在本篇論文中，為解決在alpha-gamma equalization enhancement中參數選取的問題，提出一基於自動化參數選擇的影像處理流程，進而完成指骨骨齡的判讀系統。首先以行掃描方式切割出左手X光影像，然後進行去背景與影像轉正的工作，再框出三根手指的範圍。接著以區域極值作為骨骺分割依據，獲取九個指節影像，以作為影像處理的輸入。在影像切割步驟之前，我們以適應性參數的gamma-selection enhancement作為影像增強前處理。本篇論文採用三種影像切割方式，分別為adaptive two-means clustering algorithm、GVF snake、以及圓形除均切割。為了判讀指骨骨骼年齡，我們從切割出來的影像中抽取出指骨的多種特徵，包含了三種紋理特徵、三種幾何特徵、與二種用以描述其二維和一維特性的形狀特徵，並進行特徵選擇。此外，我們統計了各個特徵在不同骨骼年齡的分布狀況，由此可以判斷出特徵和指骨骨骼年齡的關係。再以各特徵相對於標準骨齡的平均值與標準差為依據，建立多組隸屬度模型，以進行骨骼年齡的判讀。本系統主要解決了alpha-gamma equalization enhancement在參數選擇上的問題，並以多種影像切割方法進行驗證。基於之前學長所開發的骨齡判讀系統，骨骺/幹骺特徵區域的萃取成功率得到了些微的提升，最後進而發展出一套全自動化的指骨骨骼年齡判讀系統，以期輔助醫師進行骨骼年齡的判讀。

The study employs the gamma-selection enhancement to segment a radiograph of a hand and a wrist, and to build a bone age estimation (BAE) system. The proposed methods mainly include three steps: preprocessing, segmentation, and features analysis. First the preprocessing stag contains left hand cropping, background removal, orientation correction, and detection of phalangeal bone region of interest (PROI), and locating the position of epiphyseal/metaphyseal region of interest (EMROI) from local extremes. To choose the adaptive gamma parameter for equalization enhancement is one of the focal points in this thesis. Four quantitative shape measurements including misclassification error, relative foreground area error, modified Hausdorff distances, and edge mismatch via gamma-selection equalization are used to make the phalangeal assessment. By using comparison of error values, we can choose the adaptive parameters. A segmentation step is done for several methods consisting of adaptive two-means clustering algorithm, GVF snake, and local gray-level analysis segmentation. Comparing with other two methods, adaptive two-means algorithm with gamma-selection enhancement is requested for the later features analysis stage. We then extract three different sets of features, texture features, shape features, and geometric features, to build a series of membership functions for BAE. The effectiveness of the three sets of features is analyzed and a simplified procedure of feature selection is introduced to choose some representative features by using the correlation coefficients between the features and chronological age (CA). The results show that the BAE with the geometric features have better discrimination power than other two sets. The overall success rate of ROI extraction is about 90%, and the correct rate of assessing BA within 1.0 year errors and 1.5 years errors are 70.46% and 88.07% for female, and 73.34% and 86.97% for male.

[1] W. W. Greulich and S. I. Pyle, Radiographic atlas of skeletal development of the hand and wrist, 2nd ed. Stanford, Calif.,: Stanford University Press, 1959.
[2] G. Gilli, "The assessment of skeletal maturation," Hormone Research, vol. 45 Suppl 2, pp. 49-52, 1996.
[3] S. Mora, M. I. Boechat, E. Pietka, H. K. Huang, and V. Gilsanz, "Skeletal age determinations in children of European and African descent: Applicability of the Greulich and Pyle standards," Pediatric Research, vol. 50, pp. 624-628, Nov 2001.
[4] R. M. Malina and G. P. Beunen, "Assessment of skeletal maturity and prediction of adult height (TW3 method). Third edition.," American Journal of Human Biology, vol. 14, pp. 788-789, Nov-Dec 2002.
[5] S. Aja-Fernandez, R. de Luis-Garcia, M. A. Martin-Fernandez, and C. Alberola-Lopez, "A computational TW3 classifier for skeletal maturity assessment. A Computing with Words approach," Journal of Biomedical Informatics, vol. 37, pp. 99-107, Apr 2004.
[6] L. Molinari, T. Gasser, and R. H. Largo, "TW3 bone age: RUS/CB and gender differences of percentiles for score and score increments," Ann Hum Biol, vol. 31, pp. 421-35, Jul-Aug 2004.
[7] K. Ashizawa, C. Kumakura, X. Zhou, F. Fin, and J. Cao, "RUS skeletal maturity of children in Beijing," Annals of Human Biology, vol. 32, pp. 316-325, May-Jun 2005.
[8] G. R. Milner, R. K. Levick, and R. Kay, "Assessment of bone-age - a comparison of the Greulich and Pyle, and the Tanner and Whitehouse methods," Clinical Radiology, vol. 37, pp. 119-121, Mar 1986.
[9] M. Vignolo, S. Milani, G. Cerbello, P. Coroli, E. Dibattista, and G. Aicardi, "Fels, Greulich-Pyle, and Tanner-Whitehouse bone-age assessments in a group of Italian children and adolescents," American Journal of Human Biology, vol. 4, pp. 493-500, 1992.
[10] P. J. Ryan, T. P. Spector, G. M. Blake, D. V. Doyle, and I. Fogelman, "A comparison of reference bone-mineral density-measurements derived from 2 sources - referred and population-based," British Journal of Radiology, vol. 66, pp. 1138-1141, Dec 1993.
[11] D. G. King, D. M. Steventon, M. P. Osullivan, A. M. Cook, V. P. L. Hornsby, I. G. Jefferson, and P. R. King, "Reproducibility of bone ages when performed by radiology registrars - an audit of Tanner-and-Whitehouse-II versus Greulich-and-Pyle methods," British Journal of Radiology, vol. 67, pp. 848-851, Sep 1994.
[12] H. Frisch, S. Riedl, and T. Waldhor, "Computer-aided estimation of skeletal age and comparison with bone age evaluations by the method of Greulich-Pyle and Tanner-Whitehouse," Pediatric Radiology, vol. 26, pp. 226-231, Mar 1996.
[13] G. Aicardi, M. Vignolo, S. Milani, A. Naselli, P. Magliano, and P. Garzia, "Assessment of skeletal maturity of the hand-wrist and knee: A comparison among methods," American Journal of Human Biology, vol. 12, pp. 610-615, Sep-Oct 2000.
[14] A. Tristan and J. I. Arribas, "A radius and ulna skeletal age assessment system," 2005 IEEE Workshop on Machine Learning for Signal Processing (MLSP), pp. 221-226, 2005.
[15] R. K. Bull, P. D. Edwards, P. M. Kemp, S. Fry, and I. A. Hughes, "Bone age assessment: a large scale comparison of the Greulich and Pyle, and Tanner and Whitehouse (TW2) methods," Archives of Disease in Childhood, vol. 81, pp. 172-173, Aug 1999.
[16] R. M. Malina, M. E. P. Reyes, J. C. Eisenmann, L. Horta, J. Rodrigues, and R. Miller, "Height, mass and skeletal maturity of elite Portuguese soccer players aged 11-16 years," Journal of Sports Sciences, vol. 18, pp. 685-693, Sep 2000.
[17] K. Sato, T. Mito, and H. Mitani, "An accurate method of predicting mandibular growth potential based on bone maturity," American Journal of Orthodontics and Dentofacial Orthopedics, vol. 120, pp. 286-293, Sep 2001.
[18] E. Pietka, L. Kaabi, M. L. Kuo, and H. K. Huang, "Feature extraction in carpal-bone analysis," IEEE Trans Med Imaging, vol. 12, pp. 44-9, 1993.
[19] B. C. Fan, C. W. Hsieh, T. L. Jong, and C. M. Tiu, "Automatic bone age estimation based on carpal-bone image--a preliminary report," Zhonghua Yi Xue Za Zhi (Taipei), vol. 64, pp. 203-8, Apr 2001.
[20] E. Pietka, A. Gertych, S. Pospiech, F. Cao, H. K. Huang, and V. Gilsanz, "Computer-assisted bone age assessment: image preprocessing and epiphyseal/metaphyseal ROI extraction," IEEE Trans Med Imaging, vol. 20, pp. 715-29, Aug 2001.
[21] E. Pietka, M. F. McNitt-Gray, M. L. Kuo, and H. K. Huang, "Computer-assisted phalangeal analysis in skeletal age assessment," IEEE Trans Med Imaging, vol. 10, pp. 616-20, 1991.
[22] E. Pietka and H. K. Huang, "Epiphyseal fusion assessment based on wavelets decomposition analysis," Comput Med Imaging Graph, vol. 19, pp. 465-72, Nov-Dec 1995.
[23] B. E. Pietka, S. Pospiech, A. Gertych, F. Cao, H. K. Huang, and V. Gilsanz, "Computer automated approach to the extraction of epiphyseal regions in hand radiographs," Journal of Digital Imaging, vol. 14, pp. 165-72, Dec 2001.
[24] S. N. Cheng, H. P. Chan, L. T. Niklason, and R. S. Adler, "Automated segmentation of regions of interest on hand radiographs," Med Phys, vol. 21, pp. 1293-300, Aug 1994.
[25] S. Mahmoodi, B. S. Sharif, E. G. Chester, J. P. Owen, and R. Lee, "Skeletal growth estimation using radiographic image processing and analysis," Ieee Transactions on Information Technology in Biomedicine, vol. 4, pp. 292-297, Dec 2000.
[26] C. W. Hsieh, T. L. Jong, and C. M. Tin, "Bone age estimation based on phalanx information with fuzzy constrain of carpals," Medical & Biological Engineering & Computing, vol. 45, pp. 283-295, Mar 2007.
[27] C. W. Hsieh, T. C. Liu, T. L. Jong, and C. M. Tiu, "A fuzzy-based growth model with principle component analysis selection for carpal bone-age assessment," Medical & Biological Engineering & Computing, vol. 48, pp. 579-588, Jun 2010.
[28] D. J. Michael and A. C. Nelson, "Handx - a model-based system for automatic segmentation of bones from digital hand radiographs," Ieee Transactions on Medical Imaging, vol. 8, pp. 64-69, Mar 1989.
[29] T. N. Pappas, "An adaptive clustering-algorithm for image segmentation," Ieee Transactions on Signal Processing, vol. 40, pp. 901-914, Apr 1992.
[30] G. K. Manos, A. Y. Cairns, I. W. Rickets, and D. Sinclair, "Segmenting radiographs of the hand and wrist," Computer Methods and Programs in Biomedicine, vol. 43, pp. 227-237, Jun 1994.
[31] E. Pietka, "Computer-assisted bone age assessment based on features automatically extracted from a hand radiograph," Comput Med Imaging Graph, vol. 19, pp. 251-9, May-Jun 1995.
[32] S. Mahmoodi, B. S. Sharif, E. G. Chester, J. P. Owen, and R. E. J. Lee, "Automated vision system for skeletal age assessment using knowledge based techniques," in Image Processing and Its Applications, 1997., Sixth International Conference on, 1997, pp. 809-813 vol.2.
[33] C. Y. Xu and J. L. Prince, "Snakes, shapes, and gradient vector flow," Ieee Transactions on Image Processing, vol. 7, pp. 359-369, Mar 1998.
[34] A. M. M. da Silva, S. D. Olabarriaga, C. A. Dietrich, and C. A. A. Schmitz, On determining a signature for skeletal maturity. Los Alamitos: Ieee Computer Soc, 2001.
[35] E. Pietka, A. Gertych, S. Pospiecha Euro Kurkowska, F. Cao, H. K. Huang, and V. Gilzanz, "Computer-assisted bone age assessment: graphical user interface for image processing and comparison," Journal of Digital Imaging, vol. 17, pp. 175-88, Sep 2004.
[36] H. H. Lin, S. G. Shu, S. W. Kuo, C. H. Wang, Y. P. Chan, and S. S. Yu, "Alpha-gamma equalization-enhanced hand radiographic image segmentation scheme," Optical Engineering, vol. 48, Oct 2009.
[37] N. Otsu, "Threshold selection method from gray-level histograms," Ieee Transactions on Systems Man and Cybernetics, vol. 9, pp. 62-66, 1979.
[38] C. H. Chang, "An investigation of computerized automatic bone age assessment system based on phalangeal image features," Master thesis, EE NTHU, 2003.
[39] J. S. Lee, "Refined fltering of image noise using local statistics," Computer Graphics and Image Processing, vol. 15, pp. 380-389, 1981.
[40] H. Tamura, S. Mori, and T. Yamawaki, "Textural features corresponding to visual perception," Systems, Man and Cybernetics, IEEE Transactions on, vol. 8, pp. 460-473, 1978.