Automatic Detection of Left Ventricular Contour from 2-D Echocardiograms using Fuzzy Hough Transform

퍼지 Hough 변환에 의한 2-D 심초음파도에서의 좌심실 윤곽 자동검출

  • ;
  • K.P
  • 조진호 (경북대학교 공과대학 전자공학과 및 경북대학교병원 의공학과) ;
  • Published : 1992.06.01

Abstract

An algorithm has been proposed for the automatic detection of optimal epiand endocardial left ventricular borders from 2-D short axis echocardiogram which is degraded by noise and echo drop out. For the implementation of the algorithm, we modified Ballard's Generalized Hough Transform which can be applicable only for deterministic object border, and newly proposed Fuzzy Hough Transform method. The algorithm presented here allows detection of object whose exact shapes are unknown. The algorithm only requires an approximate model of target object based on anatomical data. To detect the approximate epicardial contour of left ventricle, Fuzzy Hough Transform was applied to the echocardiogram. The optimal epicardial contour was founded by using graph searching method which contains cost function analysis process. Using this optimal epicardial contour and average thickness imformation of left ventricular wall, the approximate endocardial line was founded, and graph searching method was also used to detect optimal endocardial contour.

Keywords

References

  1. IEEE Trans. Biomed. Eng. v.BME-29 no.8 An approach to optimal threshold selection on a sequence of two-dimensional echocardiographic images L.F.Zhang(et. al.)
  2. Proc. Computers in Cardiologhy Automated endocardial definition of 2-D echocardiograms : A comparision of four standard edge detectors and thresholding techiques D.T.Linker(et. al.)
  3. Proc. Computers in Cardiology A cell automation algorithm for region consolidation and edge detection on sector scan W.Siler(et al.)
  4. IEEE Trans. Medical Imaging v.MI-6 Semiautomatic border tracking of cine echocardiographic ventricular images D.Adam(et al.)
  5. Intelligent left ventricular contour detection results from two-dimensional echocardiogram A.Ezekiel(et al.)
  6. Proc. Computers in Cardiology Automated endocardial contour detection in short-axis 2-D echocardiograms : Methodology and assessment of variability J.G.Bosch(et al.)
  7. IEEE Trans. Biomed. v.BME-31 no.6 An effective algorithm for extracting serial endocardial border from 2-di-mensional echocardiogram L.F.Zhang(et al.)
  8. Pattern Recognition v.23 Detecting myocardial boundaries of left ventricle from a single frame 2DE image W.S.Chou(et al.)
  9. IEEE Trans. Medical Imaging v.8 Automatic ventricular cavity boundary detection from sequential ultrasound images using simulated annealing N.Friedland;D.Adam
  10. Journal of Am. Soc. Echo. v.3 A second generation computer based edge detection algorithm for short-axis two-dimensional echocardiographic images : Accuracy and improvement in interobserver variability E.A.Geiser(et al.)
  11. Pattern Reconstruction v.20 Plan-based boundary extraction and 3-D reconstruction for orthogonal 2-D echocardiography S.Tamura(et al.)
  12. The American Journal of Cardiology v.52 Automatic computer processing of digital 2-dimensional echocardiograms A.J.Bada(et al.)
  13. Proc. Computer in Cardiology Echocardiographic myocardial edge detection using an optimization protocol N.Friedland;D.Adam
  14. Image processing v.1445 Model-based boundary detection in echocardiography using dynamic programming technique L.Dong(et al.)
  15. Echocardiography an integrated approach Stephen Arvan
  16. Computer Visions D.H.Ballard;C.M.Brown
  17. SPIE Architechtures and Algorithms for Digital Image Processing v.534 Locating objects in a complex image B.Dawson;G.Trees
  18. IEEE Trans. Medical Imaging v.MI-8 Automated analysis of coronary arterial morphology in cineangiograms : Geometric and physiologic validation in humans S.R.Fleagle;M.R.Johnson(et al.)