Multimodal Retinal Image Registration for Optic Disk Segmentation

R. Chrástek; M. Skokan; L. Kubečka; M. Wolf; K. Donath; J. Jan; G. Michelson; H. Niemann

doi:10.1055/s-0038-1633888

Methods of Information in Medicine, Table of Contents

Methods Inf Med 2004; 43(04): 336-342
DOI: 10.1055/s-0038-1633888

Original Article

Schattauer GmbH

Multimodal Retinal Image Registration for Optic Disk Segmentation

Authors

R. Chrástek

¹Chair for Pattern Recognition, Friedrich-Alexander-University, Erlangen, Germany
M. Skokan

²Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic
L. Kubečka

²Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic
M. Wolf

¹Chair for Pattern Recognition, Friedrich-Alexander-University, Erlangen, Germany
K. Donath

¹Chair for Pattern Recognition, Friedrich-Alexander-University, Erlangen, Germany
J. Jan

²Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic
G. Michelson

³Department of Ophthalmology, Friedrich-Alexander-University Erlangen-Nuremberg, Erlangen, Germany
H. Niemann

¹Chair for Pattern Recognition, Friedrich-Alexander-University, Erlangen, Germany

Abstract

Summary

Objectives: The analysis of the optic disk morphology with the means of the scanning laser tomography is an important step for glaucoma diagnosis. A method we developed for optic disk segmentation in images of the scanning laser tomograph is limited by noise, nonuniform illumination and presence of blood vessels. Inspired by recent medical research, we wanted to develop a tool for improving optic disk segmentation by registration of images of the scanning laser tomograph and color fundus photographs and by applying a method we developed for optic disk segmentation in color fundus photographs.

Methods: The segmentation of the optic disk for glaucoma diagnosis in images of the scanning laser tomograph is based on morphological operations, detection of anatomical structures and active contours and has been described in a previous paper [1]. The segmentation of the optic disk in the fundus photographs is based on nonlinear filtering, Canny edge detector and a modified Hough transform. The registration is based on mutual information using simulated annealing for finding maxima.

Results: The registration was successful 86.8% of the time when tested on 174 images. Results of the registration have shown a very low displacement error of a maximum of about 5 pixels. The correctness of the registration was manually evaluated by measuring distances between the real vessel borders and those from the registered image.

Conclusions: We have developed a method for the registration of images of the scanning laser tomograph and fundus photographs. Our first experiments showed that the optic disk segmentation could be improved by fused information from both image modalities.

Keywords

Computer-assisted image processing - optic disk - glaucoma - multimodal registration - scanning laser tomography

Full Text

References

References
1 Chrastek R, Wolf M, Donath K, Niemann H, Hothorn T, Lausen B, Lämmer R, Mardin CY, Michelson G. Automated Segmentation of the Optic Nerve Head for Glaucoma Diagnosis. Proc of BVM. 2003: 338-42. Berlin: Springer; 2003
2 Wong TY, Klein R, Klein BE, Tielsch JM, Hubbard L, Nieto FJ. Retinal microvascular abnormalities and their relationship with hypertension, cardiovascular disease, and mortality. Surv Ophthalmol 2001; 46 (01) 59-80.
3 The World Health Report 1998: Life in the 21st century – A vision for all. Geneva: World Health Organization; 1998
4 Iester M, Mikelberg FS, Courtright P, Burk RO, Caprioli J, Jonas JB, Weinreb RN, Zangwill L. Interobserver variability of optic disk variables measured by confocal scanning laser tomography. Am J Ophthalmol 2001; 132 (01) 57-62.
5 Michelson G, Groh MJ. Screening models for glaucoma. Curr Opin Ophthalmol 2001; 12 (02) 105-11.
6 Greaney MJ, Hoffman DC, Garway-Heath DF, Nakla M, Coleman AL, Caprioli J. Comparison of optic nerve imaging methods to distinguish normal eyes from those with glaucoma. Invest Ophthalmol Vis Sci 2002; 43 (01) 140-5.
7 Hothorn T, Lausen B. Bagging tree classifiers for laser scanning images: a data- and simulation- based strategy. Artif Intell Med 2003; 27 (01) 65-79.
8 Tolias YA, Panas SM. A fuzzy vessel tracking algorithm for retinal images based on fuzzy clustering. IEEE Trans Med Imaging 1998; 17 (02) 263-73.
9 Kochner B, Schuhmann D, Michaelis M, Mann G, Englmeier KH. Course tracking and contour extraction of retinal vessels from color fundus photographs: Most efficient use of steerable filters for model-based image analysis. Procs SPIE 1998; 3338: 755-61.
10 Walter T, Klein JC, Massin P, Erginay A. A contribution of image processing to the diagnosis of diabetic retinopathy – detection of exudates in color fundus images of the human retina. IEEE Trans Med Imaging 2002; 21 (10) 1236-43.
11 Hubbard LD, Brothers RJ, King WN, Clegg LX, Klein R, Cooper LS, Sharrett AR, Davis MD, Cai J. Methods for evaluation of retinal microvascular abnormalities associated with hypertension/sclerosis in the Atherosclerosis Risk in Communities Study. Ophthalmology 1999; 106 (12) 2269-80.
12 Maintz JB, Viergever MA. A survey of medical image registration. Med Image Anal 1998; 2 (01) 1-36.
13 Zana F, Klein JC. A multimodal registration algorithm of eye fundus images using vessels detection and Hough transform. IEEE Trans Med Imaging 1999; 18 (05) 419-28.
14 Corona E, Mitra S, Wilson M, Krile T, Kwon YH, Soliz P. Digital stereo image analyzer for generating automated 3-D measures of optic disc deformation in glaucoma. IEEE Trans Med Imaging 2002; 21 (10) 1244-53.
15 Rosin PL, Marshall D, Morgan JE. Multimodal Retinal Imaging: New Strategies for the Detection of Glaucoma. Int Conf Image Processing Rochester. 2002. Vol III 137-41.
16 Bartsch DU, Freeman WR. Axial Intensity Distribution Analysis of the Human Retina with a Confocal Scanning Laser Tomograph. Exp Eye Res 1994; 58: 161-73.
17 Cree MJ, Olson JA, McHardy KC, Sharp PF, Forrester JV. The preprocessing of retinal images for the detection of fluorescein leakage. Phys Med Biol 1999; 44: 293-308.
18 Chrastek R, Wolf M, Donath K, Niemann H, Michelson G. Automated calculation of retinal arteriovenous ratio for detection and monitoring of cerebrovascular disease based on assessment of morphological changes of retinal vascular system. Proc IAPR Workshop on Machine Vision Applications. 2002: 240-3.
19 Pinz A, Bernogger S, Datlinger P, Kruger A. Mapping the human retina. IEEE Trans Med Imaging 1998; 17 (04) 606-19.
20 Tamura S, Okamoto Y, Yanashima K. Zero-crossing interval correction in tracing eye-fundus blood vessels. Pattern Recogn 1988; 21 (03) 227-33.
21 Kucera D. Segmentation of Multidimensional Image Data in Medicine. PhD Thesis, Brno; TU: 1996
22 Skokan M, Skoupy A, Jan J. Registration of multimodal images of retina. Proc. 24th Annual Intern Conf IEEE – EMBS, Houston (USA). 2002: 1094-6.
23 Maes F, Collignon A, Vandermeulen D, Marchal G, Suetens P. Multimodality image registration by maximization of mutual information. IEEE Trans Med Imaging 1997; 16 (02) 187-98.
24 Michelson G, Groh M, Pogorelov P, Scibor M, Chrastek R, Keppler K, Keller J. Projekt “e-EyeCare”: Augenheilkunde im Web. Deutsches Ärzteblatt, Supplement: Praxis Computer 2002; 99 (11) 20
25 Kubecka L, Skokan M, Jan J. Optimization Methods for Registration of Multimodal Images of Retina. Proc. 25th Annual Int Conf IEEE-EMBS, Cancún (Mexico). 2003: 599-601.
26 Chrastek R, Michelson G, Donath K, Wolf M, Niemann H. Vessel Segmentation in Retina Scans. Proc of BIOSIGNAL. 2000: 252-4. Brno: VUTIUM Press; 2000