SavedAdd your journal

Journals / Türk Doğa ve Fen Dergisi / 2026 / Cilt: 15 Sayı: 2

Comparative Evaluation of YOLOv8, YOLOv11 and ResNet32 for Deep Learning-Based COVID-19 Classification from Chest X-ray Images

Göğüs Röntgeni Görüntülerinden Derin Öğrenme Tabanlı COVID-19 Sınıflandırması İçin YOLOv8, YOLOv11 ve ResNet32 Modellerinin Karşılaştırılmalı Değerlendirilmesi

Berin Balcı(TOKAT GAZİOSMANPAŞA ÜNİVERSİTESİ, TOKAT MESLEK YÜKSEKOKULU)0000-0003-0824-6622
Fatih Basciftci(SELCUK UNIVERSITY)0000-0003-1679-7416
Pages
196–206
Publication Date
2026-07-01
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

These findings demonstrate that YOLOv11m can effectively distinguish COVID-19, Normal, and Pneumonia patterns on chest radiographs, highlighting its strong potential for AI-assisted diagnostic and clinical decision-support applications.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:COVID-19 and pneumonia are among the most common respiratory diseases worldwide and are linked to high morbidity and mortality.
📊
Key Findings & Data:This study applies the YOLOv11m deep learning model to classify chest X-ray images into three categories: COVID-19, Normal, and Pneumonia.
💡
Conclusion & Impact:These findings demonstrate that YOLOv11m can effectively distinguish COVID-19, Normal, and Pneumonia patterns on chest radiographs, highlighting its strong potential for AI-assisted diagnostic and clinical decision-support applications.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:göğüs radyografisi · covid-19 · derin öğrenme

Abstract

COVID-19 and pneumonia are among the most common respiratory diseases worldwide and are linked to high morbidity and mortality. Rapid and reliable detection is essential for effective clinical management. This study applies the YOLOv11m deep learning model to classify chest X-ray images into three categories: COVID-19, Normal, and Pneumonia. The dataset, obtained from the publicly available Kaggle repository, includes 1,518 radiographs (COVID-19: 363; Normal: 1,020; Pneumonia: 135) and is divided into training (80%), testing (10%), and validation (10%) subsets. A three-stage preprocessing pipeline was used to isolate pulmonary regions: Contrast-Limited Adaptive Histogram Equalization (CLAHE) for contrast enhancement, Otsu thresholding with morphological operations for binary lung mask generation, and cropping of lung areas with 3% padding before resizing to 224 × 224 pixels. The model was trained using the PyTorch framework. Performance evaluation included precision, recall, F1-score, ROC-AUC, and Top-1/Top-5 accuracy. YOLOv11m achieved 98.16% Top-1 accuracy, 100% Top-5 accuracy, a macro F1-score of 0.9708, and a macro ROC-AUC of 0.9993. Class-specific F1-scores were 98.0% for COVID-19, 98.7% for Normal, and 94.5% for Pneumonia. These findings demonstrate that YOLOv11m can effectively distinguish COVID-19, Normal, and Pneumonia patterns on chest radiographs, highlighting its strong potential for AI-assisted diagnostic and clinical decision-support applications.

Özet

COVID-19 ve pnömoni, dünya genelinde en yaygın solunum yolu hastalıkları arasında yer almakta olup yüksek morbidite ve mortalite oranlarıyla ilişkilidir. Bu hastalıkların hızlı ve güvenilir şekilde tespit edilmesi, etkili klinik yönetim açısından kritik önem taşımaktadır. Bu çalışmada YOLOv11m modeli, göğüs röntgeni görüntülerini COVID-19, Normal ve Pnömoni olmak üzere üç kategoriye ayırmak için uygulanmıştır. Kamuya açık Kaggle veri setinden elde edilen 1.518 radyografi; COVID-19 (363), Normal (1.020) ve Pnömoni (135) olarak sınıflandırılmış ve veriler %80 eğitim, %10 test ve %10 doğrulama olacak şekilde bölünmüştür. Akciğer bölgelerini izole etmek için üç aşamalı bir ön işleme süreci kullanılmıştır: Kontrastı artırmak için CLAHE uygulanmış, Otsu eşiği ve morfolojik işlemlerle ikili akciğer maskeleri üretilmiş, ardından çıkarılan akciğer alanları %3 boşluk bırakılarak kırpılmış ve 224 × 224 piksele yeniden boyutlandırılmıştır. Model PyTorch çerçevesi kullanılarak eğitilmiştir. Performans değerlendirmesinde kesinlik, duyarlılık, F1-skoru, ROC-AUC ve Top-1/Top-5 doğruluğu gibi ölçütler kullanılmıştır. YOLOv11m modeli %98.16 Top-1 doğruluğu, %100 Top-5 doğruluğu, 0.9708 makro F1-skoru ve 0.9993 makro ROC-AUC değeri elde etmiştir. Sınıf bazlı F1-skorları COVID-19 %98.0, Normal %98.7 ve Pnömoni %94.5 olarak bulunmuştur. Sonuçlar, YOLOv11m mimarisinin göğüs radyografilerinde COVID-19, Normal ve Pnömoni örüntülerini etkili biçimde ayırt edebildiğini göstermekte ve yapay zekâ destekli klinik karar destek sistemlerinde güçlü bir potansiyel sunduğunu ortaya koymaktadır.

🔖

Cite This Article

Balcı, B., Basciftci, F. (2026). Comparative Evaluation of YOLOv8, YOLOv11 and ResNet32 for Deep Learning-Based COVID-19 Classification from Chest X-ray Images. Türk Doğa ve Fen Dergisi, Cilt: 15 Sayı: 2, 196–206. https://doi.org/10.46810/tdfd.1871343

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (46)

  1. Uzen H, Firat H. Göğüs röntgeni görüntülerinden akciğer hastalıklarının sınıflandırılması için farklı derin öznitelikler ile beslenen destek vektör makinesi. Bilisim Teknol Derg. 2024;17(1):11-21.
  2. Wu F, Zhao S, Yu B, Chen YM, Wang W, Song ZG, et al. A new coronavirus associated with human respiratory disease in China. Nature. 2020;579(7798):265-9.
  3. Huang C, Wang Y, Li X, Ren L, Zhao J, Hu Y, et al. Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China. Lancet. 2020;395(10223):497-506.
  4. Wu Z, McGoogan JM. Characteristics of and important lessons from the coronavirus disease 2019 (COVID-19) outbreak in China. JAMA. 2020;323(13):1239-42.
  5. Holshue ML, DeBolt C, Lindquist S, Lofy KH, Wiesman J, Bruce H, et al. First case of 2019 novel coronavirus in the United States. N Engl J Med. 2020;382(10):929-36.
  6. Singhal T. A review of coronavirus disease-2019 (COVID-19). Indian J Pediatr. 2020;87(4):281-6.
  7. Pagliano P, Scarpati G, Ascione T. Pneumonia in clinical practice: causes, risks, and management. Clin Respir J. 2021;15(6):567-75.
  8. GBD 2019 Antimicrobial Resistance Collaborators. Global mortality associated with 33 bacterial pathogens in 2019: a systematic analysis for the Global Burden of Disease Study 2019. Lancet. 2022;400(10369):2221-48,
  9. Rambaud-Althaus C, Althaus F, Genton B, D'Acremont V. Clinical features for diagnosis of pneumonia in children younger than 5 years: a systematic review and meta-analysis. Lancet Infect Dis. 2015;15(4):439-50.
  10. Zu ZY, Jiang MD, Xu PP, Chen W, Ni QQ, Lu GM, et al. Coronavirus disease 2019 (COVID-19): a perspective from China. Radiology. 2020;296(2):E15-25.
  11. Kanne JP, Little BP, Chung JH, Elicker BM, Ketai LH. Essentials for radiologists on COVID-19: an update. Radiology. 2020;296(2):200527.
  12. Xie X, Zhong Z, Zhao W, Zheng C, Wang F, Liu J. Chest CT for typical 2019-nCoV pneumonia: relationship to negative RT-PCR testing. Radiology. 2020;296(2):E41-5.
  13. Lee EY, Ng MY, Khong PL. COVID-19 pneumonia: what has CT taught us? Lancet Infect Dis. 2020;20(4):384-5.
  14. Bernheim A, Mei X, Huang M, Yang Y, Fayad ZA, Zhang N, et al. Chest CT findings in coronavirus disease-19: relationship to duration of infection. Radiology. 2020;295(3):200463.
  15. Pan F, Ye T, Sun P, Gui S, Liang B, Li L, et al. Time course of lung changes on chest CT during recovery from COVID-19 pneumonia. Radiology. 2020;295(3):715-21.
  16. Long C, Xu H, Shen Q, Zhang X, Fan B, Wang C, et al. Diagnosis of the coronavirus disease (COVID-19): rRT-PCR or CT? Eur J Radiol. 2020;126:108961.
  17. Li Y, Xia L. Coronavirus disease 2019 (COVID-19): role of chest CT in diagnosis and management. AJR Am J Roentgenol. 2020;214(6):1280-6.
  18. Shi H, Han X, Jiang N, Cao Y, Alwalid O, Gu J, et al. Radiological findings from 81 patients with COVID-19 pneumonia in Wuhan, China: a descriptive study. Lancet Infect Dis. 2020;20(4):425-34.
  19. Chan JFW, Yuan S, Kok KH, To KKW, Chu H, Yang J, et al. A familial cluster of pneumonia associated with the 2019 novel coronavirus. Lancet. 2020;395(10223):514-23.
  20. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436-44.
  21. Kaushik VS, Nayyar A, Kataria G, Jain R. Pneumonia detection using convolutional neural networks (CNNs). In: Singh P, Pawłowski W, Tanwar S, Kumar N, Rodrigues J, Obaidat M, editors. Proceedings of First International Conference on Computing, Communications, and Cyber-Security (IC4S 2019). Lecture Notes in Networks and Systems. Singapore: Springer; 2020. p. 471-83.
  22. Narin A, Kaya C, Pamuk Z. Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks. Pattern Anal Appl. 2020;24:1207-20.
  23. Pathak Y, Shukla PK, Tiwari A, Stalin S, Singh S. Deep transfer learning based classification model for COVID-19 disease. IRBM. 2020;43(2):87-92. Mijwil MM, Al-Zubaidi EA. Medical image classification for coronavirus disease (COVID-19) using convolutional neural networks. Iraqi J Sci. 2021;62(8):2740-7.
  24. Mijwil MM, Al-Zubaidi EA. Medical image classification for coronavirus disease (COVID-19) using convolutional neural networks. Iraqi J Sci. 2021;62(8):2740-7.
  25. Pereira RM, Bertolini D, Teixeira LO, Silla CN Jr, Costa YMG. COVID-19 identification in chest X-ray images on flat and hierarchical classification scenarios. Comput Methods Programs Biomed. 2020;194:105532.
  26. Barstugan M, Ozkaya U, Ozturk S. Coronavirus (COVID-19) classification using CT images by machine learning methods. arXiv [Preprint]. 2020;2003.09424.
  27. Ozkaya U, Ozturk S, Barstugan M. Coronavirus (COVID-19) classification using deep features fusion and ranking technique. In: Big Data Analytics and Artificial Intelligence Against COVID-19. Studies in Big Data. Springer; 2020. p. 281-95.
  28. Sethy PK, Behera SK, Ratha PK, Biswas P. Detection of coronavirus disease (COVID-19) based on deep features and support vector machine. Int J Math Eng Manag Sci. 2020;5(4):643-51.
  29. Aggarwal P, Mishra NK, Fatimah B, Singh P, Gupta A, Joshi SD. COVID-19 image classification using deep learning: advances, challenges and opportunities. Comput Biol Med. 2022;144:105350.
  30. Shibly KH, Dey SK, Islam MTU, Rahman MM. COVID faster R-CNN: a novel framework to diagnose novel coronavirus disease (COVID-19) in X-ray images. Inform Med Unlocked. 2020;20:100405.
  31. Cai Z, Zhou K, Liao Z. A systematic review of YOLO-based object detection in medical imaging: advances, challenges, and future directions. Comput Mater Continua. 2025;85(2):2255-2303.
  32. Sharma S, Dhakal S, Bhavsar M. Transfer learning for wildlife classification: evaluating YOLOv8 against DenseNet, ResNet, and VGGNet on a custom dataset. J Artif Intell Capsule Netw. 2024;6(4):415-35.
  33. Khairkar AD, Kadam S, Kadam P, Deshpande S. Advancing dental implant classification through YOLO-based deep learning models. Int J Inf Technol. 2025. Epub ahead of print.
  34. Khokhariya A, Sarda J, Pradhan V, Vaghela R, Dave M, Thakkar A. Performance benchmarking of YOLO models for colorectal cancer histopathology image classification. In: Proceedings of the 2025 International Conference on Modeling, Simulation and Intelligent Computing (MoSICom); 2025; Dubai, UAE. IEEE; 2025. p. 185-190.
  35. Chowdhury MEH, Rahman T, Khandakar A, Mazhar R, Kadir MA, Mahbub ZB, et al. COVID-19 Radiography Database [Internet]. Kaggle; 2021 [cited 2025 Jan 30]. Available from: https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database.
  36. Hidayatullah P, Syakrani N, Sholahuddin MR, Gelar T, Tubagus R. YOLOv8 to YOLO11: a comprehensive architecture in-depth comparative review. arXiv [Preprint]. 2025;2501.13400.
  37. Ultralytics. YOLO11 [Internet]. 2024 [cited 2025 Jan 30]. Available from: https://github.com/ultralytics/ultralytics.
  38. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016; Las Vegas, NV, USA. p. 770-8.
  39. Arik K, Agdas MT, Korkmaz A, Kosunalp S, Iliev T. Advanced classification of poxvirus-based skin diseases using deep learning techniques. Trait Signal. 2025;42(5):2777-86.
  40. Suparto A, Pribadi MR. Improving oil palm fruit detection under class imbalance using class-balanced focal loss on YOLOv11. J Sisfokom. 2026;15(2):165-76.
  41. Qu R, Yang Y, Wang Y. COVID-19 detection using CT image-based YOLOv5 network. In: 2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST). IEEE; 2021. p. 622-625.
  42. Xie Q, Zhang L, Chen Y. Fast-YOLO: real-time COVID-19 and pneumonia detection using optimized YOLOv11. Pattern Recognit Lett. 2025;178:57-64.
  43. Karadeniz AT, Başaran E, Çelik Y. Classification of walnut leaf images using a hybrid CNN-based deep learning approach. Turk J Nat Sci. 2026;15(1):192-201.
  44. Joshi K, Yadav Y, Hooda S, Nandal R, Singh B, Singh K, et al. Classification of cotton leaf disease using YOLOv8 based k-fold cross validation deep learning method for precision agriculture. Sci Rep. 2025;15(1):35602.
  45. Paul A, Raj R, Gourisaria MK, Jha AV, Bizon N. HARVEST: a locality-enhanced vision transformer for efficient multi-level grocery classification. Eng Rep. 2026;8(1):e70534.
  46. Islam MP, Hatou K, Shinagawa K, Kondo S, Kadoya Y, Aono M, et al. Hort-YOLO: a multi-crop deep learning model with an integrated semi-automated annotation framework. Comput Electron Agric. 2026;240:111196.