Application of Kohonen network for automatic point correspondence in 2D medical images

In this paper, a generalized application of Kohonen Network for automatic point correspondence of unimodal medical images is presented. Given a pair of two-dimensional medical images of the same anatomical region and a set of interest points in one of the images, the algorithm detects effectively the set of corresponding points in the second image, by exploiting the properties of the Kohonen self organizing maps (SOMs) and embedding them in a stochastic optimization framework. The correspondences are established by determining the parameters of local transformations that map the interest points of the first image to their corresponding points in the second image. The parameters of each transformation are computed in an iterative way, using a modification of the competitive learning, as implemented by SOMs. The proposed algorithm was tested on medical imaging data from three different modalities (CT, MR and red-free retinal images) subject to known and unknown transformations. The quantitative results in all cases exhibited sub-pixel accuracy. The algorithm also proved to work efficiently in the case of noise corrupted data. Finally, in comparison to a previously published algorithm that was also based on SOMs, as well as two widely used techniques for detection of point correspondences (template matching and iterative closest point), the proposed algorithm exhibits an improved performance in terms of accuracy and robustness.

[1]  Yong-Sheng Chen,et al.  Fast algorithm for robust template matching with M-estimators , 2003, IEEE Trans. Signal Process..

[2]  Hamid Bolouri,et al.  Automatic registration of complex images using a self organizing neural system , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[3]  Jürgen Weese,et al.  A comparison of similarity measures for use in 2-D-3-D medical image registration , 1998, IEEE Transactions on Medical Imaging.

[4]  Helge J. Ritter,et al.  The deformable feature map - a novel neurocomputing algorithm for adaptive plasticity in pattern analysis , 2002, Neurocomputing.

[5]  H. Jeremy Bockholt,et al.  Subcortical, cerebellar, and magnetic resonance based consistent brain image registration , 2003, NeuroImage.

[6]  Clark F. Olson,et al.  Adaptive-Scale Filtering and Feature Detection Using Range Data , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Jürgen Schmidhuber,et al.  Self-organizing nets for optimization , 2004, IEEE Transactions on Neural Networks.

[8]  Farzin Mokhtarian,et al.  Scale-Based Description and Recognition of Planar Curves and Two-Dimensional Shapes , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Max A. Viergever,et al.  A survey of medical image registration , 1998, Medical Image Anal..

[10]  Yi-Ping Hung,et al.  Fast block matching algorithm based on the winner-update strategy , 2001, IEEE Trans. Image Process..

[11]  Radu Horaud,et al.  Finding Geometric and Relational Structures in an Image , 1990, ECCV.

[12]  Karl Rohr,et al.  Recognizing corners by fitting parametric models , 1992, International Journal of Computer Vision.

[13]  George K. Matsopoulos,et al.  Multimodal registration of retinal images using self organizing maps , 2004, IEEE Transactions on Medical Imaging.

[14]  Azriel Rosenfeld,et al.  Gray-level corner detection , 1982, Pattern Recognit. Lett..

[15]  Anders Heyden,et al.  An iterative factorization method for projective structure and motion from image sequences , 1999, Image Vis. Comput..

[16]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[17]  B. Rosner.  Percentage Points for a Generalized ESD Many-Outlier Procedure , 1983 .

[18]  Karl Rohr,et al.  Extraction of 3d anatomical point landmarks based on invariance principles , 1999, Pattern Recognit..

[19]  Michael Brady,et al.  The Curvature Primal Sketch , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  M. GHANBARI,et al.  The cross-search algorithm for motion estimation [image coding] , 1990, IEEE Trans. Commun..

[21]  Aldo von Wangenheim,et al.  Data-driven registration for local deformations , 1996, Pattern Recognit. Lett..

[22]  A. Ardeshir Goshtasby,et al.  A comparative study of transformation functions for nonrigid image registration , 2006, IEEE Transactions on Image Processing.

[23]  Yulong Shen,et al.  Registration and fusion of retinal images-an evaluation study , 2003, IEEE Transactions on Medical Imaging.

[24]  Cordelia Schmid,et al.  An Affine Invariant Interest Point Detector , 2002, ECCV.

[25]  Dragana Brzakovic,et al.  Establishing the correspondence between control points in pairs of mammographic images , 1997, IEEE Trans. Image Process..

[26]  Thomas S. Huang,et al.  Motion analysis of articulated objects from monocular images , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Shigeru Ando,et al.  Image Field Categorization and Edge/Corner Detection from Gradient Covariance , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Moshe Eizenman,et al.  A new methodology for determining point-of-gaze in head-mounted eye tracking systems , 2004, IEEE Transactions on Biomedical Engineering.

[29]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[30]  Guido Valli,et al.  Matching of medical images by self-organizing neural networks , 2004, Pattern Recognit. Lett..

[31]  Xinting Gao,et al.  Multiscale contour corner detection based on local natural scale and wavelet transform , 2007, Image Vis. Comput..

[32]  Bruce E. Rosen,et al.  Genetic Algorithms and Very Fast Simulated Reannealing: A comparison , 1992 .

[33]  Hiroshi Murase,et al.  Parametric Feature Detection , 1996, International Journal of Computer Vision.

[34]  Olivier D. Faugeras,et al.  Determination of Camera Location from 2-D to 3-D Line and Point Correspondences , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[35]  Pavel Krsek,et al.  The Trimmed Iterative Closest Point algorithm , 2002, Object recognition supported by user interaction for service robots.

[36]  B Likar,et al.  Automatic extraction of corresponding points for the registration of medical images. , 1999, Medical physics.

[37]  Laxmi Parida,et al.  Junctions: Detection, Classification, and Reconstruction , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[38]  Wei Cai,et al.  A region-based multi-sensor image fusion scheme using pulse-coupled neural network , 2006, Pattern Recognit. Lett..

[39]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[40]  Richard A. Baldock,et al.  Robust Point Correspondence Applied to Two-and Three-Dimensional Image Registration , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[41]  Tomás Pajdla,et al.  Structure from motion with wide circular field of view cameras , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[42]  Peter Meer,et al.  Point matching under large image deformations and illumination changes , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[43]  Stephen M. Smith,et al.  SUSAN—A New Approach to Low Level Image Processing , 1997, International Journal of Computer Vision.

[44]  G. Medioni,et al.  Corner detection and curve representation using cubic B-splines , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.