MRI diffusion-based filtering: a note on performance characterisation.

Frequently MRI data is characterised by a relatively low signal to noise ratio (SNR) or contrast to noise ratio (CNR). When developing automated Computer Assisted Diagnostic (CAD) techniques the errors introduced by the image noise are not acceptable. Thus, to limit these errors, a solution is to filter the data in order to increase the SNR. More importantly, the image filtering technique should be able to reduce the level of noise, but not at the expense of feature preservation. In this paper we detail the implementation of a number of 3D diffusion-based filtering techniques and we analyse their performance when they are applied to a large collection of MR datasets of varying type and quality.

[1]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Sophocles J. Orfanidis,et al.  Introduction to signal processing , 1995 .

[4]  Niklas Nordström.  Biased Anisotropic Diffusion - A Unified Regularization and Diffusion Approach to Edge Detection , 1990, ECCV.

[5]  Ross T. Whitaker,et al.  A multi-scale approach to nonuniform diffusion , 1993 .

[6]  Paul F. Whelan,et al.  Comparison of 2D and 3D clustering on short-axis magnetic resonance images of the left ventricle , 2004, CARS.

[7]  Jaakko Astola,et al.  Nonlinear multivariate image filtering techniques , 1995, IEEE Trans. Image Process..

[8]  Milan Sonka,et al.  Image pre-processing , 1993 .

[9]  Daniel Rueckert,et al.  Knowledge-based tensor anisotropic diffusion of cardiac magnetic resonance images , 1999, Medical Image Anal..

[10]  Ke Chen,et al.  A Feature-Preserving Adaptive Smoothing Method for Early Vision , 2000 .

[11]  Guido Gerig,et al.  Nonlinear anisotropic filtering of MRI data , 1992, IEEE Trans. Medical Imaging.

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

[13]  Milan Sonka,et al.  Image processing analysis and machine vision [2nd ed.] , 1999 .

[14]  Robert M. Haralick.  Performance Characterization in Computer Vision , 1992, BMVC.

[15]  Joachim Weickert,et al.  Anisotropic diffusion in image processing , 1996 .

[16]  R. Whitaker.  Geometry-limited diffusion in the characterization of geometric patches in images , 1993 .

[17]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[18]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Max A. Viergever,et al.  Efficient and reliable schemes for nonlinear diffusion filtering , 1998, IEEE Trans. Image Process..

[20]  Johan Montagnat,et al.  Anisotropic filtering for model-based segmentation of 4D cylindrical echocardiographic images , 2003, Pattern Recognit. Lett..

[21]  Rastislav Lukac,et al.  Fast adaptive similarity based impulsive noise reduction filter , 2003, Real Time Imaging.

[22]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.