FARKLI RENK UZAYLARINDAKİ X-RAY VE BT GÖRÜNTÜLERİNİN GÜÇLÜ ESA İLE SINIFLANDIRILMASI

Abstract

Derin öğrenme modelleri birçok alanda başarıyla kullanıldığından beri, X-ray veya Bilgisayarlı Tomografi göğüs radyolojisi görüntülerinde hasta ve sağlıklı kişileri tanılamak için kullanılmaktadır. Bu çalışmada, güçlü Evrişimsel Sinir Ağı (ESA) kullanılarak hem X-ray hem de BT görüntüleri üzerinde Covid-19 ve zatürre hastalığı sınıflandırması gerçekleştirilmektedir. BGR, HSV ve CIE LAB renk uzayı dönüşümleri; modelin veri kümesi özelliklerinden bağımsız olarak başarılı bir sınıflandırma gerçekleştirdiğini göstermek için X-ray ve BT görüntülerine uygulanmıştır. Röntgen ve BT görüntülerinin için Covid-19 ve zatürre olmak üzere ikili sınıflandırma doğruluk oranları sırasıyla %98,7 ve %98,4, %97,6 ve %99,4'tür. Her X-ray ve BT veri seti için Kesinlik, Geri Çağırma, Özgüllük, F1 puanı ve Ortalama Karesel Hata metrikleri hesaplanmıştır. Ayrıca, 5 kat çapraz doğrulama modelin doğruluğunu kanıtlamıştır. X-ray ve BT göğüs radyolojisi görüntüleri farklı renk uzaylarına dönüştürülmesine rağmen, önerilen model başarılı bir sınıflandırma gerçekleştirmiştir. Böylece radyoloji cihazı markalarının görüntü özellikleri değişse bile bilgisayar tabanlı sistem, uzman personelin yetersiz olduğu yerlerde düşük maliyetle başarılı hastalık teşhisleri yapabilecektir.

Keywords

• Evrişimli Sinir Ağı
• Covid-19 Tespiti
• BT and Röntgen Göğüs Görüntüsü
• Zatürre

CLASSIFICATION OF X-RAY AND CT IMAGES IN DIFFERENT COLOR SPACES USING ROBUST CNN

Abstract

Since deep learning models have been successfully used in many fields, they have been used to identify sick and healthy people in X-ray or Computed Tomography (CT) chest radiology images. In this study, Covid-19 and pneumonia classification is performed on both X-ray and CT images using the robust Convolutional Neural Network (CNN). BGR, HSV, and CIE LAB color space transformations are applied to X-ray and CT images to show that the model performs a successful classification independent of dataset characteristics. The binary classification accuracy rates of Covid-19 and pneumonia for X-ray images and CT images are 98.7% and 98.4%, 97.6% and 99.4%, respectively. Precision, Recall, Specificity, F1 score, and Mean Squared Error metrics are calculated for each X-ray and CT dataset. In addition, 5-fold cross-validation proved accuracy of the model. Although X-ray and CT chest radiology images are transformed into different color spaces, the proposed model performed a successful classification. Thus, even if the image characteristics of the radiology device brands change, the computer-based system will be able to make successful disease diagnoses at low cost where expert personnel are insufficient.

Keywords

• Convolutional Neural Network
• Covid-19 Detection
• CT and X-ray Chest Image
• Pneumonia

References

1. Atasoy F., Eltanashi S., 2020. A Proposed Speaker Recognition Model Using Optimized Feed Forward Neural Network and Hybrid Time-Mel Speech Feature. International Conference on Advanced Technologiess Computer Engineering and Science (ICATCES 2020), pp. 130–140, Jun.
2. Aydin Atasoy, N., Faris Abdulla Al Rahhawi, A., 2024. Examining the classification performance of pre-trained capsule networks on imbalanced bone marrow cell dataset, International Journal of Imaging Systems and Technology,34(3);https://doi.org/10.1002/ima.23067.
3. Banerjee A., Sarkar A., Roy S., Singh P. K., Sarkar R., 2022. COVID-19 chest X-ray detection through blending ensemble of CNN snapshots. Biomed Signal Process Control. 78:104000. doi: 10.1016/J.BSPC.2022.104000.
4. Bello-Cerezo R., Bianconi F., Fernández A., González E., di Maria F., 2016. Experimental comparison of color spaces for material classification. J Electron Imaging. 25(6). doi: 10.1117/1.jei.25.6.061406.
5. Bozkurt F. ,2021. Derin Öğrenme Tekniklerini Kullanarak Akciğer X-Ray Görüntülerinden COVID-19 Tespiti. Avrupa Bilim ve Teknoloji Dergisi, (24), 149-156.
6. 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.
7. Chest X-ray (Covid-19 & Pneumonia) | Kaggle, 2022. https://www.kaggle.com/prashant268/chest-xray-covid19-pneumonia Accessed Jan. 07.
8. Cohen J. P., Morrison P., Dao .L et al. 2020. COVID-19 Image Data Collection: Prospective Predictions Are the Future. Journal of Machine Learning for Biomedical Imaging. doi: 10.48550/arxiv.2006.11988.

9. COVID Live - Coronavirus Statistics - Worldometer. https://www.worldometers.info/coronavirus/ Accessed Jan. 07, 2023.
10. COVID-19 DATABASE – SIRM. https://sirm.org/category/senza-categoria/covid-19/ Accessed Jan. 10, 2023.
11. COVID-19, Radiography Database | Kaggle. https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database Accessed Jan. 10, 2023.
12. COVID-19, Normal&Pneumonia_CT_ImagesKaggle(2022).https://www.kaggle.com/anaselmasry/covid19normalpneumonia-ct-images Accessed Jan. 07.
13. CT scan – Wikipedia ,2023. https://en.wikipedia.org/wiki/CT_scan Accessed Jan. 10, 2023.
14. Elhagaggagi Emad Ba Attoch A., 2021. Thyroid Disorder Prediction Using Advance Deep Learning Paradigms: A Comparative Approach. Karabük University, The Institute of Graduate Studies.
15. Foysal Haque K., Farhan Haque F., Gandy L., Abdelgawad A., 2020. Automatic Detection of COVID-19 from Chest X-ray Images with Convolutional Neural Networks. 2020 International Conference on Computing, Electronics and Communications Engineering, pp. 125–130. doi: 10.1109/iCCECE49321.2020.9231235.
16. Gilanie G. et al., 2021. Coronavirus (COVID-19) detection from chest radiology images using convolutional neural networks. Biomed Signal Process Control, 66:102490. doi: 10.1016/J.BSPC.2021.102490.
17. Gürsoy C., Tapan Ö., Doğan E. et al., 2022. Comparison of prone position effectiveness with percentage of injured lung area in awake non - intubated COVID-19 patients. Health Sciences Medicine 5(2): 417–422.
18. Islam M. Z., Islam M. M., Asraf A. 2020. A combined deep CNN-LSTM network for the detection of novel coronavirus (COVID-19) using X-ray images. Inform Med Unlocked, 20:100412. doi: 10.1016/j.imu.2020.100412.
19. Karim A. M., Kaya H., Alcan V., Sen B., Hadimlioglu I. A., 2022. New Optimized Deep Learning Application for COVID-19 Detection in Chest X-ray Images. Symmetry, 14(5):1003, doi: 10.3390/SYM14051003.
20. Kaya A., Keceli A. S., Can A. B., 2019. Examination of various classification strategies in classification of lung nodule characteristics. Journal of the Faculty of Engineering and Architecture of Gazi University, 34(2):709–725. doi: 10.17341/gazimmfd.416530.
21. Lecun Y., Bengio Y., Hinton G., 2015. Deep learning. Nature, 521(7553):436–444. doi: 10.1038/nature14539.
22. Liu F., Chen D., Zhou J., Xu F., 2022. A review of driver fatigue detection and its advances on the use of RGB-D camera and deep learning. Eng Appl Artif Intell., 116:105399. doi: 10.1016/J.ENGAPPAI.2022.105399.
23. Metin İ. A., Karasulu B., 2021. A novel dataset of human daily activities: Its benchmarking results for classification performance via using deep learning techniques. Journal of the Faculty of Engineering and Architecture of Gazi University, 36(2):759–777. doi: 10.17341/gazimmfd.772849.
24. Mishra M., Parashar V., Shimpi R., 2020. Development and evaluation of an AI System for early detection of Covid-19 pneumonia using X-ray. 2020 IEEE 6th International Conference on Multimedia Big Data, pp. 292–296. doi: 10.1109/BigMM50055.2020.00051.
25. Nayak S. R, Nayak D. R., Sinha U., Arora V., Pachori R. B.,2021. Application of deep learning techniques for detection of COVID-19 cases using chest X-ray images: A comprehensive study. Biomedical Signal Processing and Control, vol. 64. doi: 10.1016/j.bspc.2020.102365.
26. Oğuz Ç., Yağanoğlu M., 2021. Determination of Covid-19 Possible Cases by Using Deep Learning Techniques. Sakarya University Journal of Science, 25(1),1-11, DOI: https://doi.org/10.16984/saufenbilder.774435
27. Oğuz Ç., Yağanoğlu M., 2022. Detection of COVID-19 using deep learning techniques and classification methods. Inf Process Manag. 59(5):103025. doi: 10.1016/j.ipm.2022.103025. Epub 2022 Jul 8. PMID: 35821878; PMCID: PMC9263717.
28. Özturk T., Talo M., Yildirim E. A. et al., 2020. Automated detection of COVID-19 cases using deep neural networks with X-ray images. Comput Biol Med, 121:103792. doi: 10.1016/J.COMPBIOMED.2020.103792.
29. Pneumonia & COVID-19 Image Dataset | Kaggle (2022). https://www.kaggle.com/gibi13/pneumonia-covid19-image-dataset Accessed Jan. 07.
30. Polsinelli M., Cinque L., Placidi G., 2020. A light CNN for detecting COVID-19 from CT scans of the chest. Pattern Recognit Lett, 140:95–100. doi: 10.1016/j.patrec.2020.10.001.
31. Rahimzadeh M., Attar A.., Sakhaei S. M., 2021. A fully automated deep learning-based network for detecting COVID-19 from a new and large lung CT scan dataset. Biomed Signal Process Control, 68:102588. doi: 10.1016/J.BSPC.2021.102588.
32. Serener A., Serte S., 2020. Deep learning for mycoplasma pneumonia discrimination from pneumonias like COVID-19. 4th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2020 - Proceedings, pp. 1–5. doi: 10.1109/ISMSIT50672.2020.9254561.
33. Somuncu E., Aydın Atasoy N., 2021. Evrişimli tekrarlayan sinir ağı ile metin görüntüleri üzerinde karakter tanıma uygulaması Gerçekleştirilmesi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 37:17–28. doi: 10.17341/GAZIMMFD.866552.
34. Steiniger Y., Kraus D., Meisen T.,2022. Survey on deep learning-based computer vision for sonar imagery. Eng Appl Artif Intell., 114:105157. doi: 10.1016/J.ENGAPPAI.2022.105157.
35. Taşdelen A., Şen B., 2021. A hybrid CNN-LSTM model for pre-miRNA classification. Scientific Reports, 11:1-9. doi: 10.1038/s41598-021-93656-0.
36. Thakur S., Kumar A.,2021. X-ray and CT-scan-based automated detection and classification of covid-19 using convolutional neural networks (CNN). Biomed Signal Process Control, 69:102920. doi: 10.1016/J.BSPC.2021.102920.
37. Toğaçar M., Ergen B., Sertkaya M. E., 2009. Zatürre Hastalığının Derin Öğrenme Modeli ile Tespiti. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 31(1): 223–230.
38. Uçar E., Atila Ü., Uçar M., Akyol K., 2021. Automated detection of Covid-19 disease using deep fused features from chest radiography images. Biomed Signal Process Control, 69:102862. doi: 10.1016/J.BSPC.2021.102862.
39. X-ray – Wikipedia,2023. https://en.wikipedia.org/wiki/X-ray Accessed Jan. 10, 2023.
40. Yan T., 2020 COVID-19 and Common Pneumonia Chest CT dataset (416 COVID-19 positive CT scans ) doi: 10.17632/3Y55VGCKG6.2 Accessed June 20.
41. Yan T., Wong P. K., Ren H., Wang H., Wang J., and Li Y., 2020. Automatic distinction between COVID-19 and common pneumonia using multi-scale convolutional neural network on chest CT scans. Chaos Solitons Fractals, 140:110153. doi: 10.1016/j.chaos.2020.110153.
42. Yan, T., 2020. COVID-19 and Common Pneumonia Chest CT Dataset (412 Common Pneumonia CT Scans). https://doi.org/10.17632/ygvgkdbmvt.1 Accessed June 20.
43. Yang X,. San Diego U., Zhao J. et al., 2023. COVID-CT-Dataset: A CT Image Dataset about COVID-19. https://www.researchgate.net/publication/340331511_COVID-CT-Dataset_A_CT_Scan_Dataset_about_COVID-19#fullTextFileContent Accessed April 07, 2022.
44. Yıldız O., 2019. Melanoma detection from dermoscopy images with deep learning methods: A comprehensive study, Journal Of The Faculty Of Engineering And Architecture Of Gazi University, vol. 34(4): 2241–2260. doi: 10.17341/GAZIMMFD.435217.