Abstract
In this paper we describe the automatic segmentation of the optic nerve head (ONH) with the long-term goal of automatically diagnosing early stages of glaucoma. The images are average images obtained from a scanning laser ophthalmoscope (SLO). The segmentation consists of the main s teps of finding a region of interest containing the ONH, constraining the search space for final segmentation, and computing the fine segmentation by an active contour model. The agreement of “true positive pixels,” i.e., pixels attributed to the ONH by both manual and automatic segmentation, is very good. The classification results from three different classifiers using manual or automatic segmentation still show an advantage of manual segmentation. One means to further improve the automatic segmentation is to use information from an SLO as well as from a fundus camera.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
R. Chrástek, M. Wolf, K. Donath, et al., “Automated Calculation of Retinal Arteriovenous Ratio for Detection and Monitoring of Cerebrovascular Disease Based on Assessment of Morphological Changes of Retinal Vascular System,” in Proceedings of IAPR Workshop on Machine Vision Applications, Nara, Japan, 2002, pp. 240–243.
R. Chrástek, M. Wolf, K. Donath, et al., “Automated Segmentation of the Optic Nerve Head for Glaucoma Diagnosis,” in Proceedings of Workshop Bildverarbeitung fur die Medizin 2003 (Erlangen, 2003), pp. 338–342.
L. D. Cohen and I. Cohen, “Finite Element Methods for Active Contour Models and Balloons for 2-D and 3-D Images,” IEEE Transactions on Pattern Analysis and Machine Intelligence 15, 1131–1147 (1993).
M. J. Greaney, D. C. Hoffmann, D. F. Garway-Heath, et al., “Comparison of Optic Nerve Imaging Methods to Distinguish Normal Eyes from Those with Glaucoma,” Investigative Ophthalmology and Visual Science 43, 140–145 (2002).
Heidelberg Engineering GmbH, “Quantitative Three-Dimensional Imaging of the Posterior Segment with the Heidelberg Retina Tomograph,” http://www.heidelbergengineering.de/tut/hrt/hrt-tutorial.html, 1997.
T. Hothorn and B. Lausen, “Bagging Tree Classifiers for Laser Scanning Images: Data-and Simulation-Based Strategy,” Artificial Intelligence in Medicine 27, 65–79 (2003).
L. D. Hubbard, R. J. Brothers, W. N. King, et al., “Methods for Evaluation of Retinal Microvascular Abnormalities Associated with Hypertension/Sclerosis in the Atherosclerosis Risk in Communities Study,” Ophthalmology 106, 2269–2280 (1999).
F. E. Kruse, R. O. W. Burk, H. E. Völcker, et al., “Reproducibility of Topographic Measurements of the Optic Nerve Head with Laser Tomographic Scanning,” Ophthalmology 96, 1320–1324 (1989).
L. Kubecka and J. Jan, “Registration of Bimodal Retinal Images—Improving Modifications,” in Proceedings 26th Int. Conf. IEEE-EMBS (IEEE, San Francisco, 2004), pp. 1695–1698.
D. Kucera, “Segmentation of Multidimensional Image Data in Medicine,” PhD Thesis (TU, Brno, Czech Republic, 1996).
C. Y. Mardin and A. G. Jünemann, “The Diagnostic Value of Optic Nerve Imaging in Early Glaucoma,” Current Opinion in Ophthalmology 12, 100–104 (2001).
C. Y. Mardin, T. Hothorn, A. Peters, et al., “New Glaucoma Classification Method Based on Standard HRT Parameters by Bagging Classification Trees,” Journal of Glaucoma 12, 340–346 (2003).
G. Michelson and M. J. M. Groh, “Screening Models for Glaucoma,” Current Opinion in Ophthalmology 12, 105–111 (2001).
S. Miglior, E. Albe, M. Guareschi, et al., “Intraobserver and Interobserver Reproducibility in the Evaluation of Optic Disc Stereometric Parameters by Heidelberg Retina Tomograph,” Ophthalmology 109, 1072–1077 (2002).
F. S. Mikelberg, C. M. Parfitt, N. V. Swindale, et al., “Ability of the Heidelberg Retina Tomograph to Detect Early Glaucomatous Visual Field Loss,” Journal of Glaucoma 4, 242–247 (1995).
I. Pál, H. Niemann, and G. Michelson, Experiment Mil Mehrschichtigen Perzeptron-Netzen zur Vorverarbeitung und Merkmalgewinnung auf den SLDF-Perfusionsbildern der Netzhaut, Ed. by H. Evers, G. Glombitza, T. Lehman, and H.-P. Meinzer, 1999.
H. A. Quigley, “Number of People with Glaucoma Worldwide,” British Journal of Ophthalmology 80, 389–393 (1996).
Author information
Authors and Affiliations
Additional information
The text was submitted by the authors in English.
Heinrich Niemann Obtained the degree of Dipl.-Ing. in Electrical Engineering and Dr.-Ing. from Technical University Hannover, Germany. He worked with Fraunhofer Institut fur Informationsverarbeitung in Technik und Biologic, Karlsruhe, and with Fachhochschule Giessen in the department of Electrical Engineering. Since 1975 he has been Professor of Computer Science at the University of Erlangen-Nürnberg, where he was dean of the engineering faculty of the university from 1979–1981. From 1988–2000 he was head of the research group “Knowledge Processing” at the Bavarian Research Institute for Knowledge Based Systems (FORWISS). Since 1998 he has been a speaker of a “special research area” (SFB) entitled “Model-Based Analysis and Visualization of Complex Scenes and Sensor Data,” which is funded by the German Research Foundation (DFG). His fields of research are speech and image understanding and the application of artificial intelligence techniques in these fields. He is on the editorial board of Signal Processing, Pattern Recognition Letters, Pattern Recognition and Image Analysis, and Journal of Computing and Information Technology. He is the author or coauthor of 7 books and about 400 journal and conference contributions, as well as editor or coeditor of 24 proceedings volumes and special issues. He is a member of DAGM, ISCA, EURASIP, GI, IEEE, and VDE, and a Fellow of IAPR.
Radim Chrastek was born in 1972. He received an MS degree in electronics and telecommunication engineering from Brno University of Technology (BUT), Czech Republic, in 1996. From 1996 to 1998 he was with the Department of Biomedical Engineering, BUT. From 1998 to 2003 he was with the Bavarian Research Center for Knowledge-based Systems, Erlangen, Germany. He is currently working toward a PhD degree at the Chair for Pattern Recognition, Friedrich-Alexander-University of Erlangen-Nuremberg, Germany. His field of research is biomedical image processing. He is the author or coauthor of 16 journal and conference contributions.
Berthold Lausen was born in 1961. University of Dortmund (1987), Germany, 1990 PhD, 2003 Habilitation. Affiliation: Department of Medical Informatics, Biometry and Epidemiology, University of Erlangen-Nuremberg. Position: Head of the Biostatistics group Area of research: Biostatistics and Bio-informatics. Number of publications (monographs and articles): 51. Scientific societies: 1. German region of the International Biometric Society (DR-IBG), 2. Gesellschaft fur Klassifikation e.V. (GfKI), 3. Deutsche Gesellschaft fur Medizinische Inforrnatik, Biometrie und Epidemiologie (GMDS) e.V. 4. German Epidemiological Association (DAE) 5. The Royal Statistical Society 6. American Statistical Association. Awards 1987 Award of the Freundesgesellschaft der Universität Dortmund for the Diploma, 1990 Industrial award “Benno-Orenstein Preis 1989” by the O and K Orenstein and Koppel AG for the PhD-thesis.
Libor Kubecka was born in 1980, graduated from the Faculty of Electrical Engineering and Communication Brno University of Technology (FEEC BUT) in 2003, at present he is a PhD student at the Department of Biomedical Engineering of FEEC BUT; his research is oriented toward digital image processing, image detection, and image segmentation; he is author or coauthor of one journal paper and six conference abstracts; awarded Prize of the Dean of FEEC BUT for best diploma thesis.
Jiri Jan, born in 1941 in Brno (Czech Republic), MScEE (1963), PhD in radio-electronics (Brno UT 1969), scientific degree I (Czech Academy of Sciences, Prague 1986), Full Professor of Electronics (1991). Present orientation: digital signal and image processing, including applications in biomedical engineering. Publications: over 200 papers in journals and al conferences, books: Digital Signal Filtering, Analysis and Restoration (IEE Publ. London, UK 2000), also in Czech (1997, 2002); Medical Image Processing, Reconstruction and Restoration (CRC, USA 2005, in print). Recent international activities: Associate Editor of IEEE-Trans. on Biomedical Engineering (1996–2001). EURASIP central European liaison, since 1994. Czech Society for Biomedical Engineering-National Board member, since 1990. Member of Editorial Board, EURASIP Journal of Applied Signal Processing since 2000. Founding member of Engineering Academy of the Czech Republic (since 1994). Chair of international programme committee of biennial conference EUR-ASIP-BIOSIGNAL’xx (supported by EURASIP and IEEE-EMBS). Present position: Head, Dept. of Biomedical Engineering and Coordinator of Institute for Signal and Image Processing (ISIP), both of FEEC, Brno UT.
Christian Yahya Mardin received his MD degree from Friedrich-Alexander-University of Erlangen-Nürnberg in 1993. Since 1991 he has been with the Department of Ophthalmology of Friedrich-Alexander-University of Erlangen-Nurnberg. His fields of research are glaucoma, laser-scanning tomography and polarimetry, fluorescein angiography, and laser coagulation. He is a fellow of the European Board of Ophthalmology.
Georg Michelson was born in 1953. He received his MD degree at the Institute for Physiology, University of Regensburg in 1982. From 1982 to 1985 he was with the Institute for Anesthesiology, University Erlangen-Nürnberg, and since 1989 he has been with the Department of Ophthalmology, University Erlangen-Nürnberg. He has been an associate professor in ophthalmology since 1999. Since 2000, he has been head the of Outpatient Department of the Department of Ophthalmology in Erlangen, Germany. Since 1994, he has been a deputy speaker of a “special research area” (SFB) entitled “Glaukome einschließlich Pseudoex-foliations-Syndrom,” which is funded by the German Research Foundation (DFG). His fields of research are glaucoma, ocular circulation, and telemedicine. He is a member of Deutsche Ophthalmologische Gesellschaft and the American Academy of Ophthalmology. He is the author or coauthor of more than 60 articles and 6 patents. He is the editor of Online Atlas of Ophthalmology and Online Journal of Ocular Circulation. He was awarded the Axenfeld-Preis in 1997.
Rights and permissions
About this article
Cite this article
Niemann, H., Chrastek, R., Lausen, B. et al. Towards automated diagnostic evaluation of retina images. Pattern Recognit. Image Anal. 16, 671–676 (2006). https://doi.org/10.1134/S1054661806040146
Received:
Issue Date:
DOI: https://doi.org/10.1134/S1054661806040146