Harun UĞUZ, Ömer Kaan BAYKAN, Gür Emre GÜRAKSIN

Bone age determination in young children (newborn to 6 years old) using support vector machines

Bone age is assessed through a radiological analysis of the left-hand wrist and is then compared to chronological age. A conflict between these two values indicates an abnormality in the development process of the skeleton. This study, conducted on children aged between 0 and 6 years, proposes a computer-based diagnostic system to eliminate the disadvantages of the methods used in bone age determination. For this purpose, primarily an image processing procedure was applied to the X-ray images of the left-hand wrist of children from different ethnic groups aged between 0 and 6 years. A total of 9 features, corresponding to the carpal bones and distal epiphysis of the radius bone with some physiological attributes of the children, were obtained. Then, by using gain ratio, the best 6 features were used for the classification process. Next, the bone age determination process was performed with the obtained features with the help of the support vector machine (SVM), naive Bayes, k-nearest neighborhood, and C4.5 algorithms. Finally, the features used in the determination process and their effects on the accuracies were examined. The results of the designed system showed that SVM method has a better achievement rate than the other methods at a rate of 72.82%. Additionally, in this study, a new feature corresponding to the distance between the centers of gravity of the carpal bones was used for the classification process, and the analysis of the related feature showed that there was a statistically significant difference at P

PDF

___

[1] Trist´an A, Arribas JI. A radius and ulna skeletal age assessment system. In: IEEE 2005 Workshop on Machine Learning for Signal Processing; 28 September 2005; Mystic, CT, USA. New York, NY, USA: IEEE. pp. 221-226.
[2] Hasaltın E, Be¸sdok E. Elbilek r¨ontgen g¨or¨unt¨ulerinden radyolojik kemik ya¸sıtespitinde yapay sinir a˘glarıkullanımı. In: National Conference of Electrical, Electronics and Computer Engineering; 812 December 2004; Bursa, Turkey (in Turkish).
[3] Darendeliler F, Bundak R. Boy kısalı˘gına yakla¸sım. G¨uncel Pediatri 2005; 3: 49-52 (Turkish).
[4] Boyuna˘ga O. Radyolojik olarak kemik ya¸sıtayini. Klinik Pediatri 2002; 2: 81-85 (in Turkish). ¨
[5] Giordano D, Spampinato C, Scarciofalo G, Leonardi R. An automatic system for skeletal bone age measurement by robust processing of carpal and epiphysial/metaphysial bones. IEEE T Instrum Meas 2010; 59: 2539-2553.
[6] Kim HJ, Kim WY. Computerized bone age assessment using DCT and LDA. In Gagalowicz A, Philips W, editors. Computer Vision/Computer Graphics Collaboration Techniques. Berlin, Germany: Springer, 2007. pp. 440-448.
[7] Fern´andez MAM, C´ardenes R, Moreno EM, Garc´ıa RL, Fern´andez MM, L´opez CA. Automatic articulated registration of hand radiographs. Image Vision Comput 2009; 27: 1207-1222.
[8] Cao F, Huang HK, Pietka E, Gilsanz V. Digital hand atlas and web-based bone age assessment: system design and implementation. Comput Med Imag Grap 2000; 24: 297-307.
[9] Hsieh CW, Jong TL, Tiu CM. Bone age estimation based on phalanx information with fuzzy constrain of carpals. Med Biol Eng Comput 2007; 45: 283-295.
[10] Hsieh CW, Liu TC, Jong TL, Tiu CM. A fuzzy-based growth model with principle component analysis selection for carpal bone-age assessment. Med Biol Eng Comput 2010; 48: 579-588.
[11] Garc´ıa RL, Fern´andez MM, Arribas JI, L´opez CA. A fully automatic algorithm for contour detection of bones in hand radiographs using active contours. In: IEEE 2003 International Conference on Image Processing; 1417 September 2003; Barcelona, Spain. New York, NY, USA. pp. 421-424.
[12] Zhang A, Gertych A, Liu BJ. Automatic bone age assessment for young children from newborn to 7-year-old using carpal bones. Comput Med Imag Graph 2007; 31: 299-310.
[13] Hsieh CW, Jong TL, Chou YH, Tiu CM. Computerized geometric features of carpal bone for bone age estimation. Chinese Med J-Peking 2007; 120: 767-770.
[14] Jantan S, Hussain A, Mustafa MM. Distal radius bone age estimation based on fuzzy model. In: IEEE 2010 Conference on Biomedical Engineering and Sciences; 30 November2 December 2010; Kuala Lumpur, Malaysia. New York, NY, USA: IEEE. pp. 427-432.
[15] Somkantha K, Umpon NT, Auephanwiriyakul S. Bone age assessment in young children using automatic carpal bone feature extraction and support vector regression. J Digit Imaging 2011; 24: 1044-1058.
[16] Al-Taani AT. Classification of hand bones for bone age assessment. In: IEEE 1996 International Conference on Electronics, Circuits and Systems; 1316 October 1996; Rodos, Greece. New York, NY, USA: IEEE. pp. 1088-1091.
[17] Harmsen M, Fischer B, Schramm H, Seidl T, Deserno TM. Support vector machine classification based on correlation prototypes applied to bone age assessment. IEEE T Inf Technol B 2013; 17: 190-197.
[18] Gertych A, Zhang A, Sayre J, Kurkowska SP, Huang HK. Bone age assessment of children using a digital hand atlas. Comput Med Imag Graph 2007; 31: 322-331.
[19] Pietka E. Computer-assisted bone age assessmentdatabase adjustment. Int Congr Ser 2003; 1256: 87-92.
[20] Polaka I. Feature selection approaches in antibody display data analysis. In: RHEI 2011 International Scientific and Practical Conference on Environment, Technology, and Resources; 2022 June 2011; Rezekne, Latvia. Rezekne,Latvia: Rezenke Higher Education Institute. pp. 16-23.
[21] Grimaldi M, Cunningham P, Kokaram A. An evaluation of alternative feature selection strategies and ensemble techniques for classifying music. In: Workshop in Multimedia Discovery and Mining; 22 September 2003; Dubrovnik, Croatia.
[22] C¸ omak E, Arslan A, T¨urko˘glu ˙I. A decision support system based on support machines for diagnosis of the heart valve diseases. Comput Biol Med 2007; 37: 21-27.
[23] Vapnik V, Golowich S, Smola A. Support vector method for function approximation, regression estimation, and signal processing. Adv Neur In 1996; 9: 281-287.
[24] Zhang H. The optimality of naive Bayes. In: Proceedings of the Seventeenth Florida Artificial Intelligence Research Society Conference; 1719 May 2004; Miami Beach, FL, USA. pp. 562-567.
[25] Wang Q, Garrity GM, Tiedje JM, Cole JR. Naive Bayesian classifier for rapid assignment of rRNA sequences into the new bacterial taxonomy. Appl Environ Microb 2007; 73: 5261-5267.
[26] Rish I. An empirical study of the naive Bayes classifier. In: IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence; 410 August 2001; Washington, DC, USA. New York, NY, USA: IBM. pp. 41-46.
[27] Hmeidi I, Hawashin B, El-Qawasmeh E. Performance of KNN and SVM classifiers on full word Arabic articles. Adv Eng Inform 2008; 22: 106-111.
[28] Perrizo W, Ding Q, Denton A. Lazy classifiers using p-trees. In: ICSA 2002 International Conference on Computer Applications in Industry and Engineering; 79 November 2002; San Diego, CA, USA. Winona, MN, USA: ISCA.pp. 176-179.
[29] He P, Chen L, Xu XH. Fast C4.5. In: IEEE 2007 International Conference on Machine Learning and Cybernetics; 1922 August 2007; Hong Kong. New York, NY, USA: IEEE. pp. 2841-2846.
[30] U˘guz H. A two stage feature selection method for text categorization by using information gain, principal component analysis and genetic algorithm. Knowl-Based Syst 2011; 24: 1024-1032.
[31] Sun W, Chen J, Li J. Decision tree and PCA-based fault diagnosis of rotating machinery. Mech Syst Signal Pr 2007; 21: 1300-1317.
[32] Perona P, Malik J, Scale-space and edge detection using anisotropic diffusion. IEEE T Pattern Anal 1990; 12: 629-639.
[33] Wang Q, Yang J. Eye location and eye state detection in facial images with unconstrained background. J Inform Comput Sci 2006; 1: 284-289.
[34] Pietka E, Gertych A, Pospiech S, Cao F, Huang HK, Gilsanz V. Computer-assisted bone age assessment: image preprocessing and epiphyseal/metaphyseal ROI extraction. IEEE T Med Imaging 2001; 20: 715-729.
[35] Pisano ED, Zong S, Hemminger BM, DeLuca M, Johnston RE, Muller KE, Brauening MP, Pizer SM. Contrast limited adaptive histogram equalization image processing to improve the detection of simulated spiculations in dense mammograms. J Digit Imaging; 1998; 11: 193-200.
[36] McAndrew A. Introduction to Digital Image Processing with MATLAB. Boca Raton, FL, USA: CRC Press, 2004.
[37] Ding L, Goshtasby A. On the Canny edge detector. Pattern Recogn 2001 34: 721-725.