Abstract
Bone age assessment helps to detect and schedule treatment for several disorders. Estimating bone age differs from determining physical maturity based on the individual's date of birth. Assessing bone age determines development and progress, identifying and treating juvenile illnesses. Challenges in bone age assessment notably arise from poor-quality X-images, obscured bone structures, and the complexity of feature extraction due to degraded image quality, significantly impacting model performance. The proposed methodology involves utilizing pre-trained neural networks—InceptionV3, DenseNet201, XceptionNet, and MobileNetV2—finetuned by adding dense layers alongside dropout and kernel initializers adjustments. The hyperparameters for each pre-trained model are rigorously defined, and the performance evaluation encompasses a spectrum of optimizers such as Adam, Nadam, Adamax, RMSprop, and SGD. Notably, the implementation of the Adamax optimizer yields superior results, demonstrating exceptional accuracy in bone age assessment on the RSNA dataset, particularly with DenseNet201, InceptionV3, and XceptionNet models. This research presents a comprehensive comparative analysis showcasing the enhanced accuracy of bone age estimation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Mughal, A.M., Hassan, N., Ahmed, A.: Bone age assessment methods: a critical review. Pak. J. Med. Sci. 30, 211 (1969). https://doi.org/10.12669/pjms.301.4295
Liang, B., et al.: A deep automated skeletal bone age assessment model via region-based convolutional neural network. Futur. Gener. Comput. Syst. 98, 54–59 (2019). https://doi.org/10.1016/j.future.2019.01.057
Alshamrani, K., Messina, F., Offiah, A.C.: Is the Greulich and Pyle atlas applicable to all ethnicities? A systematic review and meta-analysis. Eur. Radiol. 29, 2910–2923 (2019). https://doi.org/10.1007/s00330-018-5792-5
Ostojic, S.M.: Prediction of adult height by Tanner-Whitehouse method in young Caucasian male athletes. QJM 106, 341–345 (2013). https://doi.org/10.1093/qjmed/hcs230
Satoh, M.: Bone age: assessment methods and clinical applications. Clin. Pediatr. Endocrinol. 24, 143–152 (2015). https://doi.org/10.1297/cpe.24.143
Lee, H., et al.: Fully automated deep learning system for bone age assessment. J. Digit. Imaging 30, 427–441 (2017). https://doi.org/10.1007/s10278-017-9955-8
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826. IEEE, Las Vegas, NV, USA (2016). https://doi.org/10.1109/CVPR.2016.308
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1800–1807. IEEE, Honolulu, HI (2017). https://doi.org/10.1109/CVPR.2017.195
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269. IEEE, Honolulu, HI (2017). https://doi.org/10.1109/CVPR.2017.243
Howard, A., et al. : MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (2017)
Bashetty, S., Raja, K., Adepu, S., Jain, A.: Optimizers in deep learning: a comparative study and analysis. IJRASET 10, 1032–1039 (2022). https://doi.org/10.22214/ijraset.2022.48050
Kingma, D.P., Ba, J.: Adam: A Method for Stochastic Optimization (2017). http://arxiv.org/abs/1412.6980
Kandel, I., Castelli, M., Popovič, A.: Comparative study of first order optimizers for image classification using convolutional neural networks on histopathology images. J. Imaging 6, 92 (2020). https://doi.org/10.3390/jimaging6090092
Maggio, A., Flavel, A., Hart, R., Franklin, D.: Assessment of the accuracy of the Greulich and Pyle hand-wrist atlas for age estimation in a contemporary Australian population. Aust. J. Forensic Sci. 50, 385–395 (2018). https://doi.org/10.1080/00450618.2016.1251970
Adler, B.H.: Vicente Gilsanz, Osman Ratib: bone age atlas. Pediatr. Radiol. 35, 1035 (2005). https://doi.org/10.1007/s00247-005-1527-2
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. 36, 41–51 (2017). https://doi.org/10.1016/j.media.2016.10.010
Liu, Y., Zhang, C., Cheng, J., Chen, X., Wang, Z.J.: A multi-scale data fusion framework for bone age assessment with convolutional neural networks. Comput. Biol. Med. 108, 161–173 (2019). https://doi.org/10.1016/j.compbiomed.2019.03.015
Bui, T.D., Lee, J.-J., Shin, J.: Incorporated region detection and classification using deep convolutional networks for bone age assessment. Artif. Intell. Med. 97, 1–8 (2019). https://doi.org/10.1016/j.artmed.2019.04.005
Hao, P., et al.: Radiographs and texts fusion learning based deep networks for skeletal bone age assessment. Multimed. Tools Appl. 80, 16347–16366 (2021). https://doi.org/10.1007/s11042-020-08943-1
Lee, J.H., Kim, Y.J., Kim, K.G.: Bone age estimation using deep learning and hand X-ray images. Biomed. Eng. Lett. 10, 323–331 (2020). https://doi.org/10.1007/s13534-020-00151-y
Gao, Y., Zhu, T., Xu, X.: Bone age assessment based on deep convolution neural network incorporated with segmentation. Int. J. CARS 15, 1951–1962 (2020). https://doi.org/10.1007/s11548-020-02266-0
Wibisono, A., Mursanto, P.: Multi region-based feature connected layer (RB-FCL) of deep learning models for bone age assessment. J. Big Data 7, 67 (2020). https://doi.org/10.1186/s40537-020-00347-0
Li, S., Liu, B., Li, S., Zhu, X., Yan, Y., Zhang, D.: A deep learning-based computer-aided diagnosis method of X-ray images for bone age assessment. Complex Intell. Syst. 8, 1929–1939 (2022). https://doi.org/10.1007/s40747-021-00376-z
Xu, X., Xu, H., Li, Z.: Automated bone age assessment: a new three-stage assessment method from coarse to fine. Healthcare 10, 2170 (2022). https://doi.org/10.3390/healthcare10112170
Halabi, S.S., et al.: The RSNA pediatric bone age machine learning challenge. Radiology 290, 498–503 (2019). https://doi.org/10.1148/radiol.2018180736
Chen, C., Chen, Z., Jin, X., Li, L., Speier, W., Arnold, C.W.: Attention-guided discriminative region localization and label distribution learning for bone age assessment. IEEE J. Biomed. Health Inform. 26, 1208–1218 (2022). https://doi.org/10.1109/JBHI.2021.3095128
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nivedita, Solanki, S. (2025). Enhancing the Accuracy of Automatic Bone Age Estimation Using Optimized CNN Model on X-Ray Images. In: Khurana, M., Thakur, A., Kantha, P., Shieh, CS., Shukla, R.K. (eds) Machine Learning Algorithms. ICMLA 2024. Communications in Computer and Information Science, vol 2238. Springer, Cham. https://doi.org/10.1007/978-3-031-75861-4_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-75861-4_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-75860-7
Online ISBN: 978-3-031-75861-4
eBook Packages: Computer ScienceComputer Science (R0)