Skip to main content
SpringerLink
Log in

End-to-end multi-domain neural networks with explicit dropout for automated bone age assessment

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Pediatric skeletal bone age assessment (BAA) is a common clinical practice to diagnose endocrine and metabolic disorders in child development. Recently, several automated methods have been developed to assist the diagnosis. For most children, the chronological age will be close to the bone age. Besides, features of the left hand between males and females are different by using either Greulich and Pyle (G&P) method or Tanner Whitehouse (TW) method. However, it is truly challenging to learn a unified representation based on the male and female image samples that have completely different characteristics. We argue that chronological age and gender are necessary pieces of information for automated BAA, and delve into the auxiliary of chronological age and gender for BAA. In this paper, a new multi-domain neural network (MD-BAA) is proposed to assess bone age of males and females in a separative and end-to-end manner. Furthermore, we introduce two regularization approaches to improve the network training: 1) an explicit dropout approach to select either the male domain or the female domain; 2) a chronological age preserving loss function to prevent the predicted bone age discrepant too much from the chronological age. Experimental results show the proposed method outperforms the state-of-the-art models on two datasets.

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

References

  1. Latronico AC, Brito VN, Carel J-C (2016) Causes, diagnosis, and treatment of central precocious puberty. Lancet Diabetes Endocrinol 4(3):265–274

    Article  Google Scholar 

  2. Berberoğlu M (2009) Precocious puberty and normal variant puberty: definition, etiology, diagnosis and current management. J Clin Res Pediatr Endocrinol 1(4):164

    Article  Google Scholar 

  3. Speiser PW, White PC (2003) Congenital adrenal hyperplasia. N Engl J Med 349(8):776–788

    Article  Google Scholar 

  4. Sybert VP, McCauley E (2004) Turner’s syndrome. N Engl J Med 351(12):1227–1238

    Article  Google Scholar 

  5. Liu A, McEntee J (2019) Osteochondrodysplasia. Pediatr Rev 40(8):435–438

    Article  Google Scholar 

  6. Schmeling A, Olze A, Reisinger W (2001) Age estimation of living people undergoing criminal proceedings. Lancet 358(9276):89–90

    Article  Google Scholar 

  7. Bayer L.M. (1959) Radiographic atlas of skeletal development of the hand and wrist. California medicine 91(1):53

    Google Scholar 

  8. Sherar LB, Mirwald RL, Baxter-Jones AD, Thomis M (2005) Prediction of adult height using maturity-based cumulative height velocity curves. J Pediatr 147(4):508–514

    Article  Google Scholar 

  9. Son SJ, Song Y, Kim N, Do Y, Kwak N, Lee MS, Lee B-D (2019) Tw3-based fully automated bone age assessment system using deep neural networks. IEEE Access 7:33346–33358

    Article  Google Scholar 

  10. Chougrad H, Zouaki H, Alheyane O (2020) Multi-label transfer learning for the early diagnosis of breast cancer. Neurocomputing 392:168–180

    Article  Google Scholar 

  11. Gálvez A, Iglesias A (2020) Memetic improved cuckoo search algorithm for automatic b-spline border approximation of cutaneous melanoma from macroscopic medical images. Adv Eng Inform 43:101005

    Article  Google Scholar 

  12. Bi X, Li S, Xiao B, Li Y, Wang G, Ma X (2020) Computer aided alzheimer’s disease diagnosis by an unsupervised deep learning technology. Neurocomputing 392:296–304

    Article  Google Scholar 

  13. Pietka E, Gertych A, Pospiech S, Cao F, Huang H, Gilsanz V (2001) Computer-assisted bone age assessment: image preprocessing and epiphyseal/metaphyseal roi extraction. IEEE Trans Med Imaging 20(8):715–729

    Article  Google Scholar 

  14. Zhang A, Gertych A, Liu BJ (2007) Automatic bone age assessment for young children from newborn to 7-year-old using carpal bones. Comput Med Imaging Graph 31(4-5):299–310

    Article  Google Scholar 

  15. Gertych A, Zhang A, Sayre J, Pospiech-Kurkowska S, Huang H (2007) Bone age assessment of children using a digital hand atlas. Comput Med Imaging Graph 31(4-5):322–331

    Article  Google Scholar 

  16. Giordano D, Spampinato C, Scarciofalo G, Leonardi R (2010) An automatic system for skeletal bone age measurement by robust processing of carpal and epiphysial/metaphysial bones. IEEE Trans Instrum Meas 59(10):2539–2553

    Article  Google Scholar 

  17. Mansourvar M, Shamshirband S, Raj RG, Gunalan R, Mazinani I (2015) An automated system for skeletal maturity assessment by extreme learning machines. PLos One 10(9)

  18. Kashif M, Deserno TM, Haak D, Jonas S (2016) Feature description with sift, surf, brief, brisk, or freak? a general question answered for bone age assessment. Comput Biol Med 68:67–75

    Article  Google Scholar 

  19. Chen M (2016) Automated bone age classification with deep neural networks. Stanford University, USA Technical Report

  20. Spampinato C, Palazzo S, Giordano D, Aldinucci M, Leonardi R (2017) Deep learning for automated skeletal bone age assessment in x-ray images. Medical image analysis 36:41–51

    Article  Google Scholar 

  21. Lee H, Tajmir S, Lee J, Zissen M, Yeshiwas BA, Alkasab TK, Choy G, Do S (2017) Fully automated deep learning system for bone age assessment. J Digit Imaging 30(4):427–441

    Article  Google Scholar 

  22. Iglovikov VI, Rakhlin A, Kalinin AA, Shvets AA (2018) Paediatric bone age assessment using deep convolutional neural networks. In: Deep learning in medical image analysis and multimodal learning for clinical decision support. springer, pp 300–308, Cham

  23. Liang B, Zhai Y, Tong C, Zhao J, Li J, He X, Ma Q (2019) A deep automated skeletal bone age assessment model via region-based convolutional neural network. Futur Gener Comp Syst 98:54–59

    Article  Google Scholar 

  24. Nam H, Han B (2016) Learning multi-domain convolutional neural networks for visual tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4293–4302

  25. Halabi SS, Prevedello LM, Kalpathy-Cramer J, Mamonov AB, Bilbily A, Cicero M, Pan I, Pereira LA, Sousa RT, Abdala N et al (2019) The rsna pediatric bone age machine learning challenge. Radiology 290(2):498–503

    Article  Google Scholar 

  26. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, Van Der Laak JA, Van Ginneken B, Sancheź CI (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88

    Article  Google Scholar 

  27. Štern D, Payer C, Urschler M (2019) Automated age estimation from mri volumes of the hand. Med Image Anal 58:101538

    Article  Google Scholar 

  28. Koitka S, Kim MS, Qu M, Fischer A, Friedrich CM, Nensa F (2020) Mimicking the radiologists’ workflow: Estimating pediatric hand bone age with stacked deep neural networks. Med Image Anal 64:101743

    Article  Google Scholar 

  29. Sharif Razavian A, Azizpour H, Sullivan J, Carlsson S (2014) Cnn features off-the-shelf: an astounding baseline for recognition. In: Proceedings IEEE conference on computer vision and pattern recognition Workshops, pp 806–813

  30. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: 3Rd international conference on learning representations, ICLR 2015, San Diego, CA, USA. 7-9 May 2015, Conference Track Proceedings, pp 1–14

  31. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings IEEE conference on computer vision and pattern recognition, pp 1–9

  32. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings IEEE conference on computer vision and pattern recognition , pp 770–778

  33. Jaderberg M, Simonyan K, Zisserman A (2015) Spatial transformer networks. In: Proceedings advances in neural information processing systems, pp 2017–2025

  34. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252

    Article  Google Scholar 

  35. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958

    MATH  Google Scholar 

  36. Giordano D, Kavasidis I, Spampinato C (2016) Modeling skeletal bone development with hidden markov models. Comput Meth Programs Biomed 124:138–147

    Article  Google Scholar 

  37. Seok J, Kasa-Vubu J, DiPietro M, Girard A (2016) Expert system for automated bone age determination. Expert Syst Appl 50:75–88

    Article  Google Scholar 

  38. Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT’2010. Springer, pp 177–186, Cham

  39. He J, Jiang D (2021) Fully automatic model based on se-resnet for bone age assessment. IEEE Access 9:62460–62466

    Article  Google Scholar 

  40. Li S, Liu B, Li S, Zhu X, Yan Y, Zhang D (2021) A deep learning-based computer-aided diagnosis method of x-ray images for bone age assessment. Complex Intell Syst, pp 1–11

Download references

Acknowledgements

This research was supported by the National Natural Science Foundation of China Grant 61902139 and 81070691.

Author information

Authors and Affiliations

  1. School of Software Engineering, Huazhong University of Science and Technology, No. 1037 Luoyu Road, Wuhan, 430074, Hubei, China

    He Tang, Xiaobing Pei & Xinzhe Li

  2. Department of Pediatrics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, No. 1277 Jie Fang Avenue, Wuhan, 430022, Hubei, China

    Haihui Tong & Xin Li

  3. Department of Orthopedics, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, No. 1095 Jie Fang Avenue, Wuhan, 430030, Hubei, China

    Shilong Huang

Authors
  1. He Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaobing Pei
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xinzhe Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Haihui Tong
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xin Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Shilong Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shilong Huang.

Additional information

Publisher’s note

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

He Tang and Xiaobing Pei contributed equally to this work.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tang, H., Pei, X., Li, X. et al. End-to-end multi-domain neural networks with explicit dropout for automated bone age assessment. Appl Intell 53, 3736–3749 (2023). https://doi.org/10.1007/s10489-022-03725-8

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03725-8

Keywords

Search

Navigation