Skip to main content
SpringerLink
Log in

Comparison of Transfer Learning Models in Pelvic Tilt and Rotation Measurement in Pediatric Anteroposterior Pelvic Radiographs

  • Published:
Journal of Digital Imaging Aims and scope Submit manuscript

Abstract

The rotation and tilt of the pelvis during anteroposterior pelvic radiography can lead to misdiagnosis of developmental dysplasia of the hip (DDH) in children. At present, no method exists for accurately and conveniently measuring the precise rotation and tilt angles of pelvic on radiographs. The objective of this study was to develop several rotation and tilt measurement models using transfer learning and digital reconstructed radiographs (DRRs), and to compare their performances on pelvic radiographs. Based on the inclusion criteria, 30 of 92 children who underwent 3D hip CT scans at Xijing Hospital from 2015 to 2020 were included in the study. Using DRR techniques, radiographs were generated by rotating and tilting the pelvis in CT datasets at − 12 to 12° (projected every 3°) and were randomized to a 2:1:1 ratio of training dataset, validation dataset, and test dataset. Five pre-trained networks, including VGG16, Xception, VGG19, ResNet50 and InceptionV3 were used to develop pelvic rotation measurement models and tilt measurement models, and these models were trained with training dataset. The callback function was used during the training to slow down the learning rate when learning was stalled. Then, the validation set was used to optimize each model and compare their performances. At last, we tested the final performances of optimal rotation measurement model and optimal tilt measurement model on test dataset. The mean absolute error (MAE) was employed to assess the performance of the models. A total of 2430 pelvic DRRs were collected based on 30 CT datasets. Among 5 pre-trained transfer learning models, VGG16-Tilt achieved the best tilt prediction performance at the same BS and different LR. VGG16-Tilt model achieved its best performance on validation set at LR = 0.001 and BS = 4, and the final MAE on the test set was 0.5250°. In terms of rotation prediction, VGG16-Rotation also achieved the best performance, and it achieved its best performance on validation set at LR = 0.002 and BS = 8. The final MAE of VGG16-Rotation on the test set was 1.0731°. Pretrained transfer learning models worked well in predicting tilt and rotation angles of the pelvis on radiographs in children. Among them, VGG16-Tilt and VGG16-Rotation had the best effect in dealing with such problems despite their simple structures. These models deployed in devices can give orthopedic surgeons a powerful aid in DDH diagnosis.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Data Availability

The data are available from the corresponding author upon reasonable request and with permission from the Xijing Hospital, Fourth Military Medical University.

Abbreviations

BS:

Batch size

CNN:

Convolutional neural network

DDH:

Developmental dysplasia of the hip

DRR:

Digital reconstructed radiograph

LR:

Learning rate

MAE:

Mean absolute error

MSE:

Mean square error

ReLU:

Rectified linear unit

VGG:

Visual geometry group

References

  1. Weinstein SL, Mubarak SJ, Wenger DR. Developmental hip dysplasia and dislocation: Part I. Instr Course Lect. 2004. 53: 523-30.

    PubMed  Google Scholar 

  2. Donnelly KJ, Chan KW, Cosgrove AP. Delayed diagnosis of developmental dysplasia of the hip in Northern Ireland: can we do better. Bone Joint J. 2015. 97-B(11): 1572–6.

  3. Kosuge D, Yamada N, Azegami S, Achan P, Ramachandran M. Management of developmental dysplasia of the hip in young adults: current concepts. Bone Joint J. 2013. 95-B(6): 732–7.

  4. Mulpuri K, Song KM. AAOS Clinical Practice Guideline: Detection and Nonoperative Management of Pediatric Developmental Dysplasia of the Hip in Infants up to Six Months of Age. J Am Acad Orthop Surg. 2015. 23(3): 206-7.

    Article  PubMed  Google Scholar 

  5. Keller MS, Nijs EL. The role of radiographs and US in developmental dysplasia of the hip: how good are they. Pediatr Radiol. 2009. 39 Suppl 2: S211-5.

    Article  PubMed  Google Scholar 

  6. Simon EA, Saur F, Buerge M, Glaab R, Roos M, Kohler G. Inter-observer agreement of ultrasonographic measurement of alpha and beta angles and the final type classification based on the Graf method. Swiss Med Wkly. 2004. 134(45-46): 671-7.

    CAS  PubMed  Google Scholar 

  7. Roovers EA, Boere-Boonekamp MM, Geertsma TS, Zielhuis GA, Kerkhoff AH. Ultrasonographic screening for developmental dysplasia of the hip in infants. Reproducibility of assessments made by radiographers. J Bone Joint Surg Br. 2003. 85(5): 726–30.

  8. Rosendahl K, Aslaksen A, Lie RT, Markestad T. Reliability of ultrasound in the early diagnosis of developmental dysplasia of the hip. Pediatr Radiol. 1995. 25(3): 219-24.

    Article  CAS  PubMed  Google Scholar 

  9. Wilkin GP, Ibrahim MM, Smit KM, Beaulé PE. A Contemporary Definition of Hip Dysplasia and Structural Instability: Toward a Comprehensive Classification for Acetabular Dysplasia. J Arthroplasty. 2017. 32(9S): S20-S27.

    Article  PubMed  Google Scholar 

  10. Ghasseminia S, Hareendranathan AR, Jaremko JL. Narrative Review on the Role of Imaging in DDH. Indian J Orthop. 2021. 55(6): 1456-1465.

    Article  PubMed  PubMed Central  Google Scholar 

  11. Starr V, Ha BY. Imaging update on developmental dysplasia of the hip with the role of MRI. AJR Am J Roentgenol. 2014. 203(6): 1324-35.

    Article  PubMed  Google Scholar 

  12. Fayad LM, Johnson P, Fishman EK. Multidetector CT of musculoskeletal disease in the pediatric patient: principles, techniques, and clinical applications. Radiographics. 2005. 25(3): 603-18.

    Article  PubMed  Google Scholar 

  13. Chin MS, Betz BW, Halanski MA. Comparison of hip reduction using magnetic resonance imaging or computed tomography in hip dysplasia. J Pediatr Orthop. 2011. 31(5): 525-9.

    Article  PubMed  Google Scholar 

  14. LeBa TB, Carmichael KD, Patton AG, Morris RP, Swischuk LE. Ultrasound for Infants at Risk for Developmental Dysplasia of the Hip. Orthopedics. 2015. 38(8): e722-6.

    Article  PubMed  Google Scholar 

  15. Mathews JD, Forsythe AV, Brady Z, et al. Cancer risk in 680,000 people exposed to computed tomography scans in childhood or adolescence: data linkage study of 11 million Australians. BMJ. 2013. 346: f2360.

    Article  PubMed  PubMed Central  Google Scholar 

  16. Sewell MD, Rosendahl K, Eastwood DM. Developmental dysplasia of the hip. BMJ. 2009. 339: b4454.

    Article  CAS  PubMed  Google Scholar 

  17. Yang Y, Porter D, Zhao L, Zhao X, Yang X, Chen S. How to judge pelvic malposition when assessing acetabular index in children? Three simple parameters can determine acceptability. J Orthop Surg Res. 2020. 15(1): 12.

    Article  PubMed  PubMed Central  Google Scholar 

  18. Lee YK, Chung CY, Koo KH, Lee KM, Kwon DG, Park MS. Measuring acetabular dysplasia in plain radiographs. Arch Orthop Trauma Surg. 2011. 131(9): 1219-26.

    Article  PubMed  Google Scholar 

  19. van der Bom MJ, Groote ME, Vincken KL, Beek FJ, Bartels LW. Pelvic rotation and tilt can cause misinterpretation of the acetabular index measured on radiographs. Clin Orthop Relat Res. 2011. 469(6): 1743-9.

    Article  PubMed  PubMed Central  Google Scholar 

  20. Tönnis D. Normal values of the hip joint for the evaluation of X-rays in children and adults. Clin Orthop Relat Res. 1976. (119): 39-47.

    Google Scholar 

  21. Siebenrock KA, Kalbermatten DF, Ganz R. Effect of pelvic tilt on acetabular retroversion: a study of pelves from cadavers. Clin Orthop Relat Res. 2003. (407): 241-8.

    Article  Google Scholar 

  22. Tannast M, Murphy SB, Langlotz F, Anderson SE, Siebenrock KA. Estimation of pelvic tilt on anteroposterior X-rays--a comparison of six parameters. Skeletal Radiol. 2006. 35(3): 149-55.

    Article  CAS  PubMed  Google Scholar 

  23. Li Q, Zhong L, Huang H, et al. Auxiliary diagnosis of developmental dysplasia of the hip by automated detection of Sharp's angle on standardized anteroposterior pelvic radiographs. Medicine (Baltimore). 2019. 98(52): e18500.

    Article  PubMed  PubMed Central  Google Scholar 

  24. Zhang SC, Sun J, Liu CB, Fang JH, Xie HT, Ning B. Clinical application of artificial intelligence-assisted diagnosis using anteroposterior pelvic radiographs in children with developmental dysplasia of the hip. Bone Joint J. 2020. 102-B(11): 1574–1581.

  25. Lemieux L, Jagoe R, Fish DR, Kitchen ND, Thomas DG. A patient-to-computed-tomography image registration method based on digitally reconstructed radiographs. Med Phys. 1994. 21(11): 1749-60.

    Article  CAS  PubMed  Google Scholar 

  26. Markelj P, Tomaževič D, Likar B, Pernuš F. A review of 3D/2D registration methods for image-guided interventions. Med Image Anal. 2012. 16(3): 642-61.

    Article  CAS  PubMed  Google Scholar 

  27. Commission NH. Requirements for radiological protection in diagnostic radiology: GBZ 130–2020. China. 2020.

  28. Health D. Radiological protection requirements for X-ray computed tomography: GBZ 165–2012. China. 2013.

  29. Omiotek Z, Kotyra A. Flame Image Processing and Classification Using a Pre-Trained VGG16 Model in Combustion Diagnosis. Sensors (Basel). 2021. 21(2).

  30. Han B, Du J, Jia Y, Zhu H. Zero-Watermarking Algorithm for Medical Image Based on VGG19 Deep Convolution Neural Network. J Healthc Eng. 2021. 2021: 5551520.

    Article  PubMed  PubMed Central  Google Scholar 

  31. Rahimzadeh M, Attar A. A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2. Inform Med Unlocked. 2020. 19: 100360.

    Article  PubMed  PubMed Central  Google Scholar 

  32. Portinaro NM, Murray DW, Bhullar TP, Benson MK. Errors in measurement of acetabular index. J Pediatr Orthop. 1995. 15(6): 780-4.

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

The content of this paper is solely the responsibility of the authors and does not represent the official views of funders. We would like to thank all collaborators and participants, especially Tao Wang and Yajie Yu, for their contribution to our research.

Funding

This study was supported in part by China National Natural Science Foundation [81171735], Shaanxi Natural Science Foundation [2017JC2-04] and Fourth Military Medical University.

Author information

Authors and Affiliations

  1. Department of Orthopedics, Xijing Hospital, Air Force Military Medical University, No.169 Changle West Road, Xi’an, Shaanxi Province, 710032, China

    Chao Li, Yabo Yan, Huifa Xu, Jia Sha, Zongzhi Fan & Luyu Huang

  2. School of Electrical Engineering, Xi’an Jiaotong University, No.28 West Xianning Road, Xi’an, Shaanxi, 710049, China

    Hui Cao

  3. Department of Radiation Medicine, Preventive Medicine School, Air Force Military Medical University, No.169 Changle West Road, Xi’an, Shaanxi, 710032, China

    Jie Zhang

Authors
  1. Chao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yabo Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Huifa Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hui Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jie Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jia Sha
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Zongzhi Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Luyu Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

HLY, CH, ZJ and LC contributed to the study design. LC, YYB, and XHF contributed to the data analysis and drafted the manuscript. HLY directed data collection and provided administrative support for the project. All authors contributed to interpretation of the data, commented on the manuscript, revised the manuscript, revised the manuscript, and approved the final version for publication.

Corresponding author

Correspondence to Luyu Huang.

Ethics declarations

Ethics Approval

Approval was obtained from the Ethics Committee of the Xijing Hospital of Fourth Military Medical University. The procedures used in this study adhere to the tenets of the Declaration of Helsinki.

Consent to Participate

Informed consent was obtained from all individual participants and their legal guardians included in the study.

Competing Interests

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, C., Yan, Y., Xu, H. et al. Comparison of Transfer Learning Models in Pelvic Tilt and Rotation Measurement in Pediatric Anteroposterior Pelvic Radiographs. J Digit Imaging 35, 1506–1513 (2022). https://doi.org/10.1007/s10278-022-00672-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-022-00672-1

Keywords

Search

Navigation