Abstract
Artificial intelligence (AI) has been employed in Keratoconus screening for decades. Since the introduction of Neural Networks, the first machine learning techniques used for topographic classification, AI efforts have focused on detection of nascent forms of corneal ectasias (Forme Frustre Keratoconus and Keratoconus Suspects). Parallel to this, the development of new imaging technology has contributed to the increasing keratoconus data sets, improving the accuracy of algorithms. Currently, AI can assist ophthalmologists with automated interpretation of topographic maps, laser vision correction surgery (particularly in custom planning of the procedure), and prevention of iatrogenic ectasias. This area of medicine will continue to grow in complexity along with new technology promising to make its application routine in the future.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Burns DM, Johnston FM, Frazer DG, Patterson C, Jackson AJ, et al. Keratoconus: an analysis of corneal asymmetry. Br J Ophthalmol. 2004;88(10):1252–5. https://doi.org/10.1136/bjo.2003.033670.
Kovács I, Miháltz K, Kránitz K, Juhász É, Takács Á, Dienes L, et al. Accuracy of machine learning classifiers using bilateral data from a Scheimpflug camera for identifying eyes with preclinical signs of keratoconus. J Cataract Refract Surg. 2016;42(2):275–83. https://doi.org/10.1016/j.jcrs.2015.09.020.
Jonas JB, Nangia V, Matin A, Kulkarni M, Bhojwani K. Prevalence and associations of keratoconus in rural Maharashtra in Central India: the Central India eye and medical study. Am J Ophthalmol. 2009;148(5):760–5. https://doi.org/10.1016/j.ajo.2009.06.024.
Kennedy RH, Bourne WM, Dyer JA. A 48-year clinical and epidemiologic study of keratoconus. Am J Ophthalmol. 1986;101(3):267–73.
Lin SR, Ladas JG, Bahadur GG, Al-Hashimi S, Pineda R. A review of machine learning techniques for keratoconus detection and refractive surgery screening. Semin Ophthalmol. 2019;34(4):317–26. https://doi.org/10.1080/08820538.2019.1620812.
Klyce SD. Chasing the suspect: keratoconus. Br J Ophthalmol. 2009;93(7):845–7. https://doi.org/10.1136/bjo.2008.147371.
Ambrósio R, Randleman JB. Screening for ectasia risk: what are we screening for and how should we screen for it? J Refract Surg. 2013;29(4):230–2. https://doi.org/10.3928/1081597X-20130318-01.
Lopes BT, Ramos IC, Salomão MQ, Guerra FP, Schallhorn SC, Schallhorn JM, et al. Enhanced tomographic assessment to detect corneal ectasia based on artificial intelligence. Am J Ophthalmol. 2018;195:223–32. https://doi.org/10.1016/j.ajo.2018.08.005.
Santhiago MR, Smadja D, Gomes BF, Mello GR, Monteiro ML, Wilson SE, et al. Association between the percent tissue altered and post–laser in situ keratomileusis ectasia in eyes with normal preoperative topography. Am J Ophthalmol. 2014;158(1) https://doi.org/10.1016/j.ajo.2014.04.002.
Seiler T, Quurke AW. Iatrogenic keratectasia after LASIK in a case of forme fruste keratoconus. J Cataract Refract Surg. 1998;24(7):1007–9.
Silverman RH, Urs R, Roychoudhury A, Archer TJ, Gobbe M, Reinstein DZ. Epithelial remodeling as basis for machine-based identification of keratoconus. Invest Ophthalmol Vis Sci. 2014;55(3):1580. https://doi.org/10.1167/iovs.13-12578.
Belin MW, Villavicencio OF, Ambrósio RR. Tomographic parameters for the detection of keratoconus. Eye Contact Lens. 2014;40(6):326–30. https://doi.org/10.1097/ICL.0000000000000077.
Amancio DR, Comin CH, Casanova D, Travieso G, Bruno OM, Rodrigues FA, et al. A systematic comparison of supervised classifiers. PLoS One. 2014;9(4) https://doi.org/10.1371/journal.pone.0094137.
Klyce SD. The future of keratoconus screening with artificial intelligence. Ophthalmology. 2018;125(12):1872–3. https://doi.org/10.1016/j.ophtha.2018.08.019.
Maeda N, Klyce SD, Smolek MK, Thompson HW. Automated keratoconus screening with corneal topography analysis. Invest Ophthalmol Vis Sci. 1994;35(6):2749–57.
Hwang ES, Perez-Straziota CE, Kim SW, Santhiago MR, Randleman JB. Distinguishing highly asymmetric keratoconus eyes using combined Scheimpflug and spectral-domain OCT analysis. Ophthalmology. 2018;125(12):1862–71. https://doi.org/10.1016/j.ophtha.2018.06.020.
Maeda N, Klyce SD, Smolek MK. Neural network classification of corneal topography. Preliminary demonstration. Invest Ophthalmol Vis Sci. 1995;36(7):1327–35.
Smolek MK, Klyce SD. Current keratoconus detection methods compared with a neural network approach. Invest Ophthalmol Vis Sci. 1997;38(11):2290–9.
Smolek MK, Klyce SD. Screening of prior refractive surgery by a wavelet-based neural network. J Cataract Refract Surg. 2001;27(12):1926–31.
Accardo P, Pensiero S. Neural network-based system for early keratoconus detection from corneal topography. J Biomed Inform. 2002;35(3):151–9.
Carvalho LAVD, Barbosa MS. Neural networks and statistical analysis for classification of corneal videokeratography maps based on Zernike coefficients: a quantitative comparison. Arq Bras Oftalmol. 2008;71(3):337–41.
Smadja D, Touboul D, Cohen A, Doveh E, Santhiago MR, Mello GR, et al. Detection of subclinical keratoconus using an automated decision tree classification. Am J Ophthalmol. 2013;156(2) https://doi.org/10.1016/j.ajo.2013.03.034.
Witten IH, Frank E, Hall MA, Pal CJ. Data mining: practical machine learning tools and techniques. 4th ed. Amsterdam: Elsevier; 2016. p. 7–15.
Souza MB, Medeiros FW, Souza DB, Garcia R, Alves MR. Evaluation of machine learning classifiers in keratoconus detection from orbscan II examinations. Clinics (Sao Paulo). 2010;65(12):1223–8. https://doi.org/10.1590/s1807-59322010001200002.
Hidalgo IR, Rodriguez P, Rozema JJ, Dhubhghaill SN, Zakaria N, Tassignon M-J, et al. Evaluation of a machine-learning classifier for keratoconus detection based on Scheimpflug tomography. Cornea. 2016;35(6):827–32. https://doi.org/10.1097/ICO.0000000000000834.
Yousefi S, Yousefi E, Takahashi H, Hayashi T, Tampo H, Inoda S, et al. Keratoconus severity identification using unsupervised machine learning. PLoS One. 2018;13(11) https://doi.org/10.1371/journal.pone.0205998.
Tharwat A, Gaber T, Ibrahim A, Hassanien AE. Linear discriminant analysis: a detailed tutorial. AI Commun. 2017;30(2):169–90. https://doi.org/10.3233/AIC-170729.
Saad A, Gatinel D. Topographic and tomographic properties of Forme Fruste keratoconus corneas. Invest Ophthalmol Vis Sci. 2010;51(11):5546. https://doi.org/10.1167/iovs.10-5369.
Saad A, Gatinel D. Evaluation of total and corneal wavefront high order aberrations for the detection of Forme Fruste keratoconus. Invest Ophthalmol Vis Sci. 2012;53(6):2978. https://doi.org/10.1167/iovs.11-8803.
Alexopoulos EC. Introduction to multivariate regression analysis. Hippokratia. 2010;14(Suppl 1):23–8.
Yuan A, Pineda R. Developments in imaging of corneal biomechanics. Int Ophthalmol Clin. 2019;59(4):1–17. https://doi.org/10.1097/IIO.0000000000000286.
Gokul A, Vellara HR, Patel DV. Advanced anterior segment imaging in keratoconus: a review. Clin Exp Ophthalmol. 2018;46(2):122–32. https://doi.org/10.1111/ceo.13108.
De Stefano VSD, Dupps WJ. Biomechanical diagnostics of the cornea. Int Ophthalmol Clin. 2017;57(3):75–86. https://doi.org/10.1097/IIO.0000000000000172.
Keating A, Roberto Pineda II, Colby K. Corneal cross linking for keratoconus. Semin Ophthalmol. 2010;25(5–6):249–55. https://doi.org/10.3109/08820538.2010.518503.
Sightmap & InnovEyes – YouTube [Internet]. [cited 2020 Mar24]. https://www.youtube.com/watch?v=CPcRoH0qcPM
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Reyes Luis, J.L., Pineda, R. (2021). Artificial Intelligence for Keratoconus Detection and Refractive Surgery Screening. In: Grzybowski, A. (eds) Artificial Intelligence in Ophthalmology. Springer, Cham. https://doi.org/10.1007/978-3-030-78601-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-78601-4_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78600-7
Online ISBN: 978-3-030-78601-4
eBook Packages: MedicineMedicine (R0)