identification of essential oils from herbs and fruits based on a MOS electronic-nose technology, Chemosensors, 9 (6), 142, 2021.
• 39. Kaggle data set, https://www.kaggle.com/datasets/jtiptj/chest-xray-pneumoniacovid19tuberculosis, Erişim tarihi: 02 Haziran 2023.