International Journal of Engineering

International Journal of Engineering

An Ensemble Deep Learning Approach for Automated Bone Fracture Detection in Medical Imaging

Document Type : Original Article

Authors
M. Mahtabi 1
S. Asadi Amiri 1
S. Mavaddati 2
1 Department of Computer Engineering, Faculty of Engineering and Technology, University of Mazandaran, Babolsar, Iran
2 Department of Electronic Engineering, Faculty of Engineering and Technology, University of Mazandaran, Babolsar, Iran
10.5829/ije.2026.39.10a.19
Abstract
Recent advances in deep neural networks have significantly improved medical image analysis; however, detecting bone fractures in radiographic images remains challenging due to the complex skeletal structure, subtle fracture patterns, and limited annotated data. This study proposes an advanced ensemble deep learning framework that integrates two optimized architectures, EfficientNet-B4 and DenseNet-121, through a soft-voting fusion strategy to enable automated and precise bone fracture detection. The hybrid framework introduces adaptive weighting and optimized dense layers, which enhance feature discrimination and strengthen the network’s capacity to distinguish fine-grained fracture details. Moreover, transfer learning and fine-tuning techniques are employed to address data imbalance and improve model generalization across multiple anatomical regions. Comprehensive experiments conducted on the MURA dataset, consisting of radiographs from seven distinct anatomical regions, demonstrate that the proposed model achieves superior performance with 83.52% accuracy and 90.76% sensitivity, outperforming each individual baseline. The model’s robustness under different training configurations confirms its reliability and stability for clinical deployment. Overall, this research presents a novel ensemble-based diagnostic system that leverages complementary architectural strengths and adaptive feature fusion to achieve high diagnostic precision. The proposed method contributes not only to improving classification accuracy but also to establishing a scalable and interpretable framework for computer-aided fracture diagnosis, offering a practical step toward intelligent and reliable radiological decision support.

Graphical Abstract

An Ensemble Deep Learning Approach for Automated Bone Fracture Detection in Medical Imaging
Keywords
Deep Learning
Bone Abnormality Detection
Medical Image Analysis
Radiographic Images
EfficientNet-B4
DenseNet-121
Ensemble Learning

Subjects

1.    Lu S, Wang S, Wang G. A novel deep learning approach for image segmentation. Multimedia Tools and Applications. 2022;81:44487-503. https://doi.org/10.1007/s11042-022-13287-z
2.    Saggi SS, Kuah LZD, Toh LCA, Shah MTM, Wong MK, Abd Razak HRB. A novel approach to structural health monitoring using deep learning. Journal of Civil Engineering. 2023;50(2):115-32.
3.    Ioppolo F, Rompe JD, Furia JP, Cacchio A. Clinical application of shock wave therapy (SWT) in musculoskeletal disorders (MSDs). European Journal of Physical and Rehabilitation Medicine. 2014;50(2):217-30.
4.    Karthik K, Kamath SS. MSDNet: A deep neural ensemble model for abnormality detection and classification of plain radiographs. Journal of Ambient Intelligence and Humanized Computing. 2023;14(12):16099-113. https://doi.org/10.1007/s12652-022-03835-8
5.    Karthik K, Kamath SS. A deep neural network model for content-based medical image retrieval with multi-view classification. The Visual Computer. 2021;37(7):1837-50. https://doi.org/10.1007/s00371-020-01941-2
6.    Ying J, Dutta J, Guo N, Hu C, Zhou D, Sitek A, Li Q. Classification of exacerbation frequency in the COPDGene cohort using deep learning with deep belief networks. IEEE Journal of Biomedical and Health Informatics. 2016;24(6):1805-13. https://doi.org/10.1109/JBHI.2016.2642944
7.    Krupinski EA, Berbaum KS, Caldwell RT, Schartz KM, Kim J. Long radiology workdays reduce detection and accommodation accuracy. Journal of the American College of Radiology. 2010;7(9):698-704. https://doi.org/10.1016/j.jacr.2010.03.004
8.    Mukesh BR, Harish T, Mayya V, Kamath S. Deep learning based detection of diabetic retinopathy from inexpensive fundus imaging techniques. In: 2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT); 2021. 1-6. https://doi.org/10.1109/CONECCT52877.2021.9622703
9.    García-Floriano A, Ferreira-Santiago Á, Camacho-Nieto O, Yáñez-Márquez C. A machine learning approach to medical image classification: Detecting age-related macular degeneration in fundus images. Computers and Electrical Engineering. 2019;75:218-29. https://doi.org/10.1016/j.compeleceng.2017.11.008
10.    Nedumkunnel IM, George LE, Sowmya KS, Rosh NA, Mayya V. Explainable deep neural models for COVID-19 prediction from chest X-rays with region of interest visualization. In: 2nd International Conference on Secure Cyber Computing and Communications (ICSCCC); 2021. 96-101. https://doi.org/10.1109/ICSCCC51823.2021.9478152
11.    Mayya V, Karthik K, Sowmya KS, Karadka K, Jeganathan J. Coviddx: AI-based clinical decision support system for learning COVID-19 disease representations from multimodal patient data. In: International Conference on Health Informatics (HEALTHINF); 2021. p. 659-66.
12.    Rajpurkar P, Irvin J, Bagul A, Ding D, Duan T, Mehta H, Yang B, Zhu K, Laird D, Ball RL, Langlotz C. MURA: Large dataset for abnormality detection in musculoskeletal radiographs. arXiv. 2017. https://doi.org/10.48550/arXiv.1712.06957
13.    Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems. 2012;25:1097-105.
14.    Ebsim R, Naqvi J, Cootes TF. Automatic detection of wrist fractures from posteroanterior and lateral radiographs: A deep learning-based approach. In: International Workshop on Computational Methods and Clinical Applications in Musculoskeletal Imaging; 2018. p. 114-25. https://doi.org/10.1007/978-3-030-11166-3_10
15.    Chada G. Machine learning models for abnormality detection in musculoskeletal radiographs. Reports. 2019;2(4):26. https://doi.org/10.3390/reports2040026
16.    Yahalomi E, Chernofsky M, Werman M. Detection of distal radius fractures trained by a small set of X-ray images and Faster R-CNN. In: Intelligent Computing – Proceedings of the Computing Conference; 2019. p. 971-81. https://doi.org/10.1007/978-3-030-22871-2_69
17.    Yadav DP, Rathor S. Bone fracture detection and classification using deep learning approach. In: International Conference on Power Electronics and IoT Applications in Renewable Energy and its Control (PARC); 2020. 282-85. https://doi.org/10.1109/PARC49193.2020.236611
18.    Meena T, Roy S. Bone fracture detection using deep supervised learning from radiological images: A paradigm shift. Diagnostics. 2022;12(10):2420. https://doi.org/10.3390/diagnostics12102420
19.    Spahr A, Bozorgtabar B, Thiran JP. Self-taught semi-supervised anomaly detection on upper limb X-rays. In: IEEE International Symposium on Biomedical Imaging; 2021. 1632-36. https://doi.org/10.1109/ISBI48211.2021.9433771
20.    Dahal S, Thapa R, Panth S. A hybrid deep learning model for musculoskeletal abnormality detection. In: Proceedings of the 15th IOE Graduate Conference; 2024. 1-6.
21.    Hardalaç F, Uysal F, Peker O, Çiçeklidağ M, Tolunay T, Tokgöz N, Kutbay U, Demirciler B, Mert F. Fracture detection in wrist X-ray images using deep learning-based object detection models. Sensors. 2022;22(3):1285. https://doi.org/10.3390/s22031285
22.    Beyaz S, Yayli SB, Kılıc E, Doktur U. The ensemble artificial intelligence method: Detection of hip fractures in AP pelvis plain radiographs by majority voting using a multi-center dataset. Digital Health. 2023;9:1-14. https://doi.org/10.1177/20552076231216549
 
 
 
 
 
23.    Ghosh M, Hassan S, Debnath P. Ensemble based neural network for the classification of MURA dataset. Journal of Nature, Science and Technology. 2021;4:1-5.
24.    Lu X, Chang EY, Du J, Yan A, McAuley J, Gentili A, Hsu CN. Robust multi-view fracture detection in the presence of other abnormalities using HAMIL-Net. Military Medicine. 2023;188(Supplement 6):590-7. https://doi.org/10.1093/milmed/usad252
25.    Stanford ML Group. MURA dataset. Available from: https://stanfordmlgroup.github.io/competitions/mura/
26.    Zhang P, Yang L, Li D. EfficientNet-B4-Ranger: A novel method for greenhouse cucumber disease recognition under natural complex environment. Computers and Electronics in Agriculture. 2020;176:105652. https://doi.org/10.1016/j.compag.2020.105652
27.    Albelwi SA. Deep architecture based on DenseNet-121 model for weather image recognition. International Journal of Advanced Computer Science and Applications. 2022;13(10):559.
28.    Zhang Z, Sabuncu M. Generalized cross entropy loss for training deep neural networks with noisy labels. Advances in Neural Information Processing Systems. 2018;31.
29.    Agnihotri D, Verma K, Tripathi P, Singh BK. Soft voting technique to improve the performance of global filter based feature selection in text corpus. Applied Intelligence. 2019;49(4):1597-619. https://doi.org/10.1007/s10489-018-1349-1
30.    Mim MA, Majadi N, Mazumder P. A soft voting ensemble learning approach for credit card fraud detection. Heliyon. 2024;10:e25466. https://doi.org/10.1016/j.heliyon.2024.e25466
31.    Asadi Amiri S, Mohammadpoory Z, Nasrolahzadeh M. A novel content-based image retrieval system using fusing color and texture features. Journal of AI and Data Mining. 2022;10(4):559-68. https://doi.org/10.22044/jadm.2022.12042.2353
32.    McHugh ML. Interrater reliability: The kappa statistic. Biochemia Medica. 2012;22(3):276-82.
33.    Mavaddati S, Razavi M. An optimized YOLO-ViT hybrid model for enhanced precision in rice classification and quality assessment. International Journal of Engineering, Transactions A: Basics. 2025;38(10):2435-50. https://doi.org/10.5829/ije.2025.38.10a.19
34.    Mohammadi M, Talebpour A, Hosseinsabet A. Presenting effective methods in classification of echocardiographic views using deep learning. International Journal of Engineering, Transactions B: Applications. 2024;37(11):2150-61. https://doi.org/10.5829/ije.2024.37.11b.02
35.    Farsi H, Noursoleimani S, Mohamadzadeh S, Barati A. Multimodal biomedical image segmentation by using multi-path U-Net. International Journal of Engineering. 2025;38(1):179-93. https://doi.org/10.5829/ije.2025.38.01a.17
International Journal of Engineering
Volume 39, Issue 10
TRANSACTIONS A: Basics
October 2026
Pages 2583-2601