Title :
Registration of bimodal retinal images - improving modifications
Author :
Kubecka, L. ; Jan, J.
Author_Institution :
Dept. of Biomedical Eng., Brno Univ. of Technol., Czech Republic
Abstract :
The proper optical disc segmentation in images provided by confocal laser scanning ophthalmoscope and by color fundus-camera is a necessary step in early glaucoma or arteriosclerosis detection. Fusing information from both modalities into a vector-valued image is expected to improve the segmentation reliability. The paper describes a registration of these images using optimization based on mutual information criterion function extended with gradient-image mutual information. The controlled random search (CRS) has been found to be a more robust optimization routine than the simulated annealing (SA) while tested on a set of 174 image pairs. Finally, the multi-resolution algorithm for bimodal retinal image registration achieving the success-rate of 94% is proposed.
Keywords :
biomedical optical imaging; eye; image registration; image resolution; image segmentation; laser applications in medicine; medical image processing; optimisation; arteriosclerosis detection; bimodal retinal image registration; color fundus-camera; confocal laser scanning ophthalmoscope; controlled random search; early glaucoma detection; gradient-image mutual information; multiresolution algorithm; optical disc segmentation; optimization; simulated annealing; vector-valued image; Computational modeling; Entropy; Geometrical optics; Image processing; Image segmentation; Kernel; Mutual information; Retina; Robustness; Simulated annealing; controlled random search; image registration; mutual information; ophthalmologic image processing; optimization; retina; simplex; simulated annealing;
Conference_Titel :
Engineering in Medicine and Biology Society, 2004. IEMBS '04. 26th Annual International Conference of the IEEE
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-8439-3
DOI :
10.1109/IEMBS.2004.1403510
