Automatic Classification of Spinal Deformity by using Four Symmetrical Features on the Moire Images

Hyoungseop Kim, Satoshi Nakano, Joo Kooi Tan, Seiji Ishikawa, Yoshinori Otsuka, Hisashi Shimizu, Takashi Shinomiya

2007

Abstract

Spinal deformity is a disease mainly suffered by teenagers during their growth stage particularly from element school to middle school. There are many different causes of abnormal spinal curves, but all of them are unknown. The most common type is termed “idiopathic” that show 80% of the spinal deformity. Spinal deformity is a serious disease, mainly suffered by teenagers, especially girl’s student, during their growth stage. To find the spinal deformity in early stage, orthopedists have traditionally performed on children a painless examination called a forward bending test in mass screening of school. But this test is neither objective nor reproductive, and the inspection takes much time when applied to medical examination in schools. To solve this problem, a moire method has been proposed which takes moire topographic images of human subject backs and checks symmetry/asymmetry of the moire patterns in a two-dimensional way. In this paper, we propose a method for automatic classification of spinal deformity from moire topographic images by extracting four symmetrical features of the left-hand and right-hand side on the moire image. Feature of asymmetry degrees are applied to train employing the classifier such as Artificial Neural Network, Support Vector Machine, Self-Organization Map and AdaBoost.

References

  1. Y. Ohtsuka, A. Shinoto, and S. Inoue, “Mass school screening for early detection of scoliosis by use of moire topography camera and low dose X-ray imageing”, Clinical Orthopaedic Surgery, 14, 10, pp.973-984, 1979. (in Japanese).
  2. H. Takasaki, “Moire topography from its birth to practical application”, Optics and Lasers in Engineering, 3, pp.3-14, 1982.
  3. Kim, H.S., Ishikawa, S., Ohtsuka, Y., Shimizu, H., Sinomiya, T., Viergever, M.A. “Automatic scoliosis detection based on local centroids evaluation on moire topographic images of human backs”, IEEE Transaction on Medical Imaging, Vol.20, No.12, pp.1314-1320, 2001.
  4. Batouche, M. “A knowledge based system for diagnosing spinal deformations Moire pattern analysis and interpretation”, International Conference of Pattern Recognition, pp.591- 594, 1992.
  5. Minovic, P., Ishikawa, S., Kato, K. “Symmetry identification of a 3-D object represented by octree”, IEEE Trans. Patt. Anal. Machine Intell., PAMI-15, 5, 507-514, 1993.
  6. V. Vapnic: The nature of statistical learning theory, Springer-Verlag, New York, 1995.
  7. Christopher J. C. Burges “A Tutorial on Support Vector Machines for Pattern Recognition”, Data Mining and Knowledge Discovery 2, pp.121 - 167, 1998.
  8. T. Kohonen Self-organizing maps, Springer-Verlag New York, Inc., Secaucus, NJ, 1997.
  9. Y. Freund, R. E. Schapire, “Experiments with a New Boosting Algorithm”, International Conference on Machine Learning, pp.148-156, 1996.
Download


Paper Citation


in Harvard Style

Kim H., Nakano S., Kooi Tan J., Ishikawa S., Otsuka Y., Shimizu H. and Shinomiya T. (2007). Automatic Classification of Spinal Deformity by using Four Symmetrical Features on the Moire Images . In Proceedings of the 3rd International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2007) ISBN 978-972-8865-86-3, pages 99-106. DOI: 10.5220/0001623100990106


in Bibtex Style

@conference{anniip07,
author={Hyoungseop Kim and Satoshi Nakano and Joo Kooi Tan and Seiji Ishikawa and Yoshinori Otsuka and Hisashi Shimizu and Takashi Shinomiya},
title={Automatic Classification of Spinal Deformity by using Four Symmetrical Features on the Moire Images},
booktitle={Proceedings of the 3rd International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2007)},
year={2007},
pages={99-106},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001623100990106},
isbn={978-972-8865-86-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2007)
TI - Automatic Classification of Spinal Deformity by using Four Symmetrical Features on the Moire Images
SN - 978-972-8865-86-3
AU - Kim H.
AU - Nakano S.
AU - Kooi Tan J.
AU - Ishikawa S.
AU - Otsuka Y.
AU - Shimizu H.
AU - Shinomiya T.
PY - 2007
SP - 99
EP - 106
DO - 10.5220/0001623100990106