Sign Up Submit Enquiry

Analysis of Developmental Dysplasia of the Hip Using Deep Learning Techniques

Home Analysis of Developmental Dysplasia of the Hip Using Deep Learning Techniques

Related Articles

Contact us

Article Content

Abstract

Purpose

Developmental dysplasia of the hip (DDH) is a relatively common musculoskeletal condition in neonates. Early detection with ultrasound (US) is crucial for effective treatment. This study aimed to evaluate images obtained from hip ultrasonography with deep learning methods.

Material and Method

Patients who underwent hip ultrasonography between January 2018 and September 2021 and were found to have normal hips and hip dysplasia were retrospectively screened. A total of 947 patient images, 450 girls and 497 boys, were examined. According to the Graf method, images were classified without any marking. In the first stage, two groups were created: those with Type 1 mature hips and those with dysplastic hips (other types). In the second stage of the study, four groups were created using only the α angle: 451 were classified as Type 1, 326 as Type 2a and 2b, 137 as Type 2c and D, and 33 as Type 3 and Type 4.

During the classification, three versions of the EfficientNet model, one of the current deep learning models, were used. Classifiers were included in the study to improve the accuracy values of the models. In our study, two classifiers named support vector machine and K-nearest neighbors were used.

Results

In the classification phase with deep learning models, the highest accuracy value of 0.9577 was obtained with the EfficientNetB1 model for 2 classes in the first group, while the highest accuracy value of 0.8571 was obtained with the EfficientNetB0 model for 4 classes in the second group. By including the classifiers in the evaluation, the highest accuracy rate was found to be 0.99 with EfficientNetB1 and 1(100%) with EfficientNetB2 in the first group, while it was 0.97 with EfficientNetB0 in the second group.

Conclusion

In the diagnosis of developmental hip dysplasia, high accuracy rates were obtained in deep learning methods using US images. Accuracy rates increased with the addition of classifiers to the models.

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

  • Developmental Disabilities
  • Hypospadias
  • Machine Learning
  • Osteogenesis imperfecta
  • Preterm birth
  • Statistical Learning

Data Availability

No datasets were generated or analysed during the current study.

Code Availability

Not applicable.

References

  1. Pavone V, de Cristo C, Vescio A, Lucenti L, Sapienza M, Sessa G, Pavone P, Testa G. Dynamic and static splinting for treatment of developmental dysplasia of the hip: a systematic review. Children (Basel). 2021;8(2):104.

    PubMed Google Scholar

  2. Barrera CA, Cohen SA, Sankar WN, Ho-Fung VM, Sze RW, Nguyen JC. Imaging of developmental dysplasia of the hip: ultrasound, radiography and magnetic resonance imaging. Pediatr Radiol. 2019;49(12):1652–68.

    PubMed Google Scholar

  3. Graf R. The diagnosis of congenital hip-joint dislocation by the ultrasonic Combound treatment. Arch Orthop Trauma Surg. 1980;97(2):117–33.

    CAS PubMed Google Scholar

  4. Omeroğlu H. Use of ultrasonography in developmental dysplasia of the hip. J Child Orthop. 2014;8(2):105–13. https://doi.org/10.1007/s11832-014-0561-8.

    Article PubMed PubMed Central Google Scholar

  5. Yıldız K, Yıldız V. Determination of developmental dysplasia of the hip using artificial neural networks (ANN) on ultrasound viewing according to Graf’s method. New Trends in Medicine Sciences. 2020;1(2):106–17.

    Google Scholar

  6. Hareendranathan AR, Chahal BS, Zonoobi D, Sukhdeep D, Jaremko JL. Artificial ıntelligence to automatically assess scan quality in hip ultrasound. Indian J Orthop. 2021;55(6):1535–42.

    PubMed PubMed Central Google Scholar

  7. Valkenborg D, Rousseau AJ, Geubbelmans M, Burzykowski T. Support vector machines. Am J Orthod Dentofacial Orthop. 2023;164(5):754–7. https://doi.org/10.1016/j.ajodo.2023.08.003.

    Article PubMed Google Scholar

  8. Zhang Z. Introduction to machine learning: k-nearest neighbors. Ann Transl Med. 2016;4(11):218. https://doi.org/10.21037/atm.2016.03.37.

    Article PubMed PubMed Central Google Scholar

  9. Jacobsen S, Sonne-Holm S. Hip dysplasia: a significant risk factor for the development of hip osteoarthritis. A cross-sectional survey Rheumatology (Oxford). 2005;44(2):211–8. https://doi.org/10.1093/rheumtology/keh436.

    Article CAS PubMed Google Scholar

  10. Shorter D, Hong T, Osborn DA. Cochrane review: screening programmes for developmental dysplasia of the hip in newborn infants. Evid Based Child Health. 2013;8(1):11–54. https://doi.org/10.1002/ebch.1891.

    Article PubMed Google Scholar

  11. Tan M, LE Q. EfficientNet: rethinking model scaling for convolutional neural networks. In: International conference on machine learning. PMLR, 2019; 6105–14

  12. Hareendranathan AR, Chahal B, Ghasseminia S, Zonoobi D, Jaremko JL. Impact of scan quality on AI assessment of hip dysplasia ultrasound. J Ultrasound. 2022;25(2):145–53. https://doi.org/10.1007/s40477-021-00560-4.

    Article PubMed Google Scholar

  13. Paserin, O., Mulpuri, K., Cooper, A., Hodgson, A. J., & Garbi, R. (2018). Real time RNN based 3D ultrasound scan adequacy for developmental dysplasia of the hip. Medical image computing and computer assisted intervention—MICCAI. 365–373. Springer International Publishing.

Funding

Not applicable.

Author information

Authors and Affiliations

  1. Batman Training and Research Hospital, Radiology Clinic, Batman, Turkey

    Ramazan Çelik

  2. Hendek State Hospital, Radiology Clinic, Sakarya, Turkey

    Adem Yokuş

  3. Faculty of Medicine, Department of Radiology, Van Yüzüncü Yıl University, Van, Turkey

    Ali Mahir Gündüz, Nurşen Toprak & Saim Türkoğlu

  4. Faculty of Engineering, Department of Computer Engineering, Van Yüzüncü Yıl University, Van, Turkey

    Murat Canayaz

Contributions

Ramazan Çelik: Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Validation, Visualization, Writing original draft. Adem Yokuş, Ali Mahir Gündüz: Conceptualization, Investigation, Methodology, Project administration, Supervision, Validation, Visualization, Writing original draft, Writing – review & editing. Murat Canayaz: Conceptualization, Data curation, Deep learning analysis, Investigation, Methodology, Validation, Visualization, Writing original draft. Nurşen Toprak, Saim Türkoğlu: Data curation, Investigation, Resources, Supervision, Visualization, Writing original draft.

Corresponding author

Correspondence to Adem Yokuş.

Ethics declarations

Ethics Approval

This study was performed in line with the principles of the Declaration of Helsinki. The study procedure was approved by Van Yüzüncü Yıl University Ethics Committee of Non-interventional Research, (date: 18/03/2022, issue number: 2022/03–11).

Consent to Participate

Not applicable.

Consent for Publication

All participants in this study have given written consent for the study to be published.

Competing Interests

The authors declare no competing interests.

Additional information

About this article

Cite this article

Çelik, R., Yokuş, A., Gündüz, A.M. et al. Analysis of Developmental Dysplasia of the Hip Using Deep Learning Techniques. SN Compr. Clin. Med. 7, 214 (2025). https://doi.org/10.1007/s42399-025-01998-x

  • Received
  • Revised
  • Accepted
  • Published
  • DOI https://doi.org/10.1007/s42399-025-01998-x

Keywords

  • Developmental dysplasia of the hip
  • Hip ultrasound
  • Deep learning
  • Convolutional neural network

Copyright © All rights reserved Designed and Developed by Digital Flavers

WhatsApp