Document Type : Original/Review Paper

Authors

Department of Computer Engineering and Information Technology, Razi University, Kermanshah, Iran.

10.22044/jadm.2022.11752.2323

Abstract

Bone age assessment is a method that is constantly used for investigating growth abnormalities, endocrine gland treatment, and pediatric syndromes. Since the advent of digital imaging, for several decades the bone age assessment has been performed by visually examining the ossification of the left hand, usually using the G&P reference method. However, the subjective nature of hand-craft methods, the large number of ossification centers in the hand, and the huge changes in ossification stages lead to some difficulties in the evaluation of the bone age. Therefore, many efforts were made to develop image processing methods. These methods automatically extract the main features of the bone formation stages to effectively and more accurately assess the bone age. In this paper, a new fully automatic method is proposed to reduce the errors of subjective methods and improve the automatic methods of age estimation. This model was applied to 1400 radiographs of healthy children from 0 to 18 years of age and gathered from 4 continents. This method starts with the extraction of all regions of the hand, the five fingers and the wrist, and independently calculates the age of each region through examination of the joints and growth regions associated with these regions by CNN networks; It ends with the final age assessment through an ensemble of CNNs. The results indicated that the proposed method has an average assessment accuracy of 81% and has a better performance in comparison to the commercial system that is currently in use.

Keywords

[1] S. A. Abdelaziz Ismael, A. Mohammed, and H. Hefny, "An enhanced deep learning approach for brain cancer MRI images classification using residual networks," Artificial intelligence in medicine, vol. 102, pp. 101779-101779, 2019. [Online]. Available: https://neuro.unboundmedicine.com/medline/citation/31980109/An_enhanced_deep_learning_approach_for_brain_cancer_MRI_images_classification_using_residual_networks_
 
[2] J. H. Lee, Y. J. Kim, and K. G. Kim, "Bone age estimation using deep learning and hand X-ray images," Biomedical engineering letters, vol. 10, no. 3, pp. 323-331doi: 10.1007/s13534-020-00151-y.
 
[3] R. Lindsey et al., "Deep neural network improves fracture detection by clinicians," Proceedings of the National Academy of Sciences, vol. 115, no. 45, pp. 11591-11596, 2018, doi: doi:10.1073/pnas.1806905115.
 
 
[4] B. Guan, J. Yao, G. Zhang, and X. Wang, "Thigh fracture detection using deep learning method based on new dilated convolutional feature pyramid network," Pattern Recogn. Lett., vol. 125, no. C, pp. 521–526, 2019, doi: 10.1016/j.patrec.2019.06.015.
 
[5] V. Gilsanz and O. Ratib, Hand bone age: a digital atlas of skeletal maturity. Springer, 2005.
 
[6] H. Crawley, When is a child not a child?: Asylum, age disputes and the process of age assessment. Immigration Law Practitioners' Association (ILPA), 2007.
 
[7] A. Mateen, H. K. AFRIDI, and A. R. MALIK, "Age estimation from medial end of clavicle by X-ray examination," Pak J Med Health Sci, vol. 7, no. 4, pp. 1106-1108, 2010.
 
[8] M. K. Crocker et al., "Sexual dimorphisms in the associations of BMI and body fat with indices of pubertal development in girls and boys," (in eng), J Clin Endocrinol Metab, vol. 99, no. 8, pp. E1519-29, Aug 2014, doi: 10.1210/jc.2014-1384.
 
[9] J. Tanner, R. Whitehouse, W. Marshall, and B. Carter, "Prediction of adult height from height, bone age, and occurrence of menarche, at ages 4 to 16 with allowance for midparent height," Archives of disease in childhood, vol. 50, no. 1, pp. 14-26, 1975.
 
[10] J. M. Tanner, "Assessement of Skeletal Maturity and Predicting of Adult Height(TW2 Method)," Prediction of adult height, pp. 22-37, 1983 1983. [Online]. Available: https://cir.nii.ac.jp/crid/1573387449513088640.
 
[11] H. M. L. Carty, "Assessment of skeletal maturity and prediction of adult height (TW3 method).: 3rd edition. Edited by J. M. Tanner, M. J. R. Healy, H. Goldstein and N. Cameron. Pp 110. London, etc: W. B. Saunders, 2001. ISBN: 0-7020-2511-9. £69.95," Journal of Bone and Joint Surgery-british Volume, pp. 310-311, 2002.
 
[12] Z. Zivkovic, "Improved adaptive Gaussian mixture model for background subtraction," in Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., 26-26 Aug. 2004 2004, vol. 2, pp. 28-31 Vol.2, doi: 10.1109/ICPR.2004.1333992.
 
[13] J. Kennedy and R. Eberhart, "Particle swarm optimization," in Proceedings of ICNN'95 - International Conference on Neural Networks, 27 Nov.-1 Dec. 1995 1995, vol. 4, pp. 1942-1948 vol.4, doi: 10.1109/ICNN.1995.488968.
 
[14] M. Sepahvand and F. Abdali-Mohammadi, "A Meta-heuristic Model for Human Micro Movements Recognition Based on Inertial Sensors," TABRIZ JOURNAL OF ELECTRICAL ENGINEERING, vol. 49, no. 1, pp. 221-234, 2019.
 
[15] M. K. Mandal, T. Aboulnasr, and S. Panchanathan, "Fast wavelet histogram techniques for image indexing," Computer Vision and Image Understanding, vol. 75, no. 1-2, pp. 99-110, 1999.
 
[16] J. Seetha and S. S. Raja, "Brain tumor classification using convolutional neural networks," Biomedical & Pharmacology Journal, vol. 11, no. 3, p. 1457, 2018.
 
[17] M. Sepahvand and F. Abdali-Mohammadi, "Overcoming limitation of dissociation between MD and MI classifications of breast cancer histopathological images through a novel decomposed feature-based knowledge distillation method," Computers in Biology and Medicine, vol. 145, p. 105413, 2022/06/01/ 2022, doi: https://doi.org/10.1016/j.compbiomed.2022.105413.
 
[18] S. Hussein, K. Cao, Q. Song, and U. Bagci, "Risk stratification of lung nodules using 3D CNN-based multi-task learning," in International conference on information processing in medical imaging, 2017: Springer, pp. 249-260.
 
[19] M. Mansourvar, M. A. Ismail, T. Herawan, R. Gopal Raj, S. Abdul Kareem, and F. H. Nasaruddin, "Automated Bone Age Assessment: Motivation, Taxonomies, and Challenges," Computational and Mathematical Methods in Medicine, vol. 2013, p. 391626, 2013/12/16 2013, doi: 10.1155/2013/391626.
 
[20] G. W. Gross, J. M. Boone, and D. M. Bishop, "Pediatric skeletal age: determination with neural networks," Radiology, vol. 195, no. 3, pp. 689-695, 1995.
 
[21] E. Pietka, M. F. McNitt-Gray, M. L. Kuo, and H. K. Huang, "Computer-assisted phalangeal analysis in skeletal age assessment," IEEE Transactions on Medical Imaging, vol. 10, no. 4, pp. 616-620, 1991, doi: 10.1109/42.108597.
 
[22] H. H. Thodberg, S. Kreiborg, A. Juul, and K. D. Pedersen, "The BoneXpert Method for Automated Determination of Skeletal Maturity," IEEE Transactions on Medical Imaging, vol. 28, no. 1, pp. 52-66, 2009, doi: 10.1109/TMI.2008.926067.
 
[23] A. Tristán-Vega and J. I. Arribas, "A Radius and Ulna TW3 Bone Age Assessment System," IEEE Transactions on Biomedical Engineering, vol. 55, no. 5, pp. 1463-1476, 2008, doi: 10.1109/TBME.2008.918554.
 
[24] M. Niemeijer, B. van Ginneken, C. Maas, F. Beek, and M. Viergever, Assessing the skeletal age from a hand radiograph: automating the Tanner-Whitehouse method (Medical Imaging 2003). SPIE, 2003.
 
[25] J. Liu, J. Qi, Z. Liu, Q. Ning, and X. Luo, "Automatic bone age assessment based on intelligent algorithms and comparison with TW3 method," Computerized Medical Imaging and Graphics, vol. 32, no. 8, pp. 678-684, 2008/12/01/ 2008, doi: https://doi.org/10.1016/j.compmedimag.2008.08.005.
 
[26] M. Mansourvar et al., "Automated web based system for bone age assessment using histogram technique," Malaysian Journal of Computer Science, vol. 25, no. 3, pp. 107-121, 2012.
 
[27] H. Lee et al., "Fully Automated Deep Learning System for Bone Age Assessment," Journal of Digital Imaging, vol. 30, no. 4, pp. 427-441, 2017/08/01 2017, doi: 10.1007/s10278-017-9955-8.
 
[28] C. Spampinato, S. Palazzo, D. Giordano, M. Aldinucci, and R. Leonardi, "Deep learning for automated skeletal bone age assessment in X-ray images," Medical Image Analysis, vol. 36, pp. 41-51, 2017/02/01/ 2017, doi: https://doi.org/10.1016/j.media.2016.10.010.
 
[29] S. J. Son et al., "TW3-Based Fully Automated Bone Age Assessment System Using Deep Neural Networks," IEEE Access, vol. 7, pp. 33346-33358, 2019, doi: 10.1109/ACCESS.2019.2903131.
 
[30] D. Giordano, I. Kavasidis, and C. Spampinato, "Modeling skeletal bone development with hidden Markov models," Computer Methods and Programs in Biomedicine, vol. 124, pp. 138-147, 2016/02/01/ 2016, doi: https://doi.org/10.1016/j.cmpb.2015.10.012.
 
[31] X. Chen, J. Li, Y. Zhang, Y. Lu, and S. Liu, "Automatic feature extraction in X-ray image based on deep learning approach for determination of bone age," Future Generation Computer Systems, vol. 110, pp. 795-801, 2020/09/01/ 2020, doi: https://doi.org/10.1016/j.future.2019.10.032.
 
[32] F. A. Senel, A. Dursun, K. Ozturk, and V. A. Ayyildiz, "Determination of bone age using deep convolutional neural networks," 2021.
 
[33] L. Rabiner and B. Juang, "An introduction to hidden Markov models," ieee assp magazine, vol. 3, no. 1, pp. 4-16, 1986.
[34] M. Sepahvand and F. Abdali-Mohammadi, "A novel method for reducing arrhythmia classification from 12-lead ECG signals to single-lead ECG with minimal loss of accuracy through teacher-student knowledge distillation," Information Sciences, vol. 593, pp. 64-77, 2022/05/01/ 2022, doi: https://doi.org/10.1016/j.ins.2022.01.030.
 
[35] M. Sepahvand, F. Abdali-Mohammadi, and A. Taherkordi, "Teacher–student knowledge distillation based on decomposed deep feature representation for intelligent mobile applications," Expert Systems with Applications, vol. 202, p. 117474, 2022/09/15/ 2022, doi: https://doi.org/10.1016/j.eswa.2022.117474.
 
[36] M. Sepahvand and F. Abdali-Mohammadi, "A novel representation in genetic programming for ensemble classification of human motions based on inertial signals," Expert Systems with Applications, vol. 185, p. 115624, 2021/12/15/ 2021, doi: https://doi.org/10.1016/j.eswa.2021.115624.
 
[37] M. Sepahvand and F. Abdali-Mohammadi, "A novel multi-lead ECG personal recognition based on signals functional and structural dependencies using time-frequency representation and evolutionary morphological CNN," Biomedical Signal Processing and Control, vol. 68, p. 102766, 2021/07/01/ 2021, doi: https://doi.org/10.1016/j.bspc.2021.102766.
 
[38] F. Cao et al., An image database for digital hand atlas. 2003, pp. 461-470.
 
[39] M. Sepahvand and F. Abdali-Mohammadi, "A New Learning-based Spatiotemporal Descriptor for Online Symbol Recognition," Journal of AI and Data Mining, vol. 10, no. 1, pp. 75-86, 2022.
 
[40] M. Sepahvand and F. Abdali-Mohammadi, "A Deep Learning-Based Compression Algorithm for 9-DOF Inertial Measurement Unit Signals Along With an Error Compensating Mechanism," IEEE Sensors Journal, vol. 19, no. 2, pp. 632-640, 2019, doi: 10.1109/JSEN.2018.2877360.
 
[41] M. Sepahvand, F. Abdali-Mohammadi, and F. Mardukhi, "Evolutionary Metric-Learning-Based Recognition Algorithm for Online Isolated Persian/Arabic Characters, Reconstructed Using Inertial Pen Signals," IEEE Transactions on Cybernetics, vol. 47, no. 9, pp. 2872-2884, 2017, doi: 10.1109/TCYB.2016.2633318.
 
[42] M. Kashif, T. M. Deserno, D. Haak, and S. Jonas, "Feature description with SIFT, SURF, BRIEF, BRISK, or FREAK? A general question answered for bone age assessment," Computers in Biology and Medicine, vol. 68, pp. 67-75, 2016/01/01/ 2016, doi: https://doi.org/10.1016/j.compbiomed.2015.11.006.
 
[43] A. Gertych, A. Zhang, J. Sayre, S. Pospiech-Kurkowska, and H. K. Huang, "Bone age assessment of children using a digital hand atlas," Computerized Medical Imaging and Graphics, vol. 31, no. 4, pp. 322-331, 2007/06/01/ 2007, doi: https://doi.org/10.1016/j.compmedimag.2007.02.012.
 
[44] Y. A. Ding, F. Mutz, K. F. Côco, L. A. Pinto, and K. S. Komati, "Bone age estimation from carpal radiography images using deep learning," Expert Systems, vol. 37, no. 6, p. e12584, 2020.
 
[45] T. D. Bui, J.-J. Lee, and J. Shin, "Incorporated region detection and classification using deep convolutional networks for bone age assessment," Artificial Intelligence in Medicine, vol. 97, pp. 1-8, 2019/06/01/ 2019, doi: https://doi.org/10.1016/j.artmed.2019.04.005.
 
[46] F. Abdali-Mohammadi, V. Bajalan, and A. Fathi, "Toward a Fault Tolerant Architecture for Vital Medical-Based Wearable Computing," Journal of Medical Systems, vol. 39, no. 12, p. 149, 2015/09/12 2015, doi: 10.1007/s10916-015-0347-7.
 
[47] H. Lobabi-Mirghavami, F. Abdali-Mohammadi, and A. Fathi, "A novel grammar-based approach to atrial fibrillation arrhythmia detection for pervasive healthcare environments," Journal of Computing and Security, vol. 2, no. 2, pp. 155-163, 2015.