Automated Classification of Epiphyses in the Distal Radius and Ulna using a Support Vector Machine

The aim of this study was to automatically classify epiphyses in the distal radius and ulna using a support vector machine (SVM) and to examine the accuracy of the epiphyseal growth grades generated by the support vector machine. X‐ray images of distal radii and ulnae were collected from 140 Chinese teenagers aged between 11.0 and 19.0 years. Epiphyseal growth of the two elements was classified into five grades. Features of each element were extracted using a histogram of oriented gradient (HOG), and models were established using support vector classification (SVC). The prediction results and the validity of the models were evaluated with a cross‐validation test and independent test for accuracy (PA). Our findings suggest that this new technique for epiphyseal classification was successful and that an automated technique using an SVM is reliable and feasible, with a relative high accuracy for the models.

[1]  William M. Campbell,et al.  Support vector machines for speaker verification and identification , 2000, Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501).

[2]  Shimon Ullman,et al.  Face Recognition: The Problem of Compensating for Changes in Illumination Direction , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[4]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[5]  Qiuping Chen,et al.  Color face recognition by PCA-like approach , 2015, Neurocomputing.

[6]  Xinbo Gao,et al.  A novel semi-supervised learning for face recognition , 2015, Neurocomputing.

[7]  Hans Henrik Thodberg,et al.  Prediction of adult height based on automated determination of bone age. , 2009, The Journal of clinical endocrinology and metabolism.

[8]  Vladimir Cherkassky,et al.  The Nature Of Statistical Learning Theory , 1997, IEEE Trans. Neural Networks.

[9]  L. Morris.  Assessment of Skeletal Maturity and Prediction of Adult Height (TW3 Method) , 2003 .

[10]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[11]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[12]  Martin Küppers,et al.  Influence of the examiner’s qualification and sources of error during stage determination of the medial clavicular epiphysis by means of computed tomography , 2013, International Journal of Legal Medicine.

[13]  J. Prieto,et al.  The problem of aging human remains and living individuals: a review. , 2009, Forensic science international.

[14]  Li Guo-zheng.  Introduction to the algorithm of support vector machine and the software ChemSVM , 2002 .

[15]  Chengjun Liu,et al.  Color Image Discriminant Models and Algorithms for Face Recognition , 2008, IEEE Transactions on Neural Networks.

[16]  J. Suykens,et al.  A tutorial on support vector machine-based methods for classification problems in chemometrics. , 2010, Analytica chimica acta.

[17]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[18]  Kuo-Chen Chou,et al.  Support Vector Machine for predicting α-turn types , 2003, Peptides.

[19]  T. Riepert,et al.  Criteria for age estimation in living individuals , 2008, International Journal of Legal Medicine.

[20]  Hans Henrik Thodberg,et al.  The Use of Bone Age in Clinical Practice – Part 2 , 2011, Hormone Research in Paediatrics.

[21]  Bernard F. Buxton,et al.  Drug Design by Machine Learning: Support Vector Machines for Pharmaceutical Data Analysis , 2001, Comput. Chem..

[22]  J M Tanner,et al.  Reliability and validity of computer-assisted estimates of Tanner-Whitehouse skeletal maturity (CASAS): comparison with the manual method. , 1994, Hormone research.

[23]  Weiguang Hua,et al.  Correlation between age and the parameters of medial epiphysis and metaphysis of the clavicle using CT volume rendering images. , 2014, Forensic science international.