Abstract
Skeletal bone age assessment is a widely used standard procedure in both disease detection and growth prediction for children in endocrinology. Conventional manual assessment methods mainly rely on personal experience in observing X-ray images of left hand and wrist to calculate bone age, which show some intrinsic limitations from low efficiency to unstable accuracy. To address these problems, some automated methods based on image processing or machine learning have been proposed, while their performances are not satisfying enough yet in assessment accuracy. Motivated by the remarkable success of deep learning (DL) techniques in the fields of image classification and speech recognition, we develop a deep automated skeletal bone age assessment model based on convolutional neural networks (CNNs) and support vector regression (SVR) using multiple kernel learning (MKL) algorithm to process heterogeneous features in this paper. This deep framework has been constructed, not only exploring the X-ray images of hand and twist but also some other heterogeneous information like race and gender. The experiment results prove its better performance with higher bone age assessment accuracy on two different data sets compared with the state of the art, indicating that the fused heterogeneous features provide a better description of the degree of bones’ maturation.
Similar content being viewed by others
References
Adeshina, S. A., Lindner, C., and Cootes, T. F.: Automatic segmentation of carpal area bones with random forest regression voting for estimating skeletal maturity in infants. In: 2014 11th international conference on electronics, computer and computation (ICECCO), pp. 1–4. IEEE, 2014
Bach, F. R., Lanckriet, G. R., and Jordan, M. I.: Multiple kernel learning, conic duality, and the smo algorithm. In: Proceedings of the 21t international conference on Machine learning, p. 6, 2004
Beunen, G., Lefevre, J., Ostyn, M., Renson, R., Simons, J., and Van Gerven, D., Skeletal maturity in belgian youths assessed by the tanner-whitehouse method (tw2). Ann. Hum. Biol. 17(5):355–376, 1990.
Chai, H. Y., Wee, L. K., Swee, T. T., and Salleh, S. H., Adaptive crossed reconstructed (acr) k-mean clustering segmentation for computer-aided bone age assessment system. Int. J. Math. Models Methods Appl. Sci. 5 (3):628–635, 2011.
Chen, H., Dou, Q., Wang, X., Qin, J., Heng, P. A., et al.: Mitosis detection in breast cancer histology images via deep cascaded networks. In: AAAI, pp. 1160–1166, 2016
Chollet, F.: Keras (2015). http://keras.io, 2017
Giordano, D., Kavasidis, I., and Spampinato, C., Modeling skeletal bone development with hidden markov models. Comput. Methods Prog. Biomed. 124:138–147, 2016.
Greulich, W. W., and Pyle, S. I., Radiographic atlas of skeletal development of the hand and wrist. Am. J. Med. Sci. 238(3):393, 1959.
Haak, D., Yu, J., Simon, H., Schramm, H., Seidl, T., and Deserno, T. M.: Bone age assessment using support vector regression with smart class mapping. In: SPIE medical imaging, pp. 86,700A–86,700A, 2013
Harmsen, M., Fischer, B., Schramm, H., and Deserno, T. M.: Support vector machine classification using correlation prototypes for bone age assessment. In: Bildverarbeitung für die Medizin 2012, pp. 434–439. Springer, 2012
Hsieh, C. W., Liu, T. C., Jong, T. L., and Tiu, C. M., A fuzzy-based growth model with principle component analysis selection for carpal bone-age assessment. Med. Biol. Eng. Comput. 48(6):579–588, 2010.
Kim, Y., Jernite, Y., Sontag, D., and Rush, A. M.: Character-aware neural language models. In: AAAI, pp. 2741–2749, 2016
Krizhevsky, A., Sutskever, I., and Hinton, G. E.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp. 1097–1105, 2012
Liu, J., Qi, J., Liu, Z., Ning, Q., and Luo, X., Automatic bone age assessment based on intelligent algorithms and comparison with tw3 method. Comput. Med. Imaging Graph. 32(8):678–684, 2008.
Liu, S., Liu, S., Cai, W., Pujol, S., Kikinis, R., and Feng, D.: Early diagnosis of alzheimer’s disease with deep learning. In: 2014 IEEE 11th international symposium on biomedical imaging (ISBI), pp. 1015–1018, 2014
Michael, D. J., and Nelson, A. C., Handx: a model-based system for automatic segmentation of bones from digital hand radiographs. IEEE Trans. Med. Imaging 8(1):64–69, 1989.
Pietka, E., Gertych, A., Pospiech, S., Cao, F., Huang, H., and Gilsanz, V., Computer-assisted bone age assessment: Image preprocessing and epiphyseal/metaphyseal roi extraction. IEEE Trans. Med. Imaging 20(8): 715–729, 2001.
Qidi, W., Yibing, L., Yun, L., and Xiaodong, Y., The nonlocal sparse reconstruction algorithm by similarity measurement with shearlet feature vector. Math. Probl. Eng. 2014:1–8, 2014.
Rakotomamonjy, A., Bach, F. R., Canu, S., and Grandvalet, Y., Simplemkl. J. Mach. Learn. Res. 9:2491–2521, 2008.
Seeman, E., Growth in bone mass and sizeare racial and gender differences in bone mineral density more apparent than real? J. Clin. Endocrinol. Metabol. 83(5):1414–1419, 1998.
Seok, J., Kasa-Vubu, J., DiPietro, M., and Girard, A., Expert system for automated bone age determination. Expert Syst. Appl. 50:75–88, 2016.
Simonyan, K., and Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556, 2014
Somkantha, K., Theera-Umpon, N., and Auephanwiriyakul, S., Bone age assessment in young children using automatic carpal bone feature extraction and support vector regression. J. Digit. Imaging 24(6):1044–1058, 2011.
Spampinato, C., Palazzo, S., Giordano, D., Aldinucci, M., and Leonardi, R., Deep learning for automated skeletal bone age assessment in x-ray images. Med. Image Anal. 36:41–51, 2017.
Thodberg, H. H., Kreiborg, S., Juul, A., and Pedersen, K. D., The bonexpert method for automated determination of skeletal maturity. IEEE Trans. Med. Imaging 28(1):52–66, 2009.
Tu, Y., Lin, Y., Wang, J., and Kim, J.U.: Semi-supervised learning with generative adversarial networks on digital signal modulation classification, 2018
Wu, Q., Li, Y., and Lin, Y., The application of nonlocal total variation in image denoising for mobile transmission. Multimed. Tools Appl. 76(16):17,179–17,191, 2017.
Acknowledgements
This work was supported by the National Natural Science Foundation of China (61472024, U1433203), Project of National Engineering Laboratory for Internet Medical System and Application (NELIMSA2018P01).
Author information
Authors and Affiliations
Corresponding author
Additional information
This article is part of the Topical Collection on Image & Signal Processing
Rights and permissions
About this article
Cite this article
Tong, C., Liang, B., Li, J. et al. A Deep Automated Skeletal Bone Age Assessment Model with Heterogeneous Features Learning. J Med Syst 42, 249 (2018). https://doi.org/10.1007/s10916-018-1091-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10916-018-1091-6