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.
Similar content being viewed by others
References
Latronico AC, Brito VN, Carel J-C (2016) Causes, diagnosis, and treatment of central precocious puberty. Lancet Diabetes Endocrinol 4(3):265–274
Berberoğlu M (2009) Precocious puberty and normal variant puberty: definition, etiology, diagnosis and current management. J Clin Res Pediatr Endocrinol 1(4):164
Speiser PW, White PC (2003) Congenital adrenal hyperplasia. N Engl J Med 349(8):776–788
Sybert VP, McCauley E (2004) Turner’s syndrome. N Engl J Med 351(12):1227–1238
Liu A, McEntee J (2019) Osteochondrodysplasia. Pediatr Rev 40(8):435–438
Schmeling A, Olze A, Reisinger W (2001) Age estimation of living people undergoing criminal proceedings. Lancet 358(9276):89–90
Bayer L.M. (1959) Radiographic atlas of skeletal development of the hand and wrist. California medicine 91(1):53
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
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
Chougrad H, Zouaki H, Alheyane O (2020) Multi-label transfer learning for the early diagnosis of breast cancer. Neurocomputing 392:168–180
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
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
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
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
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
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
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)
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
Chen M (2016) Automated bone age classification with deep neural networks. Stanford University, USA Technical Report
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
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
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
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
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
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
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
Štern D, Payer C, Urschler M (2019) Automated age estimation from mri volumes of the hand. Med Image Anal 58:101538
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
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
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
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
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
Jaderberg M, Simonyan K, Zisserman A (2015) Spatial transformer networks. In: Proceedings advances in neural information processing systems, pp 2017–2025
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
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
Giordano D, Kavasidis I, Spampinato C (2016) Modeling skeletal bone development with hidden markov models. Comput Meth Programs Biomed 124:138–147
Seok J, Kasa-Vubu J, DiPietro M, Girard A (2016) Expert system for automated bone age determination. Expert Syst Appl 50:75–88
Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT’2010. Springer, pp 177–186, Cham
He J, Jiang D (2021) Fully automatic model based on se-resnet for bone age assessment. IEEE Access 9:62460–62466
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
Acknowledgements
This research was supported by the National Natural Science Foundation of China Grant 61902139 and 81070691.
Author information
Authors and Affiliations
Corresponding author
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
About this article
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
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03725-8