Retinal angiogram registration by estimation of distribution algorithm

Abstract Retinal fundus photographs are employed as standard diagnostic tools in ophthalmology. We employ optimization techniques for registration of retinal angiograms, using non-linear pre-processing (Wiener filtering and morphological gradient) and computation of a similarity criterion. The present work makes a comparison between different optimization techniques, namely the optical flow minimization method, the Nelder-Mead local search, the CEDA and CHEDA metaheuristics. The impact of the resolution and median filtering of gradient image is studied and the robustness of the approaches is tested through experimental studies, performed on ICG angiographies. Our proposed method has shown interesting results, especially for high resolution registration problems.

[1]  Rick S. Blum,et al.  A hybrid image registration technique for a digital camera image fusion application , 2001, Inf. Fusion.

[2]  Frédéric Zana,et al.  A multimodal registration algorithm of eye fundus images using vessels detection and Hough transform , 1999, IEEE Transactions on Medical Imaging.

[3]  Bhabatosh Chanda,et al.  Fusion of 2D grayscale images using multiscale morphology , 2001, Pattern Recognit..

[4]  Charles V. Stewart,et al.  Robust hierarchical algorithm for constructing a mosaic from images of the curved human retina , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[5]  Stephen M. Smith,et al.  A global optimisation method for robust affine registration of brain images , 2001, Medical Image Anal..

[6]  Nobuhiko Hata,et al.  Design considerations for a computer-vision-enabled ophthalmic augmented reality environment , 1997, CVRMed.

[7]  D. Hill,et al.  Medical image registration , 2001, Physics in medicine and biology.

[8]  Nicholas Ayache,et al.  Towards a Better Comprehension of Similarity Measures Used in Medical Image Registration , 1999, MICCAI.

[9]  A. Pinz,et al.  Mapping the human retina , 1996, IEEE Transactions on Medical Imaging.

[10]  Munchurl Kim,et al.  Moving object segmentation in video sequences by user interaction and automatic object tracking , 2001, Image Vis. Comput..

[11]  Robyn A. Owens,et al.  Registration of stereo and temporal images of the retina , 1999, IEEE Transactions on Medical Imaging.

[12]  Michael H. Goldbaum,et al.  Registering retinal images using automatically selected control point pairs , 1994, Proceedings of 1st International Conference on Image Processing.

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

[14]  J. Andrew Bangham,et al.  Morphological scale-space preserving transforms in many dimensions , 1996, J. Electronic Imaging.

[15]  Jean Claude Nunes,et al.  A multiscale elastic registration scheme for retinal angiograms , 2004, Comput. Vis. Image Underst..

[16]  Joachim H. Nagel,et al.  Registration of high-resolution images of the retina , 1992, Medical Imaging.

[17]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[18]  Esther de Ves,et al.  Segmentation of macular fluorescein angiographies. A statistical approach , 2001, Pattern Recognit..

[19]  Joseph Jy-Haw Yu,et al.  Fast algorithm for digital retinal image alignment , 1989, Images of the Twenty-First Century. Proceedings of the Annual International Engineering in Medicine and Biology Society,.

[20]  Michal Irani,et al.  Computing occluding and transparent motions , 1994, International Journal of Computer Vision.

[21]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[22]  Jean-Christophe Pesquet,et al.  Motion estimation in the presence of illumination variations , 2000, Signal Process. Image Commun..

[23]  R. Mohan,et al.  Motion adaptive x-ray therapy: a feasibility study , 2001, Physics in medicine and biology.