3D image texture analysis of simulated and real-world vascular trees

A method is proposed for quantitative description of blood-vessel trees, which can be used for tree classification and/or physical parameters indirect monitoring. The method is based on texture analysis of 3D images of the trees. Several types of trees were defined, with distinct tree parameters (number of terminal branches, blood viscosity, input and output flow). A number of trees were computer-simulated for each type. 3D image was computed for each tree and its texture features were calculated. Best discriminating features were found and applied to 1-NN nearest neighbor classifier. It was demonstrated that (i) tree images can be correctly classified for realistic signal-to-noise ratio, (ii) some texture features are monotonously related to tree parameters, (iii) 2D texture analysis is not sufficient to represent the trees in the discussed sense. Moreover, applicability of texture model to quantitative description of vascularity images was also supported by unsupervised exploratory analysis. Eventually, the experimental confirmation was done, with the use of confocal microscopy images of rat brain vasculature. Several classes of brain tissue were clearly distinguished based on 3D texture numerical parameters, including control and different kinds of tumours - treated with NG2 proteoglycan to promote angiogenesis-dependent growth of the abnormal tissue. The method, applied to magnetic resonance imaging e.g. real neovasculature or retinal images can be used to support noninvasive medical diagnosis of vascular system diseases.

[1]  Phil Brodatz,et al.  Textures: A Photographic Album for Artists and Designers , 1966 .

[2]  Jian Chen,et al.  Quantifying 3-D vascular structures in MRA images using hybrid PDE and geometric deformable models , 2004, IEEE Transactions on Medical Imaging.

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

[4]  H Benoit-Cattin,et al.  The SIMRI project: a versatile and interactive MRI simulator. , 2005, Journal of magnetic resonance.

[5]  Martin Neumann,et al.  Voronoi Polyhedra Analysis of Optimized Arterial Tree Models , 2003, Annals of Biomedical Engineering.

[6]  Andrzej Materka,et al.  Texture analysis for magnetic resonance imaging , 2006 .

[7]  Yu-Chung N. Cheng,et al.  Magnetic Resonance Imaging: Physical Principles and Sequence Design , 1999 .

[8]  R.M. Haralick,et al.  Statistical and structural approaches to texture , 1979, Proceedings of the IEEE.

[9]  Anthony N. Mucciardi,et al.  A Comparison of Seven Techniques for Choosing Subsets of Pattern Recognition Properties , 1971, IEEE Transactions on Computers.

[10]  Andrzej Materka,et al.  Clustering stability-based feature selection for unsupervised texture classification , 2009 .

[11]  Ian Witten,et al.  Data Mining , 2000 .

[12]  Francis K. H. Quek,et al.  A review of vessel extraction techniques and algorithms , 2004, CSUR.

[13]  T. Poggio.  Vision by man and machine. , 1984, Scientific American.

[14]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .

[15]  A. Guyton,et al.  Textbook of Medical Physiology , 1961 .

[16]  David G. Stork,et al.  Pattern Classification , 1973 .

[17]  Michal Strzelecki,et al.  MaZda - A software package for image texture analysis , 2009, Comput. Methods Programs Biomed..

[18]  Michal Strzelecki,et al.  FEATURE EVALUATION OF TEXTURE TEST OBJECTS FOR MAGNETIC RESONANCE IMAGING , 2001 .

[19]  A. Materka,et al.  Texture analysis in application to quantitative study of 3D vascular tree images , 2009, 2009 Proceedings of 6th International Symposium on Image and Signal Processing and Analysis.

[20]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[21]  Huan Liu,et al.  Feature Selection for Classification , 1997, Intell. Data Anal..

[22]  Paul S. Tofts,et al.  Quantitative MRI of the brain : measuring changes caused by disease , 2003 .

[23]  Andrzej Materka,et al.  Cluster Analysis in Application to Quantitative Inspection of 3D Vascular Tree Images , 2009, Computer Recognition Systems 3.

[24]  M K Markey,et al.  Application of the mutual information criterion for feature selection in computer-aided diagnosis. , 2001, Medical physics.

[25]  Marek Kretowski,et al.  Toward a better understanding of texture in vascular CT scan simulated images , 2001, IEEE Transactions on Biomedical Engineering.

[26]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[27]  Kotagiri Ramamohanarao,et al.  Blood Vessel Segmentation from Color Retinal Images using Unsupervised Texture Classification , 2007, 2007 IEEE International Conference on Image Processing.

[28]  Michal Strzelecki,et al.  Texture Analysis Methods - A Review , 1998 .

[29]  Johan Montagnat,et al.  Magnetic resonance imaging (MRI) simulation on a grid computing architecture , 2003, CCGrid 2003. 3rd IEEE/ACM International Symposium on Cluster Computing and the Grid, 2003. Proceedings..

[30]  Alan C. Evans,et al.  MRI Simulation Based Evaluation and Classifications Methods , 1999, IEEE Trans. Medical Imaging.

[31]  S. Al-Sarraj,et al.  The glial precursor proteoglycan, NG2, is expressed on tumour neovasculature by vascular pericytes in human malignant brain tumours , 2002, Neuropathology and applied neurobiology.

[32]  G. McLachlan,et al.  Pattern Classification: A Unified View of Statistical and Neural Approaches. , 1998 .

[33]  Jürgen Schürmann,et al.  Pattern classification , 2008 .

[34]  Jean-Louis Coatrieux,et al.  Fast algorithm for 3-D vascular tree modeling , 2003, Comput. Methods Programs Biomed..

[35]  M A Rupnick,et al.  Three-dimensional visualization of microvessel architecture of whole-mount tissue by confocal microscopy. , 2006, Microvascular research.

[36]  Olav Haraldseth,et al.  NG2 proteoglycan promotes angiogenesis‐dependent tumor growth in the central nervous system by sequestering angiostatin , 2002, FASEB journal : official publication of the Federation of American Societies for Experimental Biology.

[37]  Juyang Weng,et al.  Using Discriminant Eigenfeatures for Image Retrieval , 1996, IEEE Trans. Pattern Anal. Mach. Intell..