Advances in Biomedical Informatics pp 123-160 | Cite as
Machine Learning Applied to Optometry Data
- 1 Citations
- 783 Downloads
Abstract
Optometry is the primary health care of the eye and visual system. It involves detecting defects in vision, signs of injury, ocular diseases as well as problems with general health that produce side effects in the eyes. Myopia, presbyopia, glaucoma or diabetic retinopathy are some examples of conditions that optometrists usually diagnose and treat. Moreover, there is another condition that we have all experienced once in a while, especially if we work with computers or have been exposed to smoke or wind. Dry eye syndrome (DES) is a hidden multifactorial disease related with the quality and quantity of tears. It causes discomfort and could lead to severe visual problems. In this chapter, we explain how machine learning techniques can be applied in some DES medical tests in order to produce an objective, repeatable and automatic diagnosis. The results of our experiments show that the proposed methodologies behave like the experts so that they can be applied in the daily practice.
Keywords
Optometry data Dry eye syndrome Image analysis Feature selection Classification RegressionNotes
Acknowledgements
This work has been partially funded by the Ministerio de Economía y Competitividad of Spain (project DPI2015-69948-R). Beatriz Remeseiro acknowledges the support of the Ministerio de Economía y Competitividad of the Spanish Government under Juan de la Cierva Program (ref. FJCI-2014-21194).
References
- 1.Paulsen, A.J., Cruickshanks, K.J., Fischer, M.E., Huang, G., Klein, B.E.K., Klein, R., Dalton, D.S.: Dry eye in the beaver dam offspring study: prevalence, risk factors, and health-related quality of life. Am. J. Ophthalmol. 157(4), 799–806 (2014)CrossRefGoogle Scholar
- 2.Gayton, J.L.: Etiology, prevalence, and treatment of dry eye disease. Clin. Ophthalmol. 3, 405–412 (2009)CrossRefGoogle Scholar
- 3.Yu, J., Asche, C.V., Fairchild, C.J.: The economic burden of dry eye disease in the united states: a decision tree analysis. Cornea 30(4), 379–387 (2011)CrossRefGoogle Scholar
- 4.Lemp, M.A., Baudouin, C., Baum, J., et al.: The definition and classification of dry eye disease: report of the definition and classification subcommittee of the international dry eye workshop. Ocul. Surf. 5(2), B75–B92 (2007)Google Scholar
- 5.Craig, J.P., Tomlinson, A.: Importance of the lipid layer in human tear film stability and evaporation. Optom. Vis. Sci. 74, 8–13 (1997)CrossRefGoogle Scholar
- 6.Guillon, J.P.: Non-invasive tearscope plus routine for contact lens fitting. Contact Lens and Anterior Eye 21(Suppl 1), 31–40 (1998)CrossRefGoogle Scholar
- 7.Korb, D.R.: The Tear Film: Structure, Function, and Clinical Examination. Elsevier Health Sciences, Amsterdam (2002)Google Scholar
- 8.Nichols, J.J., Nichols, K.K., Puent, B., Saracino, M., Mitchell, G.L.: Evaluation of tear film interference patterns and measures of tear break-up time. Optom. Vis. Sci. 79(6), 363–369 (2002)CrossRefGoogle Scholar
- 9.Calvo, D., Mosquera, A., Penas, M., García-Resúa, C., Remeseiro, B.: Color texture analysis for tear film classification: a preliminary study. Int. Conf. Image Anal. Recogn. 6112, 388–397 (2010)Google Scholar
- 10.Ramos, L., Penas, M., Remeseiro, B., Mosquera, A., Barreira, N., Yebra-Pimentel, E.: Texture and color analysis for the automatic classification of the eye lipid layer. Int. Work Conf. Artif. Neural Netw. 6692, 66–73 (2011)Google Scholar
- 11.Remeseiro, B., Penas, M., Mosquera, A., Novo, J., Penedo, M.G., Yebra-Pimentel, E.: Statistical comparison of classifiers applied to the interferential tear film lipid layer automatic classification. Comput. Math. Methods Med. 2012, 1–10 (2012)CrossRefzbMATHGoogle Scholar
- 12.Remeseiro, B., Penas, M., Barreira, N., Mosquera, A., Novo, J., García-Resúa, C.: Automatic classification of the interferential tear film lipid layer using colour texture analysis. Comput. Methods Programs Biomed. 111, 93–103 (2013)CrossRefGoogle Scholar
- 13.Remeseiro, B., Bolón-Canedo, V., Peteiro-Barral, D., Alonso-Betanzos, A., Guijarro-Berdinas, B., Mosquera, A., Penedo, M.G., Sánchez-Marono, N.: A methodology for improving tear film lipid layer classification. IEEE J. Biomed. Health Inf. 18(4), 1485–1493 (2014)Google Scholar
- 14.Remeseiro, B., Mosquera, A., Penedo, M.G., Garca-Resúa, C.: Tear film maps based on the lipid interference patterns. 6th Int. Conf. Agents Artif. Int. 1, 732–739 (2014)Google Scholar
- 15.Remeseiro, B., Mosquera, A., Penedo, M.G.: CASDES: a computer-aided system to support dry eye diagnosis based on tear film maps. IEEE J. Biomed. Health Inf. 20(3), 936–943 (2016)CrossRefGoogle Scholar
- 16.Remeseiro, B., Barreira, N., Garca-Resúa, C., Lira, M., Giráldez, M.J., Yebra-Pimentel, E., Penedo, M.G.: iDEAS: a web-based system for dry eye assessment. Comput. Methods Prog. Biomed. 130, 186–197 (2016)CrossRefGoogle Scholar
- 17.González-Domínguez, J., Remeseiro, B., Martín, M.J.: Acceleration of tear film map definition on multicore systems. Procedia Comput. Sci. 80, 41–51 (2016)Google Scholar
- 18.González-Domínguez, J., Remeseiro, B., Martín, M.J.: Parallel definition of tear film maps on distributed-memory clusters for the support of dry eye diagnosis. Comput. Methods Programs Biomed. 139, 51–60 (2017)Google Scholar
- 19.Méndez, R., Remeseiro, B., Peteiro-Barral, D., Penedo, M.G.: Evaluation of class binarization and feature selection in tear film classification using topsis. Agents Artif. Intell. Revised Selected Papers ICAART 2013 2014(449), 179–193 (2014)Google Scholar
- 20.Peteiro-Barral, D., Remeseiro, B., Méndez, R., Penedo, M.G.: Evaluation of an automatic dry eye test using MCDM methods and rank correlation. Med. Biol. Eng. Comput. 55(4), 527–536 (2017)CrossRefGoogle Scholar
- 21.VOPTICAL_I1, VARPA optical dataset acquired and annotated by optometrists from the Optometry Service of the University of Santiago de Compostela, Spain (2012)Google Scholar
- 22.Russ, J.C.: The Image Processing Handbook, 3rd edn. CRC Press Inc, Boca Raton, FL, USA (1999)zbMATHGoogle Scholar
- 23.McLaren, K.: The development of the CIE 1976 (L*a*b) uniform colour-space and colour-difference formula. J. Soc. Dyers Colour. 92(9), 338–341 (1976)CrossRefGoogle Scholar
- 24.Bradski, G.: OpenCV. Dr. Dobb’s J Softw. Tools 25, 120–126 (2000)Google Scholar
- 25.Haralick, R.M., Shanmugam, K., Dinstein, I.: Texture features for image classification. IEEE Trans. Sys. Man Cybern. 3, 610–621 (1973)CrossRefGoogle Scholar
- 26.Furnkranz, J.: Round robin ensembles. Int. Data Anal. 7(5), 385–403 (2003)Google Scholar
- 27.Dietterich, T.G., Bakiri, G.: Solving multiclass learning problems via error-correcting output codes. J. Artif. Intell. Res. 2, 263–286 (1995)zbMATHGoogle Scholar
- 28.Allwein, E.L., Schapire, R.E., Singer, Y.: Reducing multiclass to binary: a unifying approach for margin classifiers. J. Mach. Learn. Res. 1, 113–141 (2001)zbMATHMathSciNetGoogle Scholar
- 29.Manning, C.D., Raghavan, P., Schütze, H.: Introduction to Information Retrieval, vol. 1. Cambridge University Press, Cambridge (2008)CrossRefzbMATHGoogle Scholar
- 30.Loughrey, J., Cunningham, P.: Overfitting in wrapper-based feature subset selection: the harder you try the worse it gets. Res. Dev. Intell. Sys. XXI, 2005, 33–43 (2005)Google Scholar
- 31.Guyon, I., Gunn, S., Nikravesh, M., Zadeh, L.: Feature Extraction: Foundations and Applications. Springer Verlag, Berlin (2006)CrossRefzbMATHGoogle Scholar
- 32.Hall, M.A.: Correlation-based feature selection for machine learning. PhD thesis, The University of Waikato (1999)Google Scholar
- 33.Dash, M., Liu, H.: Consistency-based search in feature selection. Artif. Intell. 151(1–2), 155–176 (2003)CrossRefzbMATHMathSciNetGoogle Scholar
- 34.Zhao, Z., Liu, H.: Searching for interacting features. Proceedings of the 20th international joint conference on Artificial intelligence, 1156–1161 (2007)Google Scholar
- 35.Mitchell, T.M.: Machine Learning. McGraw-Hill, Boston (1995)zbMATHGoogle Scholar
- 36.Friedman, J.H.: Regularized discriminant analysis. J. Am. Stat. Assoc. 84, 165–175 (1989)CrossRefMathSciNetGoogle Scholar
- 37.Jensen, F.V.: An Introduction to Bayesian Networks, vol. 210. UCL press, London (1996)Google Scholar
- 38.Murthy, S.K.: Automatic construction of decision trees from data: a multi-disciplinary survey. Data Min. Knowl. Disc. 2, 345–389 (1998)CrossRefGoogle Scholar
- 39.Burges, C.J.C.: A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Disc. 2, 121–167 (1998)CrossRefGoogle Scholar
- 40.Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65(6), 386 (1958)CrossRefGoogle Scholar
- 41.Fernandez-Caballero, J.C., Martnez, F.J., Hervás, C., Gutiérrez, P.A.: Sensitivity versus accuracy in multiclass problems using memetic pareto evolutionary neural networks. IEEE Trans. Neural Networks 21(5), 750–770 (2010)CrossRefGoogle Scholar
- 42.Hwang, C.L., Yoon, K.: Multiple Attribute Decision Making: Methods and Applications, vol. 13. Springer-Verlag, New York (1981)CrossRefzbMATHGoogle Scholar
- 43.Kuo, Y., Yang, T., Huang, G.W.: The use of grey relational analysis in solving multiple attribute decision-making problems. Comput. Ind. Eng. 55(1), 80–93 (2008)CrossRefGoogle Scholar
- 44.Opricovic, S.: Multicriteria optimization of civil engineering systems. Fac. Civil Eng. Belgrade 2(1), 5–21 (1998)MathSciNetGoogle Scholar
- 45.Gautheir, T.D.: Detecting trends using spearman’s rank correlation coefficient. Environ. Forensics 2(4), 359–362 (2001)CrossRefGoogle Scholar
- 46.Chang, C., Lin, C.: LIBSVM: A library for support vector machines. ACM Trans. on Intell. Sys. Tech. 2, 1–27, http://www.csie.ntu.edu.tw/cjlin/libsvm (2011)
- 47.Bramer, M.: Principles of Data Mining, vol. 180. Springer, London (2007)zbMATHGoogle Scholar
- 48.Yoneda, T., Sumi, T., Takahashi, A., Hoshikawa, Y., Kobayashi, M., Fukushima, A.: Automated hyperemia analysis software: reliability and reproducibility in healthy subjects. Jpn. J. Ophthalmol. 56(1), 1–7 (2012)CrossRefGoogle Scholar
- 49.Rodriguez, J.D., Johnston, P.R., Ousler, G.W., Smith, L.M., Abelson, M.B.: Automated grading system for evaluation of ocular redness associated with dry eye. Clin. Ophthalmol. 7, 1197 (2013)CrossRefGoogle Scholar
- 50.Wu, S., Hong, J., Tian, L., Cui, X., Sun, X., Xu, J.: Assessment of bulbar redness with a newly developed keratograph. Optom. Vis. Sci. 92(8), 892–899 (2015)CrossRefGoogle Scholar
- 51.Tort, M., Ornberg, R., Lay, B., Danno, R., Soong, F., Salapatek, A.: Development of an objective assessment of conjunctival hyperemia elicited via Conjunctival Allergen Provocation Testing (CAPT) and Environmental Exposure Chamber (EEC) testing. EEC (N = 13) 2, 5 (2012)Google Scholar
- 52.Wald, M.J., Lay, B., Danno, R., Grosskreutz, C.L., Chandra, S.: Performance of automated hyperemia assessment in allergic conjunctivitis interventional study. Invest. Ophthalmol. Vis. Sci. 56, 12300 (2015)Google Scholar
- 53.Downie, L.E., Keller, P.R., Vingrys, A.J.: Assessing ocular bulbar redness: a comparison of methods. Ophthalmic Physiol. Opt. 36(2), 132–139 (2016)CrossRefGoogle Scholar
- 54.Amparo, F., Wang, H., Emami-Naeini, P., Karimian, P., Dana, R.: The ocular redness index: a novel automated method for measuring ocular injectiona novel automated system to measure redness. Invest. Ophthalmol. Vis. Sci. 54(7), 4821–4826 (2013)CrossRefGoogle Scholar
- 55.Papas, E.B.: Key factors in the subjective and objective assessment of conjunctival erythema. Invest. Ophthalmol. Vis. Sci. 41(3), 687–691 (2000)Google Scholar
- 56.Wolffsohn, J.S., Purslow, C.: Clinical monitoring of ocular physiology using digital image analysis. Contact Lens and Anterior Eye 26(1), 27–35 (2003)CrossRefGoogle Scholar
- 57.Efron, N., Morgan, P.B., Katsara, S.S.: Validation of grading scales for contact lens complications. Ophthalmic Physiol. Opt. 21(1), 17–29 (2001)Google Scholar
- 58.Fieguth, P., Simpson, T.: Automated measurement of bulbar redness. Invest. Ophthalmol. Vis. Sci. 43(2), 340–347 (2002)Google Scholar
- 59.Murphy, P.J., Lau, J.S.C., Sim, M.M.L., Woods, R.L.: How red is a white eye? Clinical grading of normal conjunctival hyperemia. Eye 21(5), 633–638 (2007)CrossRefGoogle Scholar
- 60.Wolffsohn, J.S.: Incremental nature of anterior eye grading scales determined by objective image analysis. Br. J. Ophthalmol. 88(11), 1434–1438 (2004)CrossRefGoogle Scholar
- 61.Sánchez, L., Barreira, N., Pena-Verdeal, H., Yebra-Pimentel, E.: A Novel Framework for Hyperemia Grading Based on Artificial Neural Networks, pp. 263–275. Springer, Heidelberg (2015)Google Scholar
- 62.Sánchez, L., Barreira, N., Sánchez, N., Mosquera, A., Pena-Verdeal, H., Yebra-Pimentel, E.: On the analysis of local and global features for hyperemia grading. Ninth Int. Conf. Mach. Vis. 10341, 103411T–103411T (2017)CrossRefGoogle Scholar
- 63.Sánchez-Brea, M.L., Barreira-Rodrguez, N., Mosquera-González, A., Evans, K., Pena-Verdeal, H.: Defining the optimal region of interest for hyperemia grading in the bulbar conjunctiva. Comput. Math. Methods Med. 2016, 1–9 (2016)Google Scholar
- 64.Vázquez, S.G., Barreira, N., Penedo, M.G., Pena-Seijo, M., Gómez-Ulla, F.: Evaluation of SIRIUS retinal vessel width measurement in REVIEW dataset. IEEE 26th Int. Symp. Comp. Med. Syst. 2013, 71–76 (2013)Google Scholar
- 65.Robnik-Šikonja, M., Kononenko, I.: An adaptation of Relief for attribute estimation in regression. In Machine Learning: Proceedings of the Fourteenth International Conference, 296–304 (1997)Google Scholar
- 66.Quinlan, J.R.: Learning with continuous classes. Aust. Jt Conf. Artif. Intell. 92, 343–348 (1992)Google Scholar
- 67.Shevade, S.K., Keerthi, S.S., Bhattacharyya, C., Murthy, K.R.K.: Improvements to the SMO algorithm for SVM regression. IEEE Trans. Neural Netw. 11(5), 1188–1193 (2000)CrossRefzbMATHGoogle Scholar
- 68.Guyon, I., Weston, J., Barnhill, S., Vapnik, V.: Gene selection for cancer classification using support vector machines. Mach. Learn. 46(1–3), 389–422 (2002)CrossRefzbMATHGoogle Scholar
- 69.Sánchez-Brea, M.L., Barreira, N., Sánchez-Maroño, N., Mosquera, A., García-Resúa, C., Giráldez-Fernández, M.J.: On the development of conjunctival hyperemia computer-assisted diagnosis tools: Influence of feature selection and class imbalance in automatic gradings. Artif. Intell. Med. 71, 30–42 (2016)Google Scholar
- 70.Sanchez, L., Barreira, N., Mosquera, A., Pena-Verdeal, H., Yebra-Pimentel, E.: Comparing machine learning techniques in a hyperemia grading framework. Int. Conf. Agents Artif. Intell. 2, 423–429 (2016)Google Scholar
- 71.Baum, E.B.: On the capabilities of multilayer perceptrons. J Complexity 4(3), 193–215 (1988)CrossRefzbMATHMathSciNetGoogle Scholar
- 72.Park, J., Sandberg, I.W.: Universal approximation using radial-basis-function networks. Neural Comput. 3(2), 246–257 (1991)CrossRefGoogle Scholar
- 73.Kohonen, T.: The self-organizing map. Neurocomputing 21(1–3), 1–6 (1998)CrossRefzbMATHGoogle Scholar
- 74.Kohonen, T.: Improved versions of learning vector quantization. Int. Jt Conf. Neural Netw. 1990, 545–550 (1990)Google Scholar
- 75.Quinlan, J.R.: Induction of decision trees. Mach. Learn. 1(1), 81–106 (1986)Google Scholar
- 76.Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
- 77.Smola, A.J., Schölkopf, B.: A tutorial on support vector regression. Stat. Comput. 14(3), 199–222 (2004)CrossRefMathSciNetGoogle Scholar
- 78.Dudani, S.A.: The distance-weighted k-nearest-neighbor rule. IEEE Trans. Syst. Man Cybern. 6(4), 325–327 (1976)CrossRefGoogle Scholar
- 79.Abdi, H.: Partial least square regression (PLS regression). Encycl. Res. Methods Soc. Sci. 6(4), 792–795, 2003Google Scholar
- 80.John, G.H., Langley, P.: Estimating continuous distributions in bayesian classifiers.Conf. Uncertainty Artif. Intell. 1995, 338–345, (1995)Google Scholar
- 81.Abelson, M.B., Ousler, G.W., Nally, L.A., Welch, D., Krenzer, K.: Alternative reference values for tear film break up time in normal and dry eye Populations. In Lacrimal Gland, Tear Film, and Dry Eye Syndromes 3, pp. 1121–1125. Springer, New York (2002)Google Scholar
- 82.King-Smith, P.E., Fink, B.A., Nichol J.J., Braun, R.J., McFadden, G.B.: The contribution of lipid layer movement to tear film thinning and breakup. Invest. Opthalmol. Vis. Sci. 50, 2747–2756 (2009)Google Scholar
- 83.Bitton, E., Lovasik, J. V.: Longitudinal analysis of precorneal tear film rupture patterns. In Lacrimal Gland, Tear Film, and Dry Eye Syndromes 2, pp. 381–389. Springer, New York (1998)Google Scholar
- 84.Yedidya,T., Hartley, R., Guillon, J.P.: Automatic detection of pre-ocular tear film break-up sequence in dry eyes. Digit. Image Comput. Tech. and Appl., 2008, 442–448 (2008)Google Scholar
- 85.Cebreiro, E., Ramos, L., Mosquera, A., Barreira, N., Penedo, M.G.: Automation of the tear film break-up time test. Proceedings of the 4th International Symposium on Applied Sciences in Biomedical and Communication Technologies, 123 (2011)Google Scholar
- 86.Ramos, L., Barreira, N., Mosquera, A., Currás, M., Pena-Verdeal, H. Giráldez, M.J., Penedo, M.G: Adaptive parameter computation for the automatic measure of the Tear Break-Up Time. 16th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems, 243, 1370–1379 (2012)Google Scholar
- 87.Ramos, L., Barreira, N., Mosquera, A., Penedo, M.G., Yebra-Pimentel, E., García-Resúa, C.: Analysis of parameters for the automatic computation of the tear film break-up time test based on cclru standards. Comput. Methods Programs Biomed. 113(3), 715–724 (2014)CrossRefGoogle Scholar
- 88.Ramos, L., Barreira, N., Pena-Verdeal, H., Giráldez, M.J., Yebra-Pimentel, E.: Computational approach for tear film assessment based on break-up dynamics. Biosys. Eng. 138, 90–103 (2015)CrossRefGoogle Scholar
- 89.Ramos, L., Barreira, N., Mosquera, A., Pena-Verdeal, H., Yebra-Pimentel, E.: Break-up analysis of the tear film based on time, location, size and shape of the rupture area. International Conference Image Analysis and Recognition, 695–702 (2013)Google Scholar
- 90.Foracchia, M., Grisan, E., Ruggeri, A.: Luminosity and contrast normalization in retinal images. Med. Image Anal. 9(3), 179–190 (2005)CrossRefGoogle Scholar
- 91.Arora, S., Acharya, J., Verma, A., Prasanta, K.: Panigrahi. Multilevel thresholding for image segmentation through a fast statistical recursive algorithm. Pattern Recogn. Lett. 29(2), 119–125 (2008)CrossRefGoogle Scholar
- 92.Dougherty, E.R.: An introduction to morphological image processing. SPIE Optical Engineering Press, Tutorial texts in optical engineering (1992)Google Scholar
- 93.Suzuki, S., Abe, K.: Topological structural analysis of digitized binary images by border following. Comput. Vis. Graph. Image Process. 30(1), 32–46 (1985)CrossRefzbMATHGoogle Scholar
- 94.Hu, M.: Visual pattern recognition by moment invariants, computer methods in image analysis. IRE Trans. Inf. Theory 8, 179–187 (1962)Google Scholar
- 95.Reed-Teague, M.: Image analysis via the general theory of moments. J. Opt. Soc. Am. 70(8), 920–930 (1980)CrossRefMathSciNetGoogle Scholar
- 96.Nunes, J.F., Moreira, P.M., Tavares, J.M.R.S: Shape based image retrieval and classification. 5th Iberian Conference on Information Systems and Technologies (2010)Google Scholar
- 97.Rodriguez, J., Perez, A., Lozano, J.: Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE Trans. Pattern Anal. Mach. Intell. 32(3), 569–575 (2010)CrossRefGoogle Scholar
- 98.Jolliffe, I.T.: Principal Component Analysis. Springer Verlag, New York (1986)CrossRefzbMATHGoogle Scholar