Machine learning classifiers in glaucoma

Optometry and Vision Science

Volumn 85, Issue 6, 2008, Pages 396-405

  Bowd, Christopher ^a   Goldbaum, Michael H ^a,b  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b VETERANS AFFAIRS MEDICAL CENTER   (United States)

Author keywords

Classification; Diagnosis; Glaucoma; Machine learning; Neural network; Optic disc; Perimetry; Retinal nerve fiber layer

Indexed keywords

CLASSIFICATION; GLAUCOMA; MACHINE LEARNING; OPTIC DISC; PERIMETRY; RETINAL NERVE FIBER LAYER;

CLASSIFIERS; EDUCATION; MACHINE DESIGN; NEURAL NETWORKS; OPHTHALMOLOGY; OPTICAL IMAGE STORAGE; ROBOT LEARNING;

LEARNING ALGORITHMS;

DIAGNOSTIC ACCURACY; DISEASE CLASSIFICATION; GLAUCOMA; HUMAN; INTRAOCULAR PRESSURE; OPHTHALMOSCOPE; OPTIC NERVE DISEASE; OPTICAL COHERENCE TOMOGRAPHY; POLARIMETRY; PREDICTION; PRIORITY JOURNAL; RECEIVER OPERATING CHARACTERISTIC; REVIEW; ROC CURVE; SENSITIVITY AND SPECIFICITY; SUPPORT VECTOR MACHINE; VISION; VISUAL FIELD; ARTIFICIAL INTELLIGENCE; CLASSIFICATION; NERVE CELL NETWORK; PATHOPHYSIOLOGY; PHYSIOLOGY; PREDICTION AND FORECASTING; REFERENCE VALUE; REPRODUCIBILITY;

ARTIFICIAL INTELLIGENCE; GLAUCOMA; HUMANS; NERVE NET; PREDICTIVE VALUE OF TESTS; REFERENCE VALUES; REPRODUCIBILITY OF RESULTS; SENSITIVITY AND SPECIFICITY; VISION;

EID: 48549083993     PISSN: 10405488     EISSN: None     Source Type: Journal    
DOI: 10.1097/OPX.0b013e3181783ab6     Document Type: Review

References (66)

1. Rosenblatt F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 1958;65:386-408.
2. Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature 1986;323:533-6.
3. Burges CJ. A tutorial on support vector machines for pattern recognition. Data Mining Knowledge Discovery, vol 2. Boston, MA: Kluver Academic Publishers; 1998:121-67.
4. Vapnik VN. The Nature of Statistical Learning Theory, 2nd ed. New York: Springer; 2000.
5. Vapnik VN. Statistical Learning Theory. New York: Wiley; 1998.
6. Becker S. Unsupervised learning procedures for neural networks. Int J Neural Syst 1991;1/2:17-33. Available at: http://www.science. mcmaster.ca/psychology/becker/papers/becker-ijns91.pdf. Accessed February 14, 2008.
7. Kohonen T. Self-organized formation of topologically correct feature maps. Biol Cybern 1982;43:59-69.
8. Kohonen T. Self-Organizing Maps, 3rd ed. New York: Springer; 2001.
9. Drucker H, Cortes C, Jackel LD, LeCun Y, Vapnik V. Boosting and other ensemble methods. Neural Comput 1994;6:1289-301.
10. Swets JA. Measuring the accuracy of diagnostic systems. Science 1988;240:1285-93.
11. DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a non-parametric approach. Biometrics 1988;44:837-45.
12. Goldbaum MH, Sample PA, White H,Weinreb RN. Discrimination of normal and glaucomatous visual fields by neural network. Invest Ophthalmol Vis Sci 1990;31(suppl):503.
13. Goldbaum MH, Sample PA, White H, Colt B, Raphaelian P, Fechtner RD, Weinreb RN. Interpretation of automated perimetry for glaucoma by neural network. Invest Ophthalmol Vis Sci 1994;35: 3362-73.
14. Kelman SE, Perell HF, D'Autrechy L, Scott RJ. A neural network can differentiate glaucoma and optic neuropathy visual fields through pattern recognition. In: Mills RP, Heijl A, eds. Perimetry Update 1990/1991: Proceedings of the Sixth International Perimetric Society Meeting, Malmo, Sweden, June 17-20, 1990. New York: Kugler Publications; 1991:287-90.
15. Nagata S, Kani K, Sugiyama A. A computer assisted visual field diagnosis system using neural networks. In: Mills RP, Heijl A, eds. Perimetry Update 1990/1991: Proceedings of the Sixth International Perimetric Society Meeting, Malmo, Sweden, June 17-20, 1990. New York: Kugler Publications; 1991:291-5.
16. Goldbaum MH, Sample PA, Chan K, Williams J, Lee TW, Blumenthal E, Girkin CA, Zangwill LM, Bowd C, Sejnowski T, Weinreb RN. Comparing machine learning classifiers for diagnosing glaucoma from standard automated perimetry. Invest Ophthalmol Vis Sci 2002;43:162-9.
17. Tresp V. Mixtures of Gaussian processes. In: Leen TK, Dietterich TG, Tresp V, eds. Advances in Neural Information Processing Systems 13. Cambridge, MA: MIT Press; 2001:654-60.
18. Tresp V. Committee machines. In: Hu YH, Hwang J-N, eds. Handbook of Neural Network Signal Processing. Boca Raton, FL: CRC Press; 2002. Chap 3.
19. Lietman T, Eng J, Katz J, Quigley HA. Neural networks for visual field analysis: how do they compare with other algorithms? J Glaucoma 1999;8:77-80.
20. Advanced Glaucoma Intervention Study Group. Advanced glaucoma intervention study. 2. Visual field test scoring and reliability. Ophthalmology 1994;101:1445-55.
21. Schulzer M. Intraocular pressure reduction in normal-tension glaucoma patients. The normal tension glaucoma study group. Ophthalmology 1992;99:1468-70.
22. Bizios D, Heijl A, Bengtsson B. Trained artificial neural network for glaucoma diagnosis using visual field data: a comparison with conventional algorithms. J Glaucoma 2007;16:20-8.
23. Bengtsson B, Bizios D, Heijl A. Effects of input data on the performance of a neural network in distinguishing normal and glaucomatous visual fields. Invest Ophthalmol Vis Sci 2005;46:3730-6.
24. Henson DB, Spenceley SE, Bull DR. Spatial classification of glaucomatous visual field loss. Br J Ophthalmol 1996;80:526-31.
25. Aulhorn E, Karmeyer H. Frequency distribution in early glaucomatous visual field defects. Doc Ophthalmol Proc Ser 1977;14:75-83.
26. Sample PA, Chan K, Boden C, Lee TW, Blumenthal EZ, Weinreb RN, Bernd A, Pascual J, Hao J, Sejnowski T, Goldbaum MH. Using unsupervised learning with variational bayesian mixture of factor analysis to identify patterns of glaucomatous visual field defects. Invest Opthalmol Vis Sci 2004;45:2596-605.
27. Chan K, Lee TW, Sejnowski TJ. Variational learning of clusters of undercomplete non-symmetric independent components. J Mach Learn Res 2003;3:99-114.
28. Goldbaum MH. Unsupervised learning with independent component analysis can identify patterns of glaucomatous visual field defects. Trans Am Ophthalmol Soc 2005;103:270-80.
29. Goldbaum MH, Sample PA, Zhang Z, Chan K, Hao J, Lee TW, Boden C, Bowd C, Bourne R, Zangwill L, Sejnowski T, Spinak D, Weinreb RN. Using unsupervised learning with independent component analysis to identify patterns of glaucomatous visual field defects. Invest Ophthalmol Vis Sci 2005;46:3676-83.
30. Keating D, Mutlukan E, Evans A, McGarvie J, Damato B. A back propagation neural network for the classification of visual field data. Phys Med Biol 1993;38:1263-70.
31. Madsen EM, Yolton RL. Demonstration of a neural network expert system for recognition of glaucomatous visual field changes. Mil Med 1994;159:553-7.
32. Mutlukan E, Keating D. Visual field interpretation with a personal computer based neural network. Eye 1994;8(Pt 3):321-3.
33. Spenceley SE, Henson DB, Bull DR. Visual field analysis using artificial neural networks. Ophthalmic Physiol Opt 1994;14:239-48.
34. Chan K, Lee TW, Sample PA, Goldbaum MH, Weinreb RN, Sejnowski TJ. Comparison of machine learning and traditional classifiers in glaucoma diagnosis. IEEE Trans Biomed Eng 2002;49: 963-74.
35. Goldbaum MH, Sample PA, Zangwill LM, Bowd C, Boden C, Lee TW, Zhang Z, Hao J, Sejnowski T, Weinreb RN. Probability of glaucoma determined from standard automated perimetry and from optic disc topography using relevance vector machine classifiers [abstract]. Invest Ophthalmol Vis Sci 2004;45:E-Abstract 2137.
36. Tucker A, Vinciotti V, Liu X, Garway-Heath D. A spatio-temporal Bayesian network classifier for understanding visual field deterioration. Artif Intell Med 2005;34:163-77.
37. Goldbaum MH, Sample PA, Zhang Z, Boden C, Lee TW, Hao J, Zangwill LM, Putthividhya P, Spinak DJ, Weinreb RN. Learning manifolds transformation for classification of standard automated perimetry [abstract]. Invest Ophthalmol Vis Sci 2005;46:E-Abstract 3733.
38. Dreher AW, Goldbaum MH, Cote BL, Hart WE, Bailey ED. Neural network classification of glaucoma using peripapillary nerve fiber thickness measured by scanning laser tomography. Invest Ophthalmol Vis Sci 1993;34(suppl):763.
39. Brigatti L, Hoffman D, Caprioli J. Neural networks to identify glaucoma with structural and functional measurements. Am J Ophthalmol 1996;121:511-21.
40. Uchida H, Brigatti L, Caprioli J. Detection of structural damage from glaucoma with confocal laser image analysis. Invest Ophthalmol Vis Sci 1996;37:2393-401.
41. Parfitt CM, Mikelberg FS, Swindale NV. The detection of glaucoma using an artificial neural network. In: 17th Annual Conference in Engineering in Medicine and Biology Society. Montreal, QC, 20-23 September 1995, vol 1. Piscataway, NJ: IEEE Press; 1995.
42. Caudill M, Butler C. Naturally Intelligent Systems. Cambridge, MA: MIT Press; 1990.
43. Bowd C, Chan K, Zangwill LM, Goldbaum MH, Lee TW, Sejnowski TJ, Weinreb RN. Comparing neural networks and linear discriminant functions for glaucoma detection using confocal scanning laser ophthalmoscopy of the optic disc. Invest Ophthalmol Vis Sci 2002;43:3444-54.
44. Bowd C, Medeiros FA, Zhang Z, Zangwill LM, Hao J, Lee TW, Sejnowski TJ, Weinreb RN, Goldbaum MH. Relevance vector machine and support vector machine classifier analysis of scanning laser polarimetry retinal nerve fiber layer measurements. Invest Ophthalmol Vis Sci 2005;46:1322-9.
45. Huang ML, Chen HY. Development and comparison of automated classifiers for glaucoma diagnosis using Stratus optical coherence tomography. Invest Ophthalmol Vis Sci 2005;46:4121-9.
46. Huang ML, Chen HY, Lin JC. Rule extraction for glaucoma detection with summary data from StratusOCT. Invest Ophthalmol Vis Sci 2007;48:244-50.
47. Burgansky-Eliash Z, Wollstein G, Chu T, Ramsey JD, Glymour C, Noecker RJ, Ishikawa H, Schuman JS. Optical coherence tomography machine learning classifiers for glaucoma detection: a preliminary study. Invest Ophthalmol Vis Sci 2005;46:4147-52.
48. Swindale NV, Stjepanovic G, Chin A, Mikelberg FS. Automated analysis of normal and glaucomatous optic nerve head topography images. Invest Ophthalmol Vis Sci 2000;41:1730-42.
49. Park JM, Reed J, Zhou Q. Active feature selection in optic nerve data using support vector machine. In: Proceedings of the 2002 International Joint Conference Neural Networks, Honolulu, HI, May 12-17, 2002. Piscataway, NJ: IEEE Press; 2002:1178-82.
50. Hothorn T, Lausen B. Bagging tree classifiers for laser scanning images: a data-and simulation-based strategy. Artif Intell Med 2003; 27:65-79.
51. 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;12:340-6.
52. Pluhacek F, Pospisil J. Statistical and neural net methods for automatic glaucoma diagnosis determination. Cent Eur J Phys 2004;2: 12-24.
53. Zangwill LM, Chan K, Bowd C, Hao J, Lee TW, Weinreb RN, Sejnowski TJ, Goldbaum MH. Heidelberg retina tomograph measurements of the optic disc and parapapillary retina for detecting glaucoma analyzed by machine learning classifiers. Invest Ophthalmol Vis Sci 2004;45:3144-51.
54. Lee TW, Hao J, Bowd C, Zhang Z, Putthividhya D, Zangwill LM, Weinreb RN, Goldbaum MH. Learning low dimensional manifold representation of scanning laser polarimetry data from healthy and glaucomatous eyes [abstract]. Invest Ophthalmol Vis Sci 2005;46:E-Abstract 2529.
55. Bowd C, Chiou C, Hao J, Racette L, Zangwill LM, Medeiros FA, Lee TW, Weinreb RN, Goldbaum MH, Sample PA. Relevance vector machine for combining HRT II and SWAP results for discriminating between healthy and glaucoma eyes. Acta Ophthalmol Scand 2006; 84:569.
56. Mardin CY, Peters A, Horn F, Junemann AG, Lausen B. Improving glaucoma diagnosis by the combination of perimetry and HRT measurements. J Glaucoma 2006;15:299-305.
57. Yu J, Abidi SS, Artes P, McIntyre A, Heywood M. Diagnostic support for glaucoma using retinal images: a hybrid image analysis and data mining approach. Stud Health Technol Inform 2005;116: 187-92.
58. Bowd C, Hao J, Tavares IT, Medeiros FA, Zangwill LM, Lee T-W, Sample PA, Weinreb RN, Goldbaum MH. Bayesian machine learning classifiers for combining structural and functional measurements to classify healthy and glaucomatous eyes. Invest Ophthalmol Vis Sci 2008;49:945-53.
59. Brigatti L, Nouri-Mahdavi K, Weitzman M, Caprioli J. Automatic detection of glaucomatous visual field progression with neural networks. Arch Ophthalmol 1997;115:725-8.
60. Sample PA, Goldbaum MH, Chan K, Boden C, Lee TW, Vasile C, Boehm AG, SejnowskiT, Johnson CA, Weinreb RN. Using machine learning classifiers to identify glaucomatous change earlier in standard visual fields. Invest Ophthalmol Vis Sci 2002;43:2660-5.
61. Johnson CA, Sample PA, Cioffi GA, Liebmann JR, Weinreb RN. Structure and function evaluation (SAFE): I. Criteria for glaucomatous visual field loss using standard automated perimetry (SAP) and short wavelength automated perimetry (SWAP). Am J Ophthalmol 2002;134:177-85.
62. Sample PA, Boden C, Zhang Z, Pascual J, Lee TW, Zangwill LM, Weinreb RN, Crowston JG, Hoffmann EM, Medeiros FA, Sejnowski T, Goldbaum M. Unsupervised machine learning with independent component analysis to identify areas of progression in glaucomatous visual fields. Invest Ophthalmol Vis Sci 2005;46: 3684-92.
63. Boden C, Blumenthal EZ, Pascual J, McEwan G, Weinreb RN, Medeiros F, Sample PA. Patterns of glaucomatous visual field progression identified by three progression criteria. Am J Ophthalmol 2004;138:1029-36.
64. Leske MC, Heijl A, Hyman L, Bengtsson B. Early manifest glaucoma trial: design and baseline data. Ophthalmology 1999;106:2144-53.
65. Bowd C, Zangwill LM, Medeiros FA, Hao J, Chan K, Lee TW, Sejnowski TJ, Goldbaum MH, Sample PA, Crowston JG, Weinreb RN. Confocal scanning laser ophthalmoscopy classifiers and stereophotograph evaluation for prediction of visual field abnormalities in glaucoma-suspect eyes. Invest Ophthalmol Vis Sci 2004;45: 2255-62.
66. Kozak I, Sample PA, Hao J, Freeman WR, Weinreb RN, Lee TW, Goldbaum MH. Machine learning classifiers detect subtle field defects in eyes of HIV individuals. Trans Am Opthalmol Soc 2007;105: 111-8.