Seyed Mohammad ALAVI, Pedram MASAELI

Automatic detection of coronary artery disease using registration of ultrasound images of the heart (echocardiography

Coronary artery diseases cause more than half of all deaths in the world. Obviously, early identification is an important way to control coronary artery disease that is diagnosed by measurement and scoring the general and regional movement of the left ventricle of heart (normal, hypokinetic, and akinetic). The most common method of imaging the heart using ultrasound is called echocardiography. Using this method accurate views of the heart walls, valves, and beginning of main arteries can be obtained. Due to the difficulty of the interpretation of these images, the length of time required, and errors in manual methods, an automated analysis method is required. In line with this goal, in this paper we have calculated the displacement field in a cycle of heart motion from two-dimensional echocardiography images. To do this, a frame is usually chosen as the reference frame and then all images in a cycle are mapped to it with a mathematical equation. The main idea is to find a semilocal spatiotemporal parametric model for deformation created in a cardiac cycle with nonrigid registration using B-spline functions as an optimization problem that effectively corrects differences due to movements by minimizing the difference between current frame and a reference frame. Motion estimation accuracy is measured using sum of squares differences. We use a gradient-descent algorithm and multiresolution method to acquire the coefficients in the motion model. The accuracy of the proposed method is assessed using a synthesis sequence of cardiac cycles produced with the simulation software Field II. This algorithm can be applied for the clinical analysis of the regional left ventricle and then movement parameters and threshold values for the scoring of each section can be extracted. The algorithm represents the significant difference between a part of a normal heart and an unhealthy heart and shows the potential of the clinical applications of the proposed method.

PDF

___

[1] Noble JA, Boukerroui D. Ultrasound image segmentation: a survey. IEEE T Med Imaging 2006; 25: 987-1010.
[2] Bosch JG, Mitchell SC, Lelieveldt BF, Nijland F, Sonka M, Reiber JC. Automatic segmentation of echocardiographic sequences by active appearance motion models. IEEE T Med Imaging 2002; 21: 1374-1383.
[3] Carranza N, Cristobal G, Ledesma-Carbayo MJ, Santos A. A new cardiac motion estimation method based on a spatio-temporal frequency approach and Hough transform. Comput Cardiol 2006; 33: 805-808.
[4] Ledesma-Carbayo MJ, Kybic J, Desco M, Santos A, S¨uhling M, Hunziker P, Unser M. Spatio-temporal nonrigid registration for ultrasound cardiac motion estimation. IEEE T Med Imaging 2005; 24: 1113-1126.
[5] S¨uhling M, Arigovindan M, Jansen C, Hunziker P, Unser M. Myocardial motion analysis from B-mode echocardiogram. IEEE T Med Imaging 2005; 14: 525-536.
[6] Ledesma-Carbayo MJ, Santos A, Kybic J, Mahia-Casado P, Fernandez G, Malpica N, Perez E. Myocardial strain analysis of echocardiographic sequences using non-rigid registration. Comput Cardiol 2004; 31: 313-316.
[7] Barcaro U, Moroni D, Salvetti O. Automatic computation of left ventricle ejection fraction from dynamic ultrasound imaging. Lect Notes Comput Sc 2008; 18: 351-358.
[8] Zitova B, Flusser J. Image registration methods: a survey. Image Vision Comput 2003; 21: 977-1000.
[9] Makela DT, Clarysse P, Sipila O, Pauna N, Pham Q, Katila T, I. Magnin I. A review of cardiac image registration methods. IEEE T Med Imaging 2002; 21: 1011-1021.
[10] Hill DG, Batchelor PG, Holden M, Hawkes DJ. Medical image registration. Phys Med Biol 2001; 46: 1-45.
[11] Rueckert D, Aljabar P. Nonrigid registration of medical images: theory, methods, and applications. IEEE Signal Proc Mag 2010; 27: 113-119.
[12] Malpica N, Santos A, Zuluaga MA, Ledesma MJ, Perez E, Fernandez MG, Desco M. Tracking of regions of interest in myocardial contrast echocardiography. Ultrasound Med Biol 2004; 30: 303-309.
[13] Kybic J. Fast parametric elastic image registration. IEEE T Image Process 2003; 12: 1427-1442.
[14] Ledesma-Carbayo MJ, Santos A, Kybic J, Mahia-Casado P, Fernandez G, Malpica N, Perez E. Cardiac motion analysis from ultrasound sequences using nonrigid registration: validation against Doppler tissue velocity. Ultrasound Med Biol 2006; 32: 483-490.
[15] Xie Z, Farin GE. Image registration using hierarchical B-splines. IEEE T Vis Comput Gr 2004; 10: 85-94.
[16] Mahia P, Ledesma-Carbayo MJ, Verdugo V, David EP, Santos A, Moreno M, Menendez MD, Fernandez MA. Radial versus longitudinal myocardial deformation from gray-scale echocardiography. Ultrasound Med Biol 2007; 33: 1699-1705.
[17] Rueckert D, Sonoda LI, Hayes C, Hill DG, Leach MO, Hawkes DJ. Nonrigid registration using free-form deformations: application to breast MR images. IEEE T Med Imaging 1999; 18: 712-721.
[18] Odobez JM, Bouthemy P. Robust multiresolution estimation of parametric motion models. J Vis Commun Image R 1995; 6: 348-365.
[19] Jensen JA. Field II: A program for simulating ultrasound systems. Med Biol Eng Comput 1996; 34: 351-353.