Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지

Preprocessing Effect by Using k-means Clustering and Merging .Algorithms in MR Cardiac Left Ventricle Segmentation

자기공명 심장 영상의 좌심실 경계추출에서의 k 평균 군집화와 병합 알고리즘의 사용으로 인한 전처리 효과

  • Ik-Hwan Cho (Department of Electronic Engineering, College of Engineering, Inha University) ;
  • Jung-Su Oh (Interdisciplinary Program of Biomedical Engineering, Seoul National University) ;
  • Kyong-Sik Om (Institute of Medical Biological Engineering, Medical Research Center Seoul National University Hospital) ;
  • In-Chan Song (Department of Radiology, Seoul National University Hospital) ;
  • Kee-Hyun Chang (Department of Radiology, Seoul National University Hospital) ;
  • Dong-Seok Jeong (Department of Electronic Engineering, College of Engineering, Inha University)
  • Published : 2003.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

For quantitative analysis of the cardiac diseases. it is necessary to segment the left-ventricle (LY) in MR (Magnetic Resonance) cardiac images. Snake or active contour model has been used to segment LV boundary. However, the contour of the LV front these models may not converge to the desirable one because the contour may fall into local minimum value due to image artifact inside of the LY Therefore, in this paper, we Propose the Preprocessing method using k-means clustering and merging algorithms that can improve the performance of the active contour model. We verified that our proposed algorithm overcomes local minimum convergence problem by experiment results.

심장 질환의 정량적 분석을 위해서 자기공명 심장 영상에서 좌심실의 경계를 추출하는 것이 중요하다. Snake 또는 active contour 모델은 좌심실 경계 추출을 위해서 사용되어 왔다. 그러나 이 모델을 사용하는데 있어서 좌심실의 경계선이 좌심실 내부에 생긴 결절 때문에 경계선이 지역최소값으로 빠져서 원하는 경계선에 수렴하지 못 할 수도 있다. 그러므로 본 논문에서는 active contour 모델의 성능을 향상시킬 수 있는 k 평균 군집화와 병합 알고리즘을 이용한 전처리 방법을 제안하였다. 제안된 방법으로 지역 최소값 수렴 문제를 해결함을 확인하였다.

Keywords

References

  1. Determining the optimal weights in multiple objective function optimization M. A. Gennert;A. L. Yuille
  2. Ph.D. dissertation (Ecole Polytechnique Federale de Lausanne) Sequential and competitive methods for estimation of multiple motions S. Ayer
  3. A new algorithm for 3D automatic detection and tracking of cardiac wall motion M. F. Santarelli;V. Positano;L. Landini;A. Benassi
  4. Snake : Avtive contour models v.66 M. Kass;A. Witkin;D. Tezopoulos
  5. A geometric model for active contours v.66 V. Caselles;F. Catte;T. Coll;F. Dibos
  6. Shape modeling with front propagation: A level set app roach v.17 R. Malladi;J. A. SethianB. C. Vemuri
  7. Geodesic active contours V. Caselles;R. Kimmel;G. Sapiro
  8. Multi-resolution algorithms for active contour models B. Leroy;I. Herlin;L. D. Cohen
  9. On active contour models and ballonns v.53 L. D. Cohen
  10. IEEE Trans. Pattern Anal. Machine Intell v.15 Finite-element methods for active contour models and balloons for 2-D and 3-D images L. D. Cohen;I. Cohen
  11. Gradient Vector Flow: A New External Force for Snakes Xu. Chenyang;J. L. Prince
  12. IEEE Transactions on Image processing v.7 no.3 Snake, Shapes, and Gradient Vector Flow Xu. Chenyang;J. L. Prince
  13. IEEE Trans. Pattern Anal. Machine Intell. v.6 K-means-type algorithms S. Z. Selim;M. A. Ismail
  14. in Proc. Picture Coding Symp. 97, Berlin, Germany Image segmentation by integration approach using initial dependence of k-means algorithm S. Sakaida;Y. Shishikui;Y. Tanaka;I. Yuyama
  15. in Proc. Eur. Conf. Mulitmedia Applications Sevices and Techniques (ECMAST98) 3D representation of videconference image sequences using VRML 2.0 I. Kompatsiaris;M. G. Strintzis
  16. IEEE Trans . On circuits and Systems for Video Technology v.10 no.8 Spatiotemporal Segmentation and Tracking of Object for Visualization of Videoconference Image Sequences I. Kompatsiaris;M. G. Strintzis