A fully automated lumen contour detection of intravascular ultrasound images based on Gabor texture analysis

The detection of the lumen contour in the Intravascular Ultrasound (IVUS) image plays a very important part in assessing atherosclerosis. However, for the images at a high sampling frequency, the blood signals make it difficult to detect the lumen contours. In this paper, a new segmentation method is proposed and implemented that detects the lumen contour in IVUS images automatically. The method is based on the difference of the texture features between the blood signals and the vessel wall. During preprocessing of the raw IVUS images, the method successfully removed the artificial noise, which was caused by the sampling catheter. After that, the lumen texture features and the vessel wall texture features were able to be distinguished through applying the Gabor wavelet transformation. Based on the distinguished texture features, the lumen contour was detected and refined smoothly. The experiment results indicate that the lumen contour in the raw IVUS image can be detected completely automatically and accurately.

[1]  W. Cleveland.  Robust Locally Weighted Regression and Smoothing Scatterplots , 1979 .

[2]  Wilson S. Geisler,et al.  Multichannel Texture Analysis Using Localized Spatial Filters , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Alan C. Bovik,et al.  Analysis of multichannel narrow-band filters for image texture segmentation , 1991, IEEE Trans. Signal Process..

[4]  Anil K. Jain,et al.  Unsupervised texture segmentation using Gabor filters , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.

[5]  Michael Unser,et al.  Texture classification and segmentation using wavelet frames , 1995, IEEE Trans. Image Process..

[6]  William E. Higgins,et al.  Efficient Gabor filter design for texture segmentation , 1996, Pattern Recognit..

[7]  Milan Sonka,et al.  Tissue characterization in intravascular ultrasound images , 1998, IEEE Transactions on Medical Imaging.

[8]  Jon D. Klingensmith,et al.  Quantification of coronary arterial plaque volume using 3D reconstructions formed by fusing intravascular ultrasound and biplane angiography , 1999, Medical Imaging.

[9]  J. Thomas,et al.  Three-dimensional segmentation of luminal and adventitial borders in serial intravascular ultrasound images. , 1999, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[10]  P. Serruys,et al.  True 3-dimensional reconstruction of coronary arteries in patients by fusion of angiography and IVUS (ANGUS) and its quantitative validation. , 2000, Circulation.

[11]  D. Vince,et al.  Evaluation of three-dimensional segmentation algorithms for the identification of luminal and medial-adventitial borders in intravascular ultrasound images , 2000, IEEE Transactions on Medical Imaging.

[12]  David A. Clausi,et al.  Designing Gabor filters for optimal texture separability , 2000, Pattern Recognit..

[13]  Petia Radeva,et al.  Automatic segmentation of artery wall in coronary IVUS images: a probabilistic approach , 2000, Computers in Cardiology 2000. Vol.27 (Cat. 00CH37163).

[14]  G Kovalski,et al.  Three-dimensional automatic quantitative analysis of intravascular ultrasound images. , 2000, Ultrasound in medicine & biology.

[15]  Hui Zhu,et al.  IVUS image segmentation based on contrast , 2002, SPIE Medical Imaging.

[16]  Dimitrios I. Fotiadis,et al.  An automated method for lumen and media-adventitia border detection in a sequence of IVUS frames , 2004, IEEE Transactions on Information Technology in Biomedicine.

[17]  J. Reiber,et al.  Advanced contour detection for three-dimensional intracoronary ultrasound: a validation – in vitro and in vivo , 2002, The International Journal of Cardiovascular Imaging.

[18]  Johan H. C. Reiber,et al.  Multi-agent segmentation of IVUS images , 2004, Pattern Recognit..

[19]  Frits Mastik,et al.  Fully automatic luminal contour segmentation in intracoronary ultrasound imaging-a statistical approach , 2004, IEEE Transactions on Medical Imaging.

[20]  E. Tuzcu,et al.  Assessment of coronary compensatory enlargement by three-dimensional intravascular ultrasound , 2000, The International Journal of Cardiac Imaging.

[21]  Makoto Yoshizawa,et al.  Moment-based texture segmentation of luminal contour in intravascular ultrasound images , 2005, Journal of Medical Ultrasonics.

[22]  N. Maglaveras,et al.  Integration of multi-modality imaging for accurate 3D reconstruction of human coronary arteries in vivo , 2006 .

[23]  N. Maglaveras,et al.  In-vivo validation of spatially correct three-dimensional reconstruction of human coronary arteries by integrating intravascular ultrasound and biplane angiography , 2006, Coronary artery disease.

[24]  Jean Meunier,et al.  Intravascular ultrasound image segmentation: a three-dimensional fast-marching method based on gray level distributions , 2006, IEEE Transactions on Medical Imaging.

[25]  Yiannis Kompatsiaris,et al.  Automated IVUS Contour Detection Using Intesity Features and Radial Basis Function Approximation , 2007, Twentieth IEEE International Symposium on Computer-Based Medical Systems (CBMS'07).

[26]  Aleksandra Mojsilović,et al.  Automatic segmentation of intravascular ultrasound images: A texture-based approach , 1997, Annals of Biomedical Engineering.

[27]  Ioannis Kompatsiaris,et al.  Image analysis techniques for automated IVUS contour detection. , 2008, Ultrasound in medicine & biology.

[28]  Johan H. C. Reiber,et al.  User-Agent Cooperation in Multiagent IVUS Image Segmentation , 2009, IEEE Transactions on Medical Imaging.

[29]  P. Mishra,et al.  Texture Segmentation Using Gabor Filters and Wavelets , 2010 .