Abstract
Glaucoma is defined by morphologic changes in the optic nerve head and irreversible restriction of the visual field. Consequently, early glaucoma detection includes consideration of the morphology of the optic disc as well as measurements of the functional integrity of the visual system. Sensory tests with frequency doubling technology (FDT) perimetry and structural measurements with the Heidelberg Retina Tomograph (HRT) are able to deliver numerous parameters with diagnostic power for glaucoma detection. We aim to develop a diagnostic setup with classification rules for combined analysis of parameters from these techniques. For this task, “random forests” were learned on subjects of the Erlangen glaucoma registry with all information of the tests. With this automated classification method, we successfully combined the FDT and HRT parameters for glaucoma identification. The usage of separate training and test data from two independent study populations enables us to provide an adequately tested diagnostic tool for glaucoma detection in a heterogenous population. The feasibility of machine learning for medical diagnostic assistance could be demonstrated in an Internet-based application. The trained classifier can be used for telemedicine, diagnosis, and research via the World Wide Web.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Horn FK, Mardin CY, Bendschneider D, Junemann AG, Adler W, Tornow RP. Frequency doubling technique perimetry and spectral domain optical coherence tomography in patients with early glaucoma. Eye (Lond). 2011;25(1):17–29.
Johnson CA, Sample PA, Zangwill LM, Vasile CG, Cioffi GA, Liebmann JR, et al. Structure and function evaluation (SAFE): II. Comparison of optic disk and visual field characteristics. Am J Ophthalmol. 2003;135(2):148–54.
Anton A, Yamagishi N, Zangwill L, Sample PA, Weinreb RN. Mapping structural to functional damage in glaucoma with standard automated perimetry and confocal scanning laser ophthalmoscopy. Am J Ophthalmol. 1998;125(4):436–46.
Brigatti L, Hoffman D, Caprioli J. Neural networks to identify glaucoma with structural and functional measurements. Am J Ophthalmol. 1996;121(5):511–21.
Horn FK, Nguyen NX, Mardin CY, Junemann AG. Combined use of frequency doubling perimetry and polarimetric measurements of retinal nerve fiber layer in glaucoma detection. Am J Ophthalmol. 2003;135(2):160–8.
Mardin CY, Peters A, Horn F, Junemann AG, Lausen B. Improving glaucoma diagnosis by the combination of perimetry and HRT measurements. J Glaucoma. 2006;15(4):299–305.
Racette L, Chiou CY, Hao J, Bowd C, Goldbaum MH, Zangwill LM, et al. Combining functional and structural tests improves the diagnostic accuracy of relevance vector machine classifiers. J Glaucoma. 2010;19(3):167–75.
Bathija R, Zangwill L, Berry CC, Sample PA, Weinreb RN. Detection of early glaucomatous structural damage with confocal scanning laser tomography. J Glaucoma. 1998;7(2):121–7.
Ford BA, Artes PH, McCormick TA, Nicolela MT, LeBlanc RP, Chauhan BC. Comparison of data analysis tools for detection of glaucoma with the Heidelberg Retina Tomograph. Ophthalmology. 2003;110(6):1145–50.
Mikelberg FS, Parfitt CM, Swindale NV, Graham SL, Drance SM, Gosine R. Ability of the heidelberg retina tomograph to detect early glaucomatous visual field loss. J Glaucoma. 1995;4(4):242–7.
Wollstein G, Garway-Heath DF, Hitchings RA. Identification of early glaucoma cases with the scanning laser ophthalmoscope. Ophthalmology. 1998;105(8):1557–63.
Bowd C, Zangwill LM, Berry CC, Blumenthal EZ, Vasile C, Sanchez-Galeana C, et al. Detecting early glaucoma by assessment of retinal nerve fiber layer thickness and visual function. Invest Ophthalmol Vis Sci. 2001;42(9):1993–2003.
Wollstein G, Garway-Heath DF, Poinoosawmy D, Hitchings RA. Glaucomatous optic disc changes in the contralateral eye of unilateral normal pressure glaucoma patients. Ophthalmology. 2000;107(12):2267–71.
Quigley HA. Identification of glaucoma-related visual field abnormality with the screening protocol of frequency doubling technology. Am J Ophthalmol. 1998;125(6):819–29.
Burnstein Y, Ellish NJ, Magbalon M, Higginbotham EJ. Comparison of frequency doubling perimetry with Humphrey visual field analysis in a glaucoma practice. Am J Ophthalmol. 2000;129(3):328–33.
Stoutenbeek R, Heeg GP, Jansonius NM. Frequency doubling perimetry screening mode compared to the full-threshold mode. Ophthalmic Physiol Opt. 2004;24(6):493–7.
Jonas JB, Gusek GC, Naumann GO. Optic disc morphometry in chronic primary open-angle glaucoma. I. Morphometric intrapapillary characteristics. Graefes Arch Clin Exp Ophthalmol. 1988;226(6):522–30.
Breiman L. Bagging predictors. Mach Learn. 1996;24:123–40.
Lauterwald F, Neumann CP, Lenz R, Jünemann AG, Mardin CY, Meyer-Wegener K, et al. The Erlangen Glaucoma registry: a scientific database for longitudinal analysis of glaucoma. Tech Rep. 2012;CS-2011(2):1–9. ISSN 2191-5008.
Jonas JB, Budde WM, Panda-Jonas S. Ophthalmoscopic evaluation of the optic nerve head. Surv Ophthalmol. 1999;43(4):293–320.
Horn FK, Brenning A, Junemann AG, Lausen B. Glaucoma detection with frequency doubling perimetry and short-wavelength perimetry. J Glaucoma. 2007;16(4):363–71.
Casson R, James B, Rubinstein A, Ali H. Clinical comparison of frequency doubling technology perimetry and Humphrey perimetry. Br J Ophthalmol. 2001;85(3):360–2.
Johnson CA, Samuels SJ. Screening for glaucomatous visual field loss with frequency-doubling perimetry. Invest Ophthalmol Vis Sci. 1997;38(2):413–25.
Adams CW, Bullimore MA, Wall M, Fingeret M, Johnson CA. Normal aging effects for frequency doubling technology perimetry. Optom Vis Sci. 1999;76(8):582–7.
Horn FK, Wakili N, Junemann AM, Korth M. Testing for glaucoma with frequency-doubling perimetry in normals, ocular hypertensives, and glaucoma patients. Graefes Arch Clin Exp Ophthalmol. 2002;240(8):658–65.
Hawker MJ, Vernon SA, Ainsworth G. Specificity of the Heidelberg Retina Tomograph’s diagnostic algorithms in a normal elderly population: the Bridlington Eye Assessment Project. Ophthalmology. 2006;113(5):778–85.
Horn FK, Lammer R, Mardin CY, Junemann AG, Michelson G, Lausen B, et al. Combined evaluation of frequency doubling technology perimetry and scanning laser ophthalmoscopy for glaucoma detection using automated classification. J Glaucoma. 2012;21(1):27–34.
Burk R. Laser Scanning Tomographé: Interpretation der Ausdrucke des Heidelberg Retina Tomographen HRT II [Laser scanning tomography: interpretation of the HRT II printout]. Z prakt Augenheilkd. 2001;22:183–90.
Mardin CY, Horn FK. Influence of optic disc size on the sensitivity of the Heidelberg Retina Tomograph. Graefes Arch Clin Exp Ophthalmol. 1998;236(9):641–5.
Ramrattan RS, Wolfs RC, Jonas JB, Hofman A, de Jong PT. Determinants of optic disc characteristics in a general population: the Rotterdam Study. Ophthalmology. 1999;106(8):1588–96.
Mardin CY, Hothorn T, Peters A, Junemann AG, Nguyen NX, Lausen B. New glaucoma classification method based on standard Heidelberg Retina Tomograph parameters by bagging classification trees. J Glaucoma. 2003;12(4):340–6.
Hothorn T, Lausen B. Bagging tree classifiers for laser scanning images: a data- and simulation-based strategy. Artif Intell Med. 2003;27(1):65–79.
Adler W, Peters A, Lausen B. Comparison of classifiers applied to confocal scanning laser ophthalmoscopy data. Methods Inf Med. 2008;47(1):38–46.
Liaw A, Wiener M. Classification and regression by random forest. R News. 2002;2:18–22.
Borg I, Groenen P. Modern multidimensional scaling: theory and applications. New York: Springer; 1997. p. 207–12.
Iester M, Traverso CE, De Feo F, Sanna G, Altieri M, Vittone P, et al. Correlation between frequency doubling technology and heidelberg retina tomograph. J Glaucoma. 2005;14(5):368–74.
Kunimatsu S, Tomita G, Araie M, Aihara M, Suzuki Y, Iwase A, et al. Frequency doubling technology and scanning laser tomography in eyes with generalized enlargement of optic disc cupping. J Glaucoma. 2005;14(4):280–7.
Robin TA, Muller A, Rait J, Keeffe JE, Taylor HR, Mukesh BN. Performance of community-based glaucoma screening using Frequency Doubling Technology and Heidelberg Retinal Tomography. Ophthalmic Epidemiol. 2005;12(3):167–78.
Shah NN, Bowd C, Medeiros FA, Weinreb RN, Sample PA, Hoffmann EM, et al. Combining structural and functional testing for detection of glaucoma. Ophthalmology. 2006;113(9):1593–602.
Sample PA, Bosworth CF, Blumenthal EZ, Girkin C, Weinreb RN. Visual function-specific perimetry for indirect comparison of different ganglion cell populations in glaucoma. Invest Ophthalmol Vis Sci. 2000;41(7):1783–90.
Spry PG, Johnson CA, Mansberger SL, Cioffi GA. Psychophysical investigation of ganglion cell loss in early glaucoma. J Glaucoma. 2005;14(1):11–9.
Paczka JA, Friedman DS, Quigley HA, Barron Y, Vitale S. Diagnostic capabilities of frequency-doubling technology, scanning laser polarimetry, and nerve fiber layer photographs to distinguish glaucomatous damage. Am J Ophthalmol. 2001;131(2):188–97.
Landers JA, Goldberg I, Graham SL. Comparison of clinical optic disc assessment with tests of early visual field loss. Clin Experiment Ophthalmol. 2002;30(5):338–42.
Agarwal HC, Gulati V, Sihota R. The normal optic nerve head on Heidelberg Retina Tomograph II. Indian J Ophthalmol. 2003;51(1):25–33.
Uysal Y, Bayer A, Erdurman C, Kilic S. Sensitivity and specificity of Heidelberg Retinal Tomography II parameters in detecting early and moderate glaucomatous damage: effect of disc size. Clin Experiment Ophthalmol. 2007;35(2):113–8.
Hoesl LM, Mardin CY, Horn FK, Juenemann AGM, Laemmer R. Influence of glaucomatous damage and optic disc size on glaucoma detection by scanning laser tomography. J Glaucoma. 2009;18(5):385–9.
Yip LW, Mikelberg FS. A comparison of the glaucoma probability score to earlier heidelberg retina tomograph data analysis tools in classifying normal and glaucoma patients. J Glaucoma. 2008;17(7):513–6.
Medeiros FA, Zangwill LM, Bowd C, Sample PA, Weinreb RN. Influence of disease severity and optic disc size on the diagnostic performance of imaging instruments in glaucoma. Invest Ophthalmol Vis Sci. 2006;47(3):1008–15.
Bowd C, Chan K, Zangwill LM, Goldbaum MH, Lee T-W, Sejnowski TJ, et al. Comparing neural networks and linear discriminant functions for glaucoma detection using confocal scanning laser ophthalmoscopy of the optic disc. Invest Ophthalmol Vis Sci. 2002;43(11):3444–54.
Bowd C, Lee I, Goldbaum MH, Balasubramanian M, Medeiros FA, Zangwill LM, et al. Predicting glaucomatous progression in glaucoma suspect eyes using relevance vector machine classifiers for combined structural and functional measurements. Invest Ophthalmol Vis Sci. 2012;53(4):2382–9.
Acknowledgments
The authors thank Sylvia Rühl for skilful technical assistance; Professor G. Michelson, Professor A. Jünemann, Professor C. Mardin, and Dr. Lämmer for classification of the patients; Dipl. Ing. Dr. F. Lauterwald for implementation of the database; and Professor B. Lausen for help in statistical questions. The development of the “Erlangen Glaucoma Registry” was supported by DFG grant SFB 539. The authors have no commercial interest in the equipment used in this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Horn, F.K., Adler, W. (2015). Multimodal Screening of Glaucoma Improves Sensitivity and Specificity. In: Michelson, G. (eds) Teleophthalmology in Preventive Medicine. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-44975-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-662-44975-2_3
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-44974-5
Online ISBN: 978-3-662-44975-2
eBook Packages: MedicineMedicine (R0)