BT Görüntülerinden Hassas Covid-19 Tespiti için Yenilikçi Hibrit CNN+SVM Modeli

Abstract

Gelişmiş derin öğrenme tekniklerinin ortaya çıkışı, doğru ve etkili teşhis araçlarının büyük önem taşıdığı sağlık hizmetleri de dahil olmak üzere çeşitli alanlarda devrim yaratmıştır. COVID-19 salgını bağlamında, hızlı ve kesin teşhis ihtiyacı, virüsün yayılmasını yönetmek ve azaltmak için kritik öneme sahiptir. Bu çalışmada, BT görüntülerini kullanarak COVID-19 teşhisi için derin öğrenme algoritmaları kullanan bir karar destek sistemi öneriyoruz. Modellerimizin performansını değerlendirmek için, titizlikle düzenlenmiş ve eldeki göreve göre uyarlanmış benzersiz bir veri kümesi oluşturuyoruz. Bu veri kümesi, modellerimizin yeteneklerinin sağlam bir şekilde değerlendirilmesine olanak tanıyan COVID-19 pozitif ve negatif sınıflarına ayrılmış çok sayıda BT görüntüsünden oluşmaktadır. Yaklaşımımız, kapsamlı bir modelleme çalışmasında ResNet50v2 ve VGG16 gibi önceden eğitilmiş mimarilerin keşfedilmesinin yanı sıra yeni CNN modellerinin geliştirilmesini de içermektedir. Ayrıca, CNN modellerini SVM algoritması ile birleştirerek hibrit bir model sunuyoruz. Hiperparametre optimizasyonu ızgara arama yöntemi kullanılarak gerçekleştirilir ve modelleme sürecinde iki sınıflı (COVID-19 ve Normal) orijinal bir veri kümesi kullanılır. Performans değerlendirmesi, veri kümesinin eğitim ve test kümelerine bölünmesini (%85-%15 oranı) ve 5 kat çapraz doğrulama kullanılmasını içerir. Önerilen yeni CNN modelleri %99,93 ve %99,86 doğruluk oranına ulaşırken, hibrit CNN+SVM modeli sırasıyla %100 ve %99,77 doğruluk oranına ulaşmaktadır. Önerilen bu derin öğrenme modellerinin sağlık hizmetlerinde başarılı bir şekilde uygulanması, teşhis doğruluğunu ve hasta sonuçlarını iyileştirme potansiyellerini göstermektedir.

Keywords

• CNN
• derin öğrenme
• hibrit model
• ızgara arama
• BT görüntüleri

Innovative Hybrid CNN+SVM Model for Accurate Covid-19 Detection From CT Images

Abstract

The advent of advanced deep learning techniques has revolutionized various fields, including healthcare, where accurate and efficient diagnostic tools are of paramount importance. In the context of the COVID-19 pandemic, the need for rapid and precise diagnosis is critical to managing and mitigating the spread of the virus. In this study, we propose a decision support system for the diagnosis of COVID-19 using CT images, employing deep learning algorithms. To evaluate the performance of our models, we create a unique dataset that is meticulously curated and tailored to the task at hand. This dataset consists of a large number of CT images categorized into COVID-19 positive and negative classes, allowing for a robust evaluation of our models' capabilities. Our approach involves the development of novel CNN models as well as the exploration of pre-trained architectures, such as ResNet50v2 and VGG16, in a comprehensive modelling study. Additionally, we introduce a hybrid model by combining CNN models with the SVM algorithm. Hyperparameter optimization is performed using the grid search method, and the modelling process utilizes an original dataset with two classes (COVID-19 and Normal). Performance evaluation involves dividing the dataset into training and test sets (85%-15% ratio) and employing 5-fold cross-validation. Proposed novel CNN models achieve an accuracy rate of 99.93% and 99.86%, while the hybrid CNN+SVM model achieves an accuracy rate of 100% and 99.77%, respectively. Successful application of these proposed deep learning models in healthcare shows their potential to improve diagnostic accuracy and patient outcomes.

Keywords

• CNN
• deep learning
• hybrid model
• grid search
• CT images

References

1. [1] WHO. “COVID-19 Public Health Emergency of International Concern (PHEIC) Global research and innovation forum.” Glob Res Collab Infect Dis Prep., pp. 1-10, 2020. [Online]. Available:https://www.who.int/publications/m/item/covid-19-public-health-emergency-of international-concern-(pheic)-global-research-and-innovation-forum
2. [2] WHO. “Weekly epidemiological update on COVID-19 - pp. 1-16, 2022. [Online]. Available: https://www.who.int/publications/m/item/weekly-epidemiological-update-on-covid-19---16 november-2022
3. [3] J. P. Kanne, B. P. Little, J. H. Chung, B. M. Elicker, and L. H. Ketai, “Essentials for radiologists on COVID-19: An update-radiology scientific expert panel,” Radiology, vol. 296, no. 2. pp. 113–114, 2020.
4. [4] M. Mossa-Basha, C. C. Meltzer, D. C. Kim, M. J. Tuite, K. P. Kolli, and B. S. Tan, “Radiology Department Preparedness for COVID-19: Radiology Scientific Expert Review Panel,” Radiology, vol. 296, no. 2, pp. 106–112, Aug. 2020. [5] E. Martínez Chamorro, A. Díez Tascón, L. Ibáñez Sanz, S. Ossaba Vélez, and S. Borruel Nacenta, “Radiologic diagnosis of patients with COVID-19,” Radiologia. (English Ed)., vol. 63, no. 1, pp. 56–73, Jan. 2021.
5. [6] E. Benmalek, J. Elmhamdi, and A. Jilbab, “Comparing CT scan and chest X-ray imaging for COVID-19 diagnosis,” Biomed. Eng. Adv., vol. 1, p. 100003, Jun. 2021.
6. [7] S. Wang et al., “A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19),” European Radiology., vol. 31, pp. 6096-6104, 2021.
7. [8] C. Lin et al., “Asymptomatic novel coronavirus pneumonia patient outside Wuhan: The value of CT images in the course of the disease,” Clin. Imaging, vol. 63, pp. 7–9, Jul. 2020.
8. [9] Y. Fang et al., “Sensitivity of chest CT for COVID-19: Comparison to RT-PCR,” Radiology. vol.296, no. 2, pp. 115-117, 2020.

9. [10] T. Ai et al., “Correlation of Chest CT and RT-PCR Testing for Coronavirus Disease 2019 (COVID-19) in China: A Report of 1014 Cases,” Radiology, vol. 296, no.2, pp.32-40, 2020.
10. [11] S. Minaee, R. Kafieh, M. Sonka, S. Yazdani, and G. Jamalipour Soufi, “Deep-COVID: Predicting COVID-19 from chest X-ray images using deep transfer learning,” Med. Image Anal., vol.65, 2020.
11. [12] V. Gavini, G. Ramasamy, and J. Lakshmi, “CT Image Denoising Model Using Image Segmentation for Image Quality Enhancement for Liver Tumor Detection Using CNN.” Traitement du Signal, vol.39, no.5, pp.1807-1814, 2022.
12. [13] D. Afchar, V. Nozick, J. Yamagishi, and I. Echizen, “MesoNet: A compact facial video forgery detection network,” 10th IEEE Int. Work. Inf. Forensics Secur. WIFS 2018, Jan. 2019.
13. [14] M. E. Sahin, H. Ulutas, E. Yuce and M.F. Erkoc, “Detection and classification of COVID-19 by using faster R-CNN and mask R-CNN on CT images.” Neural Computing and Applications, vol.35, no. 18, pp. 13597-13611, 2023.
14. [15] H. Ulutas, M. E. Sahin, and M. O. Karakus. “Application of a novel deep learning technique using CT images to implement the COVID-19 automatic diagnosis system on embedded systems.” Alexandria Engineering Journal, vol.74, pp. 345-358, 2023
15. [16] N. Cinar, A. Ozcan, and M. Kaya, “A hybrid DenseNet121-UNet model for brain tumor segmentation from MR Images,” Biomed. Signal Process. Control, vol. 76, 2022.
16. [17] M. E. Sahin, “Image processing and machine learning-based bone fracture detection and classification using X-ray images,” Int. J. Imaging Syst. Technol., vol. 33, no. 3, 2023.
17. [18] M. Emin Sahin, “Deep learning-based approach for detecting COVID-19 in chest X-rays,” Biomed. Signal Process. Control, vol. 78, 2022.
18. [19] K. Gupta and V. Bajaj, “Deep learning models-based CT-scan image classification for automated screening of COVID-19,” Biomed. Signal Process. Control, vol. 80,2023.
19. [20] P. Gaur, V. Malaviya, A. Gupta, G. Bhatia, R. B. Pachori, and D. Sharma, “COVID-19 disease identification from chest CT images using empirical wavelet transformation and transfer learning,” Biomed. Signal Process. Control, vol.71, 2022.
20. [21] F. M. Shah et al., “A Comprehensive Survey of COVID-19 Detection Using Medical Images,” SN Comput. Sci., vol. 2, no. 6, pp. 1–22, Nov. 2021.
21. [22] K. Singh and J. Kaur, “A CNN Approach to Identify COVID-19 Patients among Patients with Pneumonia,” Int. J. Intell. Syst. Appl. Eng., vol. 10, no. 2, pp. 166–169, May 2022.
22. [23] P. M. de Sousa et al., “A new model for classification of medical CT images using CNN: a COVID-19 case study,” Multimed. Tools Appl., pp. 1–29, Dec. 2022.
23. [24] M. Ragab, S. Alshehri, N. A. Alhakamy, R. F. Mansour, and D. Koundal, “Multiclass Classification of Chest X-Ray Images for the Prediction of COVID-19 Using Capsule Network,” Comput. Intell. Neurosci., vol. 2022, 2022.
24. [25] N. A. Baghdadi, A. Malki, S. F. Abdelaliem, H. Magdy Balaha, M. Badawy, and M. Elhosseini, “An automated diagnosis and classification of COVID-19 from chest CT images using a transfer learning-based convolutional neural network,” Comput. Biol. Med., vol. 144, p. 105383, May 2022.
25. [26] A. Banerjee, A. Sarkar, S. Roy, P. K. Singh, and R. Sarkar, “COVID-19 chest X-ray detection through blending ensemble of CNN snapshots,” Biomed. Signal Process. Control, vol. 78, p. 104000, Sep. 2022.
26. [27] S. Thandapani et al., “IoMT with Deep CNN: AI-Based Intelligent Support System for Pandemic Diseases,” Electron. 2023, Vol. 12, Page 424, vol. 12, no. 2, p. 424, Jan. 2023.
27. [28] M. H. Saad, S. Hashima, W. Sayed, E. H. El-Shazly, A. H. Madian, and M. M. Fouda, “Early Diagnosis of COVID-19 Images Using Optimal CNN Hyperparameters,” Diagnostics 2023, Vol. 13, Page 76, vol. 13, no. 1, p. 76, Dec. 2022.
28. [29] A. P. Umejiaku, P. Dhakal, and V. S. Sheng, “Detecting COVID-19 Effectively with Transformers and CNN-Based Deep Learning Mechanisms,” Appl. Sci. 2023, Vol. 13, Page 4050, vol. 13, no. 6, p. 4050, Mar. 2023.
29. [30] A. K. Azad, Mahabub-A-Alahi, I. Ahmed, and M. U. Ahmed, “In Search of an Efficient and Reliable Deep Learning Model for Identification of COVID-19 Infection from Chest X-ray Images,” Diagnostics 2023, Vol. 13, Page 574, vol. 13, no. 3, p. 574, Feb. 2023.
30. [31] A. M. Ayalew, A. O. Salau, Y. Tamyalew, B. T. Abeje, and N. Woreta, “X-Ray image-based COVID-19 detection using deep learning,” Multimed. Tools Appl., pp. 1–19, Apr. 2023.
31. [32] H. Kibriya and R. Amin, “A residual network-based framework for COVID-19 detection from CXR images,” Neural Comput. Appl., vol. 35, no. 11, pp. 8505–8516, Apr. 2022.
32. [33] J. Jiang, E. H. El-Shazly, and X. Zhang, “Gaussian weighted deep modeling for improved depth estimation in monocular images,” IEEE Access, vol. 7, pp. 134718–134729, 2019.
33. [34] L. Chen, W. Tang, T. R. Wan, and N. W. John, “Self-supervised monocular image depth learning and confidence estimation,” Neurocomputing, vol. 381, no. 5, pp. 272–281, Mar. 2020.
34. [35] L. Deng and D. Yu, “Deep learning: Methods and applications,” Foundations and Trends in Signal Processing. vol. 7, no.3-4, pp. 197-3872013.
35. [36] J. D. Kelleher, “Deep Learning.” MIT Press, 2019.
36. [37] J. Bergstra and Y. Bengio, “Random search for hyper-parameter optimization,” J. Mach. Learn. Res., 2012.
37. [38] T. Hastie, R. Tibshirani, and J. Friedman, Springer Series in Statistics The Elements of Statistical Learning - Data Mining, Inference, and Prediction. 2009.
38. [39] S. Sengupta and W. S. Lee, “Identification and determination of the number of immature green citrus fruit in a canopy under different ambient light conditions,” Biosyst. Eng., vol. 117, pp. 51 61, 2014.
39. [40] J. Xu, S. Zhou, A. Xu, J. Ye, and A. Zhao, “Automatic scoring of postures in grouped pigs using depth image and CNN-SVM,” Comput. Electron. Agric., vol. 194, 2022.
40. [41] F. S. A. Sa’ad, M. F. Ibrahim, A. Y. Md. Shakaff, A. Zakaria, and M. Z. Abdullah, “Shape and weight grading of mangoes using visible imaging,” Comput. Electron. Agric., vol 115, pp. 51-56, 2015.
41. [42] M. F. Aslan, “A robust semantic lung segmentation study for CNN-based COVID-19 diagnosis,” Chemom. Intell. Lab. Syst., vol. 231, p. 104695, Dec. 2022.
42. [43] A. F. Mohammed, S. M. Hashim, and I. K. Jebur, “The diagnosis of COVID-19 in CT images using hybrid machine learning approaches (CNN & SVM),” Period. Eng. Nat. Sci., vol. 10, no. 2, pp. 376–387, Apr. 2022.
43. [44] T. Ozturk, M. Talo, E. A. Yildirim, U. B. Baloglu, O. Yildirim, and U. Rajendra Acharya, “Automated detection of COVID-19 cases using deep neural networks with X-ray images,” Comput. Biol. Med., vol 121, 2020.
44. [45] L. Wang, Z. Q. Lin, and A. Wong, “COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images,” Sci. Rep., 2020.
45. [46] A. Narin, C. Kaya, and Z. Pamuk, “Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks,” Pattern Anal. Appl., vol. 24, pp. 1207 1220, 2021. doi: 10.1007/s10044-021-00984-y
46. [47] P. K. Sethy, S. K. Behera, P. K. Ratha, and P. Biswas, “Detection of coronavirus disease (COVID-19) based on deep features and support vector machine,” Int. J. Math. Eng. Manag. Sci., 2020.
47. [48] E. E. D. Hemdan, M. A. Shouman, and M. E. Karar, “COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images.” arXiv preprint arXiv:2003.11055. 2020