Deep Learning-Based Pediatric Bone Age Estimation Using Hand Radiography

Document Type : Original Article(s)

Authors

1 MSc Student of Medical Physics, Department of Medical Physics, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran

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

3 Professor, Department of Medical Physics, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran

Abstract

Background: Hand radiographs are commonly used to evaluate bone maturity. So that the significant difference between the estimated bone age and the chronological age can indicate a developmental disorder. However, the manual evaluation of images is usually a time-consuming and observer-dependent process. Therefore, in this paper, an automatic method for the assessment of bone age using radiographs of children's hands is proposed.
Methods: In this fundamental-applied research, the collection of radiographic images of the Radiological Society of North America (RSNA) was used, and transfer learning methods were proposed. The input images were first pre-processed due to low quality. Then a pre-trained model based on DenseNet-121 was used to extract the discriminating spatial features.
Findings: Evaluations using five pre-trained models on the RSNA dataset showed that the DenseNet-121 model, after adjustment, could perform better than other models, with a mean absolute error of 9.8 months.
Conclusion: Skeletal maturity can be estimated with satisfactory accuracy using the DenseNet-121 model, and this method can help radiologists in quick and accurate measurement of bone age.

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.
  2. Greulich WW, Pyle SI. Radiographic atlas of skeletal development of the hand and wrist. 1st California, UD: Stanford University Press; 1999.
  3. Poznanski AK. Assessment of skeletal maturity and prediction of adult height. Am J Dis Child 1977; 131(9): 1041-2.
  4. Harmsen M, Fischer B, Schramm H, Seidl T, Deserno TM. Support vector machine classification based on correlation prototypes applied to bone age assessment. IEEE Journal of Biomedical and Health Informatics 2012; 17(1): 190-7.
  5. Fischer B, Welter P, Grouls C, Günther RW, Deserno TM. Bone age assessment by content-based image retrieval and case-based reasoning. Int J Comput Assist Radiol Surg 2012; 7(3): 389-99.
  6. Fritz B, Marbach G, Civardi F, Fucentese SF, Pfirrmann CW. 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.
  7. He J, Jiang D. Fully automatic model based on se-resnet for bone age assessment. IEEE Access. 2021; 9: 62460-6.
  8. 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.
  9. Wibisono A, Saputri MS, Mursanto P, Rachmad J, Yudasubrata ATW, Rizki F, et al. Deep learning and classic machine learning approach for automatic bone age assessment. Proceedings of the 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS); 2019: IEEE; Nagoya, Japan.
  10. 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.
  11. Halabi SS, Prevedello LM, Kalpathy-Cramer J, Mamonov AB, Bilbily A, Cicero M, et al. The RSNA pediatric bone age machine learning challenge. Radiology 2019; 290(2): 498-503.
  12. Tsiakmaki M, Kostopoulos G, Kotsiantis S, Ragos O. Transfer learning from deep neural networks for predicting student performance. Appl Sci 2020; 10(6): 2145.
  13. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. Imagenet: A large-scale hierarchical image database. Proceedings of the IEEE conference on computer vision and pattern recognition; 2009 Jun 20-25; Miami, FL, USA.
  14. Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition; 2017. Available from: URL: https://arxiv.org/abs/1608.06993v5
  15. van Laarhoven T. L2 regularization versus batch and weight normalization. 2017. Available from: URL: https://arxiv.org/abs/1706.05350
  16. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. 2016. Available from: URL:
    https://arxiv.org/abs/1512.03385
  17. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014. Available from: URL:

https://arxiv.org/abs/1409.1556

  1. Chollet F. Deep learning with depthwise separable convolutions. 2017. Available from: URL: https://arxiv.org/abs/1610.02357
  2. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
    2016 Jun 27-30; Las Vegas, NV, USA; 2016.
  3. Ronneberger O, Fischer P, Brox T, Olaf R. U-net: Convolutional networks for biomedical image In: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Navab N, Hornegger J, Wells WM, Frangi AF, Editors. New York, NY: Springer International Publishing; 2015.
  4. Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. 2017. Available from: URL: https://arxiv.org/abs/1704.04861
Journal of Isfahan Medical School
Volume 40, Issue 700
4th Week, February
January and February 2023
Pages 1037-1043

Files

History

  • Receive Date: 18 September 1401
  • Accept Date: 18 October 1401

Share

How to cite

Statistics