SavedAdd your journal

Journals / Journal of Artificial Intelligence and Data Science / 2026 / Cilt: 6 Sayı: 1

Dual-View Deep Learning for Tibial Plateau Fracture Detection Using Input-Level Fusion of X-Ray Images

X-Işını Görüntülerinin Giriş Seviyesinde Birleştirilmesi Kullanılarak Tibial Plato Kırığı Tespiti için Çift Görünümlü Derin Öğrenme

Özlem Karabiber Cura(İZMİR KATİP ÇELEBİ ÜNİVERSİTESİ)0000-0001-8650-1137
Fatma Günseli Yaşar Çıklaçandır(IZMIR KATIP CELEBI UNIVERSITY)0000-0001-6182-7173
Mehmet Göktuğ Efgan(IZMIR KATIP CELEBI UNIVERSITY)0000-0002-0794-1239
Pages
22–30
Publication Date
2026-06-29
DOI
—
🏛️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)

The results show that all models perform well, and EfficientNet-B0 achieved the best balance between sensitivity (87.23%) and specificity (94.23%) on the test set.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Tibial plateau fractures are serious injuries of the knee joint.
📊
Key Findings & Data:Therefore, accurate detection from X-ray images is very important.
💡
Conclusion & Impact:The results show that all models perform well, and EfficientNet-B0 achieved the best balance between sensitivity (87.23%) and specificity (94.23%) on the test set.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Evrişimsel sinir ağları · derin öğrenme · çift görüşlü röntgen

Abstract

Tibial plateau fractures are serious injuries of the knee joint. If they are not diagnosed and treated on time, they can lead to important functional problems. Therefore, accurate detection from X-ray images is very important. In this study, a deep learning-based method is proposed for detecting tibial plateau fractures using dual-view X-ray images. Anterior–posterior and lateral images are combined at the input level to create a 6-channel representation. This simple design allows the model to learn from both views at the same time. In experiments, five pre-trained convolutional neural network models (ResNet18, ResNet50, DenseNet201, EfficientNet-B0, and MobileNetV2) are used and evaluated under the same conditions. The results show that all models perform well, and EfficientNet-B0 achieved the best balance between sensitivity (87.23%) and specificity (94.23%) on the test set. In addition, Grad-CAM and t-SNE analyses are used to understand model decisions better. Overall, the proposed method provides a simple and effective approach for dual-view fracture detection and can support clinical diagnosis.

Özet

Tibia platosu kırıkları, diz ekleminin ciddi yaralanmalarıdır. Zamanında teşhis ve tedavi edilmezlerse, önemli fonksiyonel sorunlara yol açabilirler. Bu nedenle, röntgen görüntülerinden doğru tespit çok önemlidir. Bu çalışmada, çift yönlü röntgen görüntüleri kullanılarak tibia platosu kırıklarının tespiti için derin öğrenmeye dayalı bir yöntem önerilmiştir. Ön-arka ve yan görüntüler, 6 kanallı bir temsil oluşturmak için giriş seviyesinde birleştirilmiştir. Bu basit tasarım, modelin her iki görüntüden aynı anda öğrenmesini sağlamıştır. Deneylerde, beş önceden eğitilmiş evrişimsel sinir ağı modeli (ResNet18, ResNet50, DenseNet201, EfficientNet-B0 ve MobileNetV2) kullanılmış ve aynı koşullar altında değerlendirilmiştir. Sonuçlar, tüm modellerin iyi performans gösterdiğini ve EfficientNet-B0'ın test setinde duyarlılık (%87,23) ve özgüllük (%94,23) arasında en iyi dengeyi sağladığını göstermektedir. Ayrıca, model kararlarını daha iyi anlamak için Grad-CAM ve t-SNE analizleri kullanılmıştır. Genel olarak, önerilen yöntem, çift yönlü kırık tespiti için basit ve etkili bir yaklaşım sunmakta ve klinik tanıya destek sağlayabilmektedir.

🔖

Cite This Article

Cura, Ö. K., Çıklaçandır, F. G. Y., Efgan, M. G. (2026). Dual-View Deep Learning for Tibial Plateau Fracture Detection Using Input-Level Fusion of X-Ray Images. Journal of Artificial Intelligence and Data Science, Cilt: 6 Sayı: 1, 22–30. https://ajindex.com/articles/1618283

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (21)

  1. S. E. Karapinar, S. Korkmaz, and R. Dincer, “An Evaluation of Intra-articular Pathologies Accompanying Tibial Plateau Fractures Postoperatively,” Cureus, 16(10), 2024.
  2. J. L. Marsh, “Tibial plateau fractures,” In Management of Fractures in Severely Osteoporotic Bone: Orthopedic and Pharmacologic Strategies (pp. 296-308), 2000. London: Springer London.
  3. D. J. Haslhofer, N. Kraml, P. W. Winkler, T. Gotterbarm, and A. Klasan, “Risk for total knee arthroplasty after tibial plateau fractures: a systematic review,” Knee Surgery, Sports Traumatology, Arthroscopy, 31(11), 5145-5153, 2023.
  4. T. Resch, F. Hartz, L. Faber, P. Zehnder, G. Römmermann, A. Ellafi, and F. Greve, “Low rate of secondary interventions for post-traumatic osteoarthritis and satisfactory mid-to-long-term outcomes following tibial plateau fractures,” BMC Musculoskeletal Disorders, 26(1), 427, 2025.
  5. N. Manidakis, A. Dosani, R. Dimitriou, D. Stengel, S. Matthews, and P. Giannoudis, “Tibial plateau fractures: functional outcome and incidence of osteoarthritis in 125 cases,” International orthopaedics, 34(4), 565-570, 2010.
  6. P. J. Papagelopoulos, A. A. Partsinevelos, G. S. Themistocleous, A. F. Mavrogenis, D. S. Korres, and P. N. Soucacos, “Complications after tibia plateau fracture surgery,” Injury, 37(6), 475-484, 2006.
  7. R. L. M. Van Dreumel, B. P. W. Van Wunnik, L. Janssen, P. C. G. Simons, and H. M. J. Janzing, “Mid-to long-term functional outcome after open reduction and internal fixation of tibial plateau fractures,” Injury, 46(8), 1608-1612, 2015.
  8. C. Neidlein, J. Watrinet, R. Pätzold, D. P. Berthold, W. C. Prall, W. Böcker, and Bormann, M., “Patient-Reported outcomes following tibial plateau fractures: Mid-to Short-Term implications for knee function and activity level,” Journal of Clinical Medicine, 13(8), 2327, 2024.
  9. A. S. García, D. G. Quevedo, M. S. Casado, D. M. Garceso, L. de la Puerta Migueles, D. M. Molinero, and I. Tamimi, “The functional outcome and complication rates in tibial plateau fractures: A comparison between three different classification systems,” The Knee, 55, 214-225, 2025.
  10. K. D. Ahmed, and R. Hawezi, “Detection of bone fracture based on machine learning techniques,” Measurement: Sensors, 27, 100723, 2023.
  11. N. Van der Gaast, P. Bagave, N. Assink, S. Broos, R. L. Jaarsma, R. L., M. J. R Edwards, and Machine Learning Consortium, “Deep learning for tibial plateau fracture detection and classification,” The Knee, 54, 81-89, 2025.
  12. T. Huo, P. Liu, M. Xue, J. Zhang, Y. Xie, H. Wang, Z. Ye, “Deep learning diagnosis of adult tibial plateau fractures: multicenter study with external validation,” Radiology Advances, 2(3), 2025.
  13. S. P. Wang, H. T. Shih, Y. X. Liao, C. H. Wei, J. C. Liu, E. Kristiani, and C. T. Yang, “On Construction of Tibial Plateau Fracture Detection in Different Radiographic Views Using YOLO Models,” Diagnostics, 16(2), 182, 2026.
  14. N. Assink, M. P. Gonzalez-Perrino, R. Santana-Trejo, J. N. Doornberg, H. Hoekstra, J. Kraeima, and F. F. IJpma, “Development of machine learning–based algorithms to predict the 2-and 5-year risk of TKA after tibial plateau fracture treatment,” Clinical Orthopaedics and Related Research®, 483(9), 1731-1743, 2025.
  15. S. Abd El-Ghany, M. A. Mahmood, and A. A. Abd El-Aziz, “FracFusionNet: A Multi-Level Feature Fusion Convolutional Network for Bone Fracture Detection in Radiographic Images,” Diagnostics, 15(17), 2212, 2025.
  16. A. Subasi, “Applications of artificial intelligence in medical imaging,” Academic Press, 2022.
  17. A. W. Salehi, S. Khan, G. Gupta, B. I. Alabduallah, A. Almjally, H. Alsolai, A. Mellit, A., “A study of CNN and transfer learning in medical imaging: Advantages, challenges, future scope,” Sustainability, 15(7), 5930, 2023.
  18. A. Mahbod, N. Saeidi, S. Hatamikia, and R. Woitek, “Evaluating pre-trained convolutional neural networks and foundation models as feature extractors for content-based medical image retrieval,” Engineering Applications of Artificial Intelligence, 150, 110571, 2025.
  19. A. Souid, N. Sakli, H. Sakli, “Classification and predictions of lung diseases from chest x-rays using mobilenet v2,” Applied Sciences, 11(6), 2751, 2021.
  20. Z. Zhao, H. Chen, Y. P. Wang, D. Meng, Q. Xie, Q. Yu, and L. Wang, “Retinal disease diagnosis with unsupervised Grad-CAM guided contrastive learning,” Neurocomputing, 593, 127816, 2024.
  21. B. M. Malau, and M. O. Olusanya, “Comparative Evaluation of Parallel and Sequential Hybrid CNN–ViT Models for Wrist X-Ray Anomaly Detection,” Applied Sciences, 15(22), 11865, 2025.