Journal of Korea Multimedia Society (한국멀티미디어학회논문지)

Korea Multimedia Society (한국멀티미디어학회)
권호 표지

A Bone Age Assessment Method Based on Normalized Shape Model

정규화된 형상 모델을 이용한 뼈 나이 측정 방법

  • 유주환 (한양대학교 전자통신컴퓨터공학과) ;
  • 이종민 (한양대학교 전자컴퓨터통신공학과) ;
  • 김회율 (한양대학교 전자통신컴퓨터공학부)
  • Published : 2009.03.30
Download PDF
⟨ Previous Next ⟩

Abstract

Bone age assessment has been widely used in pediatrics to identify endocrine problems of children. Since the number of trained doctors is far less than the demands, there has been numerous requests for automatic estimation of bone age. Therefore, in this paper, we propose an automatic bone age assessment method that utilizes pattern classification techniques. The proposed method consists of three modules; a finger segmentation module, a normalized shape model generation module and a bone age estimation module. The finger segmentation module segments fingers and epiphyseal regions by means of various image processing algorithms. The shape model abstraction module employ ASM to improves the accuracy of feature extraction for bone age estimation. In addition, SVM is used for estimation of bone age. Features for the estimation include the length of bone and the ratios of bone length. We evaluated the performance of the proposed method through statistical analysis by comparing the bone age assessment results by clinical experts and the proposed automatic method. Through the experimental results, the mean error of the assessment was 0.679 year, which was better than the average error acceptable in clinical practice.

뼈 나이 측정은 소아의 내분비계 관련 질병 진단을 위해 소아과에서 널리 사용되는 방법이다. 그러나 전문 인력이 부족하여 자동화된 측정 방법에 대한 꾸준한 요구가 있었다. 따라서 본 논문에서는 패턴 인식기법을 이용한 자동화된 뼈 나이 측정 알고리즘을 제안한다. 제안하는 알고리즘은 X-ray 영상에서 손가락뼈의 각 부분을 자동으로 분류하는 과정과 분류된 뼈 영상으로부터 정규화된 형상 모델을 추출하는 과정, 그리고 정규화된 형상 모델로부터 뼈 나이를 측정하는 과정으로 구성된다. 제안하는 알고리즘은 능동 형상 모델(Active Shape Model: ASM)을 이용하여 나이 측정에 사용되는 특정값 추출의 정확도를 향상시켰으며, 뼈 나이 분류를 위해 사용된 Support Vector Machine(SVM)의 입력으로 정규화된 형상 모델로부터 얻어진 각 뼈의 크기와 비율을 특징값으로 사용하였다. 성능 평가를 위해서 한양대학교 부속병원에서 제공한 영상에 대해 전문가가 평가한 나이와 제안한 알고리즘을 이용하여 측정된 나이를 통계적으로 비교 분석하였다. 실험을 통하여 본 논문에서 제안한 특징값과 알고리즘으로 뼈 나이를 진단한 결과, 전문가에 의한 결과와 평균 0.679살의 오차 이내의 뛰어난 뼈 나이 측정 성능을 보였다.

Keywords

References

  1. W. W. Greulich and S. I. Pyle, Radiographic Atlas of Skeletal Development of the Hand and Wrist, Stanford University Press, San Francisco, Calif., 1959.
  2. W. W. Greulich and S. I. Pyle, Radiographic Atlas of Skeletal Development of the Hand and Wrist 2nd ed., Stanford University Press, San Francisco, Calif., 1971.
  3. J. M. Tanner and R. H. Whitehous, Assessment of Skeletal Maturity and Prediction of Adult Height (TW Method), Academic Press, London, 1962.
  4. J. M. Tanner and R. H. Whitehouse, Assessment of Skeletal Maturity and Prediction of Adult Height (TW2 Method), Academic Press, London, 1975.
  5. J. M. Tanner and R. H. Whitehouse, Assessment of Skeletal Maturity and Prediction of Adult Height 2nd ed., Academic Press, London, 1983.
  6. E. Pietka and Lotfi Kaabi, "Feature Extraction in Carpal-Bone Analysis," IEEE Transactions on Medical Imaging, Vol.12, No.1, pp. 44-49, 1993. https://doi.org/10.1109/42.222665
  7. E. Pietka and M. F. McNitt-Gray, "Computer-Assisted Phalangeal Analysis in Skeletal Age Assessment," IEEE Transactions on Medical Imaging, Vol.10, No.4, pp. 616-620, 1991. https://doi.org/10.1109/42.108597
  8. E. Pietka and A. Gertych, "Computer-Assisted Bone Age Assessment: Image Preprocessing and Epiphyseal/Metaphyseal ROI Extraction," IEEE Transaction on Medical Image, Vol.20, No.8, pp. 715-729, 2001. https://doi.org/10.1109/42.938240
  9. E. Pietka and S. Pospiech-Kurkowskaa, "Integration of Computer Assisted Bone Age Assessment with Clinical PACS," Computerized Medical Imaging and Graphics, Vol.27, No.2-3, pp. 217-228, 2003. https://doi.org/10.1016/S0895-6111(02)00076-9
  10. B. C. Fan and C. W. Hsieh, "Automatic Bone Age Estimation Based on Carpal-bone Image: A Preliminary Report," Chinese Medical Journal(Taipei), Vol.64, No.4, pp. 203-208, 2001.
  11. M. Niemeijer and B. van Ginneken, "Assessing the Skeletal Age from a Hand Radiograph: Automating the Tanner-Whitehouse Method," Proceeding of SPIE Medical Imaging, Vol.5032, pp. 1197-1205, 2003.
  12. T. F. Cootes and C. J. Taylor, "Active Shape models - Their Training and Application," Computer Vision and Image Understanding, Vol.61, No.1, pp. 38-59, 1995. https://doi.org/10.1006/cviu.1995.1004
  13. T. F. Cootes and A. Hill, C. J. Taylor, "The Use of Active Shape Models for Locating Structures in Medical Images," Image and Vision Computing, Vol.12, No.6, pp. 355-366, 1994. https://doi.org/10.1016/0262-8856(94)90060-4
  14. M. Kass and A. Witkin, "Snakes: Active Contour models," International Journal of Computer Vision, Vol.1, No.4, pp. 321-331, 1988. https://doi.org/10.1007/BF00133570
  15. V. Vapnik, The Nature of Statistical Learning Theory, Springer-verlag, New York, 1995.
  16. C. J. C. Burges, "A Tutorial on Support Vector Machines for Pattern Recognition," Data Mining and Knowledge Discovery, Vol.2, No.2, pp. 121-167, 1998. https://doi.org/10.1023/A:1009715923555
  17. B. Scholkopf, Support Vector Learning, Oldenburg-Verlag, Munich, 1997.
  18. E. Osuna and R. Fereund, "Training Support Vector Machines : An Application to Face Detection," Proceeding IEEE. Computer Vision and Pattern Recognition, pp. 130-136, 1997.
  19. 황재문, 장석환, “컴퓨터 비젼 기법을 이용한 자동 뼈 나이 측정 시스템,” 신호처리합동학술대회, 제17권, 1호, pp. 91-91, 2004.
  20. R. C. Gonzalez, Digital Image Processing, Pearson Prentice Hall, New Jersey, 1992.
  21. J.M. Lee, W.H. Kim, "Epiphyses Extraction Method Using Shape Informtion for Left hand Radiography," International Conference on Convergence and Hybrid Information Technology 2008, pp. 319-326, 2008.