Skip to main content

Forensic bone age estimation of adolescent pelvis X-rays based on two-stage convolutional neural network

Abstract

In the forensic estimation of bone age, the pelvis is important for identifying the bone age of teenagers. However, studies on this topic remain insufficient as a result of lower accuracy due to the overlapping of pelvic organs in X-ray images. Segmentation networks have been used to automate the location of key pelvic areas and minimize restrictions like doubling images of pelvic organs to increase the accuracy of estimation. This study conducted a retrospective analysis of 2164 pelvis X-ray images of Chinese Han teenagers ranging from 11 to 21 years old. Key areas of the pelvis were detected with a U-Net segmentation network, and the findings were combined with the original X-ray image for regional augmentation. Bone age estimation was conducted with the enhanced and not enhanced pelvis X-ray images by separately using three convolutional neural networks (CNNs). The root mean square errors (RMSE) of the Inception-V3, Inception-ResNet-V2, and VGG19 convolutional neural networks were 0.93 years, 1.12 years, and 1.14 years, respectively, and the mean absolute errors (MAE) of these networks were 0.67 years, 0.77 years, and 0.88 years, respectively. For comparison, a network without segmentation was employed to conduct the estimation, and it was found that the RMSE of the three CNNs above became 1.22 years, 1.25 years, and 1.63 years, respectively, and the MAE became 0.93 years, 0.96 years, and 1.23 years. Bland–Altman plots and attention maps were also generated to provide a visual comparison. The proposed segmentation network can be used to reduce the influence of restrictions like image overlapping of organs and can thus increase the accuracy of pelvic bone age estimation.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

References

  1. Greulich WW, Pyle SI (1959) Radiographic atlas of skeletal development of the hand and wrist. AM J MED SCI 238:393. https://doi.org/10.1097/00000441-195909000-00030

    Article  Google Scholar 

  2. Ehrenberg ASC, Tanner JM, Whitehouse RH, Marshall WA, Goldstein H (1977) Estimation of skeletal maturity and prediction of adult height (TWII-method). Appl Stat 26:80. https://doi.org/10.2307/2346874

    Article  Google Scholar 

  3. Michael DJ, Nelson AC (1989) HANDX: a model-based system for automatic segmentation of bones from digital hand radiographs. IEEE Trans Med Imaging 8:64–69. https://doi.org/10.1109/42.20363

    CAS  Article  PubMed  Google Scholar 

  4. Tanner JM, Gibbons RD (1994) Automatic bone age measurement using computerized image analysis. J Pediatr Endocrinol 7:141–145. https://doi.org/10.1515/jpem.1994.7.2.141

    CAS  Article  PubMed  Google Scholar 

  5. Halabi SS, Prevedello LM, Kalpathy-Cramer J, Mamonov AB, Bilbily A, Cicero M, Pan I, Pereira LA, Sousa RT, Abdala N, Kitamura FC, Thodberg HH, Chen L, Shih G, Andriole K, Kohli MD, Erickson BJ, Flanders AE (2019) The RSNA pediatric bone age machine learning challenge. Radiology 290:498–503. https://doi.org/10.1148/radiol.2018180736

    Article  PubMed  Google Scholar 

  6. Campanella G, Hanna MG, Geneslaw L, Miraflor A, Werneck KSV, Busam KJ, Brogi E, Reuter VE, Klimstra DS, Fuchs TJ (2019) Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. NAT MED. https://doi.org/10.1038/s41591-019-0508-1

    Article  PubMed  PubMed Central  Google Scholar 

  7. Liu Y, Balagurunathan Y, Atwater T, Antic S, Li Q, Walker RC, Smith GT, Massion PP, Schabath MB, Gillies RJ (2017) Radiological image traits predictive of cancer status in pulmonary nodules. CLIN CANCER RES 23:1442–1449. https://doi.org/10.1158/1078-0432.ccr-15-3102

    Article  PubMed  Google Scholar 

  8. Zhang B, He X, Ouyang F, Gu D, Dong Y, Zhang L, Mo X, Huang W, Tian J, Zhang S (2017) Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma. CANCER LETT 403:21–27. https://doi.org/10.1016/j.canlet.2017.06.004

    CAS  Article  PubMed  Google Scholar 

  9. Ming C, Viassolo V, Probst-Hensch N, Chappuis PO, Dinov ID, Katapodi MC (2019) Machine learning techniques for personalized breast cancer risk prediction: comparison with the BCRAT and BOADICEA models. BREAST CANCER RES 21:75. https://doi.org/10.1186/s13058-019-1158-4

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  10. Guo Y, Han M, Chi Y, Long H, Zhang D, Yang J, Yang Y, Chen T, Du S (2021) Accurate age classification using manual method and deep convolutional neural network based on orthopantomogram images. Int J Legal Med 135:1589–1597. https://doi.org/10.1007/s00414-021-02542-x

    Article  PubMed  Google Scholar 

  11. Diedrichs V, Wagner UA, Seiler W, Schmitt O (1998) Reference values for development of the iliac crest apophysis (Risser sign). Z Orthop Ihre Grenzgeb 136:226–229. https://doi.org/10.1055/s-2008-1054227

    CAS  Article  PubMed  Google Scholar 

  12. Risser JC (2010) The classic: The iliac apophysis: an invaluable sign in the management of scoliosis. 1958. Clin Orthop Relat Res 468:643–653. https://doi.org/10.1007/s11999-009-1096-z

    Article  PubMed  Google Scholar 

  13. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. IEEE 2818-2826. https://doi.org/10.1109/cvpr.2016.308

  14. Szegedy C, Ioffe S, Vanhoucke V, Alemi A (2016) Inceptionv4, Inception-ResNet and the impact of residual connections on learning. Thirty-First AAAI Conference on Artificial Intelligence 4278–4284. http://arxiv.org/1602.07261v2

  15. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations 1–14. http://arxiv.org/abs/1409.1556v6

  16. Group CSPA (2007) Report on the physical fitness and health surveillance of Chinese school students in 2005. Higher Educaion Press, Beijing

    Google Scholar 

  17. Krizhevsky A, Sutskever I, Hinton G (2017) ImageNet classification with deep convolutional neural networks. Communications of the ACM 60:84–90

  18. Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention. Springer Press, Berlin. https://doi.org/10.1007/978-3-319-24574-4_28

  19. Verma S, Nagar R, Raman S (2020). Fast semantic feature extraction using superpixels for soft segmentation. In International Conference on Computer Vision and Image Processing. Springer Press, Rio de Janeiro. https://doi.org/10.1007/978-981-15-4015-8

  20. Ghosh S, Das I, Das N, Das I, Maulik U (2019) Understanding deep learning techniques for image segmentation. Z Orthop Ihre Grenzgeb 52(4):40. https://doi.org/10.1145/3329784

    Article  Google Scholar 

  21. Li Y, Huang Z, Dong X, Liang W, Xue H, Zhang L, Zhang Y, Deng Z (2019) Forensic age estimation for pelvic X-ray images using deep learning. EUR RADIOL 29:2322–2329. https://doi.org/10.1007/s00330-018-5791-6

    Article  PubMed  Google Scholar 

  22. Kotěrová A, Navega D, Štepanovský M et al (2018) Age estimation of adult human remains from hip bones using advanced methods[J]. Forensic Sci Int 287:163–175. https://doi.org/10.1016/j.forsciint.2018.03.047

    Article  PubMed  Google Scholar 

  23. Fan F, Dong X, Wu X et al (2020) An evaluation of statistical models for age estimation and the assessment of the 18-year threshold using conventional pelvic radiographs[J]. Forensic Sci Int 314:110350. https://doi.org/10.1016/j.forsciint.2020.110350

    Article  PubMed  Google Scholar 

  24. Larson DB, Chen MC, Lungren MP, Halabi SS, Stence NV, Langlotz CP (2018) Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs. Radiology 287:313–322. https://doi.org/10.1148/radiol.2017170236

    Article  PubMed  Google Scholar 

  25. Creo AL, Frederick Schwenk II W (2017) Bone age: a handy tool for pediatric providers. Pediatrics 140(6):e20171486. https://doi.org/10.1542/peds.2017-1486

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

The authors would like to thank letPub (www.letpub.com) for its linguistic assistance during the preparation of this manuscript.

Funding

This work was supported by the National Natural Science Foundation of China under Grant Nos. 81571859, 81102305, and 81701869; Shanghai 2019 “Science and Technology Innovation Action Plan” technical standard project guide under Grant No. 19DZ2201300; and the Science and Technology Committee of Shanghai Municipality under Grant Nos. 17DZ2273200 and 19DZ2292700.

Author information

Authors and Affiliations

Authors

Contributions

Guarantor of integrity of entire study: Ya-Hui Wang and Hu Zhao; study concepts/study design or data acquisition or data analysis/interpretation: all authors; manuscript drafting or manuscript revision for important intellectual content: all authors; approval of final version of submitted manuscript: all authors; agrees to ensure any questions related to the work are appropriately resolved: all authors; literature research: Ya-Hui Wang, Li-Qin Peng, and Yu-Cheng Guo; clinical studies: Ya-Hui Wang, Hu Zhao, and Li-Qin Peng; experimental studies: Li-Qin Peng, Tai-Ang Liu, and Lei Wan and Peng Wang; statistical analysis: Li-Qin Peng and Ya-Hui Wang; and manuscript editing: Li-Qin Peng, Yu-Cheng Guo, Ya-Hui Wang, and Hu Zhao.

Corresponding authors

Correspondence to Hu Zhao or Ya-Hui Wang.

Ethics declarations

Ethical approval

Ethical approval was granted by the ethics committee of the Academy of Forensic Science, Ministry of Justice, People’s Republic of China. All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards. Correct ethical informed consent has been obtained before our study.

Conflict of interest

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

Verify currency and authenticity via CrossMark

Cite this article

Peng, LQ., Guo, Yc., Wan, L. et al. Forensic bone age estimation of adolescent pelvis X-rays based on two-stage convolutional neural network. Int J Legal Med 136, 797–810 (2022). https://doi.org/10.1007/s00414-021-02746-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00414-021-02746-1

Keywords

  • Bone age estimation
  • Pelvis
  • Image recognition
  • Deep learning
  • Convolutional neural networks
  • Adolescent