Image processing algorithms for retinal montage synthesis, mapping, and real-time location determination

Although laser retinal surgery is the best available treatment for choroidal neovascularization, the current procedure has a low success rate (50%). Challenges, such as motion-compensated beam steering, ensuring complete coverage and minimizing incidental photodamage, can be overcome with improved instrumentation. This paper presents core image processing algorithms for (1) rapid identification of branching and crossover points of the retinal vasculature; (2) automatic montaging of video retinal angiograms; (3) real-time location determination and tracking using a combination of feature-tagged point-matching and dynamic-pixel templates. These algorithms tradeoff conflicting needs for accuracy, robustness to image variations (due to movements and the difficulty of providing steady illumination) and noise, and operational speed in the context of available hardware. The algorithm for locating vasculature landmarks performed robustly at a speed of 16-30 video image frames/s depending upon the field on a Silicon Graphics workstation. The montaging algorithm performed at a speed of 1.6-4 s for merging 5-12 frames. The tracking algorithm was validated by manually locating six landmark points on an image sequence with 180 frames, demonstrating a mean-squared error of 1.35 pixels. It successfully detected and rejected instances when the image dimmed, faded, lost contrast, or lost focus.

[1]  Persistent and recurrent neovascularization after krypton laser photocoagulation for neovascular lesions of ocular histoplasmosis. Macular Photocoagulation Study Group. , 1989, Archives of ophthalmology.

[2]  David L. Milgram,et al.  Adaptive Techniques for Photomosaicking , 1977, IEEE Transactions on Computers.

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

[4]  Rama Chellappa,et al.  A computational vision approach to image registration , 1993, IEEE Trans. Image Process..

[5]  Larry S. Davis,et al.  A survey of edge detection techniques , 1975 .

[6]  K. Rayner Eye Movements and Visual Cognition , 1992 .

[7]  M. Goldbaum,et al.  DIGITAL OVERLAY OF FLUORESCEIN ANGIOGRAMS AND FUNDUS IMAGES FOR TREATMENT OF SUBRETINAL NEOVASCULARIZATION , 1992, Retina.

[8]  K. Gitter,et al.  USE OF DIGITIZED FLUORESCEIN ANGIOGRAM SYSTEM TO EVALUATE LASER TREATMENT FOR SUBRETINAL NEOVASCULARIZATION: TECHNIQUE , 1993, Retina.

[9]  Recurrent choroidal neovascularization after argon laser photocoagulation for neovascular maculopathy. Macular Photocoagulation Study Group. , 1986, Archives of ophthalmology.

[10]  Arthur C. Sanderson,et al.  Model-based matching using a hybrid genetic algorithm , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[11]  Steven F. Barrett,et al.  Digital tracking and control of retinal images , 1994 .

[12]  G Soubrane,et al.  Occult subretinal new vessels in age-related macular degeneration. Natural History and early laser treatment. , 1990, Ophthalmology.

[13]  Stephen L. Trokel,et al.  Lasers in Ophthalmology , 1992 .

[14]  Emanuele Trucco,et al.  Computer and Robot Vision , 1995 .

[15]  G. S. Watson Statistics on Spheres , 1983 .

[16]  Juan Carlos Esteva,et al.  3D object pose form clustering with multiple views , 1985, Pattern Recognit. Lett..

[17]  N. Bressler,et al.  Clinical characteristics of choroidal neovascular membranes. , 1987, Archives of ophthalmology.

[18]  R. Flower,et al.  A clinical technique and apparatus for simultaneous angiography of the separate retinal and choroidal circulations. , 1973, Investigative ophthalmology.

[19]  A. V. Cideciyan,et al.  Registration of ocular fundus images: an algorithm using cross-correlation of triple invariant image descriptors , 1995 .

[20]  G. Timberlake,et al.  Feature-Based Registration of Retinal Images , 1987, IEEE Transactions on Medical Imaging.

[21]  Harvey F. Silverman,et al.  A Class of Algorithms for Fast Digital Image Registration , 1972, IEEE Transactions on Computers.

[22]  K. Gitter,et al.  EVALUATION OF PERSISTENCE OF SUBRETINAL NEOVASCULAR MEMBRANES USING DIGITIZED ANGIOGRAPHIC ANALYSIS , 1993, Retina.

[23]  Emin Anarim,et al.  Decision based directional edge detector , 1994, Signal Process..

[24]  R. Wootton,et al.  Measurement of capillary dropout in retinal angiograms by computerised image analysis , 1992, Pattern Recognit. Lett..

[25]  Subhasis Chaudhuri,et al.  Automated assembling of images: image montage preparation , 1995, Pattern Recognit..

[26]  H. G. Rylander,et al.  Real-time algorithm for retinal tracking , 1993, IEEE Transactions on Biomedical Engineering.

[27]  S. Umeyama,et al.  Least-Squares Estimation of Transformation Parameters Between Two Point Patterns , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[29]  M. Goldbaum,et al.  Detection of blood vessels in retinal images using two-dimensional matched filters. , 1989, IEEE transactions on medical imaging.

[30]  R Birngruber,et al.  Semiconductor diode laser photocoagulation in retinal vascular disease. , 1990, Ophthalmology.

[31]  Gabriel Coscas,et al.  Natural History of Occult Subretinal New-Vessels in Age-Related Macular Degeneration , 1987 .

[32]  George C. Stockman,et al.  Matching Images to Models for Registration and Object Detection via Clustering , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  S. Fine Observations following laser treatment for choroidal neovascularization. , 1988, Archives of ophthalmology.

[34]  Mark Nelson,et al.  Automated registration of digital ocular fundus images for comparison of lesions , 1993, Photonics West - Lasers and Applications in Science and Engineering.

[35]  J T Thompson,et al.  RETINAL CARTOGRAPHY: An Analysis of Two-dimensional and Three-dimensional Mapping of the Retina , 1992, Retina.

[36]  Badrinath Roysam,et al.  Algorithms for automatic retinal mapping and real-time location determination for an improved retinal laser surgery system , 1995 .