Journal of Biomedical Physics and Engineering

Current Issue

By Issue

By Author

By Subject

Author Index

Keyword Index

About Journal

Aims and Scope

Staff Members

Editorial Board

Publication Ethics

Indexing and Abstracting

Related Links

FAQ

Peer Review Process

News

AE-BoNet: A Deep Learning Method for Pediatric Bone Age Estimation using an Unsupervised Pre-Trained Model

Document Type : Original Research

Authors

1 Department of Medical Physics, Faculty of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran

2 Department of Applied Mathematics, Faculty of Sciences and Modern Technologies, Graduate University of Advanced Technology, Kerman, Iran

10.31661/jbpe.v0i0.2304-1609

Abstract

Background: Accurate bone age assessment is essential for determining the actual degree of development and indicating a disorder in growth. While clinical bone age assessment techniques are time-consuming and prone to inter/intra-observer variability, deep learning-based methods are used for automated bone age estimation.
Objective: The current study aimed to develop an unsupervised pre-training approach for automatic bone age estimation, addressing the challenge of limited labeled data and unique features of radiographic images of hand bones. Bone age estimation is complex and usually requires more labeling data. On the other hand, there is no model trained with hand radiographic images, reused for bone age estimation.
Material and Methods: In this fundamental-applied research, the collection of Radiological Society of North America (RSNA) X-ray image collection is used to evaluate the efficiency of the proposed bone age estimation method. An autoencoder is trained to reconstruct the original hand radiography images. Then, a model based on the trained encoder produces the final estimation of bone age.
Results: Experimental results on the Radiological Society of North America (RSNA) X-ray image collection achieve a Mean Absolute Error (MAE) of 9.3 months, which is comparable to state-of-the-art methods. 
Conclusion: This study presents an approach to estimating bone age on hand radiographs utilizing unsupervised pre-training with an autoencoder and also highlights the significance of autoencoders and unsupervised learning as efficient substitutes for conventional techniques.

Highlights

Mojtaba Sirati-Amsheh (Google Scholar)

Elham Shabaninia (Google Scholar)

Keywords

References
  1. Spampinato C, Palazzo S, Giordano D, Aldinucci M, Leonardi R. Deep learning for automated skeletal bone age assessment in X-ray images. Med Image Anal. 2017;36:41-51. doi: 10.1016/j.media.2016.10.010. PubMed PMID: 27816861.
  2. Greulich WW, Pyle SI. Radiographic atlas of skeletal development of the hand and wrist. The American Journal of the Medical Sciences. 1959;238(3):393.
  3. Tanner JM. Assessement of Skeletal Maturity and Predicting of Adult Height (TW2 Method). Prediction of Adult Height. 1983:22-37.
  4. Tanner J, Healy M, Goldstein H, Cameron N. Prediction of Adult Height TW3 equations. In: Assessment of Skeletal Maturity and Prediction of adult height by TE3 method, 3rd ed. London, WB Saunders; 2001. p. 26-43.
  5. Li K, Zhang J, Sun Y, Huang X, Sun C, Xie Q, Cong S. Automatic bone age assessment of adolescents based on weakly-supervised deep convolutional neural networks. IEEE Access. 2021;9:120078-87. doi: 10.1109/ACCESS.2021.3108219.
  6. Fritz B, Marbach G, Civardi F, Fucentese SF, Pfirrmann CWA. Deep convolutional neural network-based detection of meniscus tears: comparison with radiologists and surgery as standard of reference. Skeletal Radiol. 2020;49(8):1207-17. doi: 10.1007/s00256-020-03410-2. PubMed PMID: 32170334. PubMed PMCID: PMC7299917.
  7. Chea P, Mandell JC. Current applications and future directions of deep learning in musculoskeletal radiology. Skeletal Radiol. 2020;49(2):183-97. doi: 10.1007/s00256-019-03284-z. PubMed PMID: 31377836.
  8. Grauhan NF, Niehues SM, Gaudin RA, Keller S, Vahldiek JL, Adams LC, Bressem KK. Deep learning for accurately recognizing common causes of shoulder pain on radiographs. Skeletal Radiol. 2022;51(2):355-62. doi: 10.1007/s00256-021-03740-9. PubMed PMID: 33611622. PubMed PMCID: PMC8692302.
  9. Guan B, Liu F, Mizaian AH, Demehri S, Samsonov A, Guermazi A, Kijowski R. Deep learning approach to predict pain progression in knee osteoarthritis. Skeletal Radiol. 2022;51(2):363-73. doi: 10.1007/s00256-021-03773-0. PubMed PMID: 33835240. PubMed PMCID: PMC9232386.
  10. Yi PH, Kim TK, Wei J, Li X, Hager GD, Sair HI, Fritz J. Automated detection and classification of shoulder arthroplasty models using deep learning. Skeletal Radiol. 2020;49(10):1623-32. doi: 10.1007/s00256-020-03463-3. PubMed PMID: 32415371.
  11. Zulkifley MA, Mohamed NA, Abdani SR, Kamari NAM, Moubark AM, Ibrahim AA. Intelligent Bone Age Assessment: An Automated System to Detect a Bone Growth Problem Using Convolutional Neural Networks with Attention Mechanism. Diagnostics (Basel). 2021;11(5):765. doi: 10.3390/diagnostics11050765. PubMed PMID: 33923215. PubMed PMCID: PMC8146101.
  12. Halabi SS, Prevedello LM, Kalpathy-Cramer J, Mamonov AB, Bilbily A, Cicero M, et al. The RSNA Pediatric Bone Age Machine Learning Challenge. 2019;290(2):498-503. doi: 10.1148/radiol.2018180736. PubMed PMID: 30480490. PubMed PMCID: PMC6358027.
  13. Oh M, Zhang L. DeepMicro: deep representation learning for disease prediction based on microbiome data. Sci Rep. 2020;10(1):6026. doi: 10.1038/s41598-020-63159-5. PubMed PMID: 32265477. PubMed PMCID: PMC7138789.
  14. Yang Y, Wu QJ, Wang Y. Autoencoder with invertible functions for dimension reduction and image reconstruction. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2016;48(7):1065-79. doi: 10.1109/TSMC.2016.2637279.
  15. Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32 nd International Conference on Machine Learning; Lille, France: JMLR; 2015.
  16. Van Laarhoven T. L2 regularization versus batch and weight normalization [Internet]. arXiv [Preprint]. 2017 [cited 2017 Jun 16]. Available from: https://arxiv.org/abs/1706.05350.
  17. Kingma DP, Ba J. Adam: A method for stochastic optimization [Internet]. arXiv [Preprint]. 2014 [cited 2014 Dec 22]. Available from: https://arxiv.org/abs/1412.6980.
  18. Wibisono A, Saputri MS, Mursanto P, Rachmad J, Yudasubrata AT, Rizki F, Anderson E. Deep learning and classic machine learning approach for automatic bone age assessment. In 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS); Nagoya, Japan: IEEE; 2019. p. 235-40.
  19. Gao Y, Zhu T, Xu X. Bone age assessment based on deep convolution neural network incorporated with segmentation. Int J Comput Assist Radiol Surg. 2020;15(12):1951-62. doi: 10.1007/s11548-020-02266-0. PubMed PMID: 32986142.
  20. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. [Internet]. arXiv [Preprint]. 2014 [cited 2014 Sep 4]. Available from: https://arxiv.org/abs/1409.1556.
  21. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR); Las Vegas, NV, USA: CVPR; 2016. p. 2818-26.
  22. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR); Las Vegas, NV, USA: CVPR; 2016. p. 770-8.
  23. Fran C. Xception: Deep learning with depthwise separable convolutions. In IEEE conference on computer vision and pattern recognition (CVPR); Honolulu, HI, USA: CVPR; 2017.
  24. Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications [Internet]. arXiv [Preprint]. 2017 [cited 2017 Apr 17]. Available from: https://arxiv.org/abs/1704.04861.
  25. He J, Jiang D. Fully automatic model based on se-resnet for bone age assessment. IEEE Access. 2021;9:62460-6. doi: 10.1109/ACCESS.2021.3074713.
  26. Koitka S, Demircioglu A, Kim MS, Friedrich CM, Nensa F. Ossification area localization in pediatric hand radiographs using deep neural networks for object detection. PLoS One. 2018;13(11):e0207496. doi: 10.1371/journal.pone.0207496. PubMed PMID: 30444906. PubMed PMCID: PMC6239319.
  27. Koitka S, Kim MS, Qu M, Fischer A, Friedrich CM, Nensa F. Mimicking the radiologists’ workflow: Estimating pediatric hand bone age with stacked deep neural networks. Med Image Anal. 2020;64:101743. doi: 10.1016/j.media.2020.101743. PubMed PMID: 32540698.
  28. Ren S, He K, Girshick R, Sun J. Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems 28 (NIPS 2015). NeurIPS Proceedings; 2015.
  29. Szegedy C, Ioffe S, Vanhoucke V, Alemi A. Inception-v4, inception-resnet and the impact of residual connections on learning. Thirty-First AAAI Conference on Artificial Intelligence; California USA: AAAI Press; 2017.
  30. Pan X, Zhao Y, Chen H, Wei D, Zhao C, Wei Z. Fully Automated Bone Age Assessment on Large-Scale Hand X-Ray Dataset. Int J Biomed Imaging. 2020;2020:8460493. doi: 10.1155/2020/8460493. PubMed PMID: 32190035. PubMed PMCID: PMC7072110.
  31. Ren X, Li T, Yang X, Wang S, Ahmad S, Xiang L, Stone SR, Li L, Zhan Y, Shen D, Wang Q. Regression Convolutional Neural Network for Automated Pediatric Bone Age Assessment From Hand Radiograph. IEEE J Biomed Health Inform. 2019;23(5):2030-8. doi: 10.1109/JBHI.2018.2876916. PubMed PMID: 30346295.
  32. Salim I, Hamza AB. Ridge regression neural network for pediatric bone age assessment. Multimedia Tools and Applications. 2021;80(20):30461-78. doi: 10.1007/s11042-021-10935-8.
  33. He K, Gkioxari G, Dollár P, Girshick R. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (ICCV); Venice, Italy: ICCV; 2017. p. 2961-9.
  34. Liu B, Zhang Y, Chu M, Bai X, Zhou F. Bone age assessment based on rank-monotonicity enhanced ranking CNN. IEEE Access. 2019;7:120976-83. doi: 10.1109/ACCESS.2019.2937341.
  35. Chen C, Chen Z, Jin X, Li L, Speier W, Arnold CW. Attention-Guided Discriminative Region Localization and Label Distribution Learning for Bone Age Assessment. IEEE J Biomed Health Inform. 2022;26(3):1208-18. doi: 10.1109/JBHI.2021.3095128. PubMed PMID: 34232898.
  36. Zulkifley MA, Abdani SR, Zulkifley NH. Automated bone age assessment with image registration using hand X-ray images. Applied Sciences. 2020;10(20):7233. doi: 10.3390/app10207233.
  37. Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV); Munich, Germany: 2018. p. 801-18.
  38. Hao P, Ye T, Xie X, Wu F, Ding W, Zuo W, Chen W, Wu J, Luo X. Radiographs and texts fusion learning based deep networks for skeletal bone age assessment. Multimedia Tools and Applications. 2021;80:16347-66. doi: 10.1007/s11042-020-08943-1.
  39. Hao G, Li Y. Bone age estimation with x-ray images based on efficientnet pre-training model. Journal of Physics: Conference Series. 2021;1827:012082. doi: 10.1088/1742-6596/1827/1/012082.
Journal of Biomedical Physics and Engineering
Volume 15, Issue 3 - Serial Number 1
71
June 2025
Pages 271-280
Files
Share
How to cite
Statistics