AN INTELLIGENT SYSTEM FOR DETECTING SHOULDER JOINT IN RADIOGRAPHIC IMAGES USING DEEP LEARNING

Authors

  • Nietbay Uteulievich Uteuliev

    Nukus State Technical University

  • Gafur Muratbaevich Djaykov

    Nukus State Technical University

  • Javlonbek Ziyatbaevichi Artikbaev

    Nukus State Technical University

  • Nursultan Ibadullaevich Sagidullaev

    Tashkent University of Information Technology image/svg+xml

Keywords: deep learning, EfficientNet, radiography, fractures, MURA, classification

Abstract

This paper presents a deep learning-based model for automatic shoulder fracture detection using EfficientNet-B0. The model was trained on the XR_SHOULDER subset of the MURA dataset. The achieved accuracy of about 80% confirms the effectiveness of the proposed approach.

References

1. Chung S. W. et al. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. // Acta orthopaedica. Т. 89, №4, 2018. – С. 468-473.

2. Sperling Jr J. W. et al. A deep learning algorithm to detect proximal humerus fractures on radiographs. // JSES Reviews, Reports and Techniques, 2025.

3. Lundervold A.S., Lundervold A. An overview of deep learning in medical imaging focusing on MRI and X-ray. // Zeitschrift für Medizinische Physik. Vol. 29, №2, 2019. – P. 102-127.

4. Esteva A. et al. A guide to deep learning in healthcare. // Nature medicine. Т. 25, №1, 2019. – С. 24-29.

5. Tan M., Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks. // International conference on machine learning. PMLR, 2019. – С. 6105-6114.

6. Zech J.R. et al. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. // PLoS medicine. Т. 15, №11, 2018. – С. e1002683.