{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T21:38:36Z","timestamp":1774993116319,"version":"3.50.1"},"reference-count":32,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2005,2,1]],"date-time":"2005-02-01T00:00:00Z","timestamp":1107216000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2005,2,1]],"date-time":"2005-02-01T00:00:00Z","timestamp":1107216000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["OVS"],"published-print":{"date-parts":[[2005,2]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose.<\/jats:title>\n                    <jats:p>Our main goal in this work was to develop an artificial neural network (NN) that could classify specific types of corneal shapes using Zernike coefficients as input. Other authors have implemented successful NN systems in the past and have demonstrated their efficiency using different parameters. Our claim is that, given the increasing popularity of Zernike polynomials among the eye care community, this may be an interesting choice to add complementing value and precision to existing methods. By using a simple and well\u2010documented corneal surface representation scheme, which relies on corneal elevation information, one can generate simple NN input parameters that are independent of curvature definition and that are also efficient.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods.<\/jats:title>\n                    <jats:p>\n                      We have used the Matlab Neural Network Toolbox (MathWorks, Natick, MA) to implement a three\u2010layer feed\u2010forward NN with 15 inputs and 5 outputs. A database from an EyeSys System 2000 (EyeSys Vision, Houston, TX) videokeratograph installed at the\n                      <jats:italic>Escola Paulista de Medicina\u2010S\u00e3o Paulo<\/jats:italic>\n                      was used. This database contained an unknown number of corneal types. From this database, two specialists selected 80 corneas that could be clearly classified into five distinct categories: (1) normal, (2) with\u2010the\u2010rule astigmatism, (3) against\u2010the\u2010rule astigmatism, (4) keratoconus, and (5) post\u2013laser\u2010assisted\n                      <jats:italic>in situ<\/jats:italic>\n                      keratomileusis. The corneal height (SAG) information of the 80 data files was fit with the first 15 Vision Science and it Applications (VSIA) standard Zernike coefficients, which were individually used to feed the 15 neurons of the input layer. The five output neurons were associated with the five typical corneal shapes. A group of 40 cases was randomly selected from the larger group of 80 corneas and used as the training set.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results.<\/jats:title>\n                    <jats:p>The NN responses were statistically analyzed in terms of sensitivity [true positive\/(true positive + false negative)], specificity [true negative\/(true negative + false positive)], and precision [(true positive + true negative)\/total number of cases]. The mean values for these parameters were, respectively, 78.75, 97.81, and 94%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion.<\/jats:title>\n                    <jats:p>Although we have used a relatively small training and testing set, results presented here should be considered promising. They are certainly an indication of the potential of Zernike polynomials as reliable parameters, at least in the cases presented here, as input data for artificial intelligence automation of the diagnosis process of videokeratography examinations. This technique should facilitate the implementation and add value to the classification methods already available. We also discuss briefly certain special properties of Zernike polynomials that are what we think make them suitable as NN inputs for this type of application.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/01.opx.0000153193.41554.a1","type":"journal-article","created":{"date-parts":[[2005,2,10]],"date-time":"2005-02-10T04:00:58Z","timestamp":1108008058000},"page":"151-158","source":"Crossref","is-referenced-by-count":21,"title":["Preliminary Results of Neural Networks and Zernike Polynomials for Classification of Videokeratography Maps"],"prefix":"10.1002","volume":"82","author":[{"given":"Luis Alberto","family":"Carvalho","sequence":"first","affiliation":[{"name":"Grupo de \u00d3ptica Instituto de F\u00edsica de S\u00e3o Carlos, Universidade de S\u00e3o Paulo (IFSC\u2010USP) Brazil"},{"name":"Departamento de Oftalmologia Escola Paulista de Medicina\u2013Universidade Federal de S\u00e3o Paulo (UNIFESP) Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2005,2,1]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/BF02478259","article-title":"A logical calculus of the ideas immanent in nervous activity","volume":"5","author":"McCulloch WS","year":"1943","journal-title":"Bull Math Biophys"},{"key":"e_1_2_7_3_1","volume-title":"Neural Networks: A Comprehensive Foundation","author":"Haykin SS","year":"1999"},{"key":"e_1_2_7_4_1","doi-asserted-by":"crossref","first-page":"2554","DOI":"10.1073\/pnas.79.8.2554","article-title":"Neural networks and physical systems with emergent collective computational abilities","volume":"79","author":"Hopfield JJ","year":"1982","journal-title":"Proc Natl Acad Sci U S A"},{"key":"e_1_2_7_5_1","volume-title":"Visions: How Science Will Revolutionize the 21st Century","author":"Kaku M","year":"1997"},{"key":"e_1_2_7_6_1","first-page":"2749","article-title":"Automated keratoconus screening with corneal topography analysis","volume":"35","author":"Maeda N","year":"1994","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"e_1_2_7_7_1","first-page":"164","article-title":"Automated topographic screening for keratoconus in refractive surgery candidates","volume":"22","author":"Kalin NS","year":"1996","journal-title":"CLAO J"},{"key":"e_1_2_7_8_1","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1016\/S0039-6257(97)00119-7","article-title":"Keratoconus","volume":"42","author":"Rabinowitz YS","year":"1998","journal-title":"Surv Ophthalmol"},{"key":"e_1_2_7_9_1","doi-asserted-by":"crossref","first-page":"1327","DOI":"10.1016\/S0886-3350(99)00195-9","article-title":"KISA% index: a quantitative videokeratography algorithm embodying minimal topographic criteria for diagnosing keratoconus","volume":"25","author":"Rabinowitz YS","year":"1999","journal-title":"J Cataract Refract Surg"},{"key":"e_1_2_7_10_1","doi-asserted-by":"crossref","first-page":"2105","DOI":"10.1364\/JOSAA.12.002105","article-title":"Representation of videokeratoscopic height data with Zernike polynomials","volume":"12","author":"Schwiegerling J","year":"1995","journal-title":"J Opt Soc Am A Opt Image Sci Vis"},{"key":"e_1_2_7_11_1","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1097\/00006324-199612000-00001","article-title":"Keratoconus detection based on videokeratoscopic height data","volume":"73","author":"Schwiegerling J","year":"1996","journal-title":"Optom Vis Sci"},{"key":"e_1_2_7_12_1","doi-asserted-by":"crossref","first-page":"963","DOI":"10.1097\/00006324-199711000-00029","article-title":"Cone dimensions in keratoconus using Zernike polynomials","volume":"74","author":"Schwiegerling J","year":"1997","journal-title":"Optom Vis Sci"},{"key":"e_1_2_7_13_1","first-page":"217","article-title":"Keratoconus screening with wave\u2010front parameters based on topography height data","volume":"214","author":"Langenbucher A","year":"1999","journal-title":"Klin Monatsbl Augenheilkd"},{"key":"e_1_2_7_14_1","volume-title":"Principles of Optics: Electromagnetic Theory of Propagation, Interference, and Diffraction of Light, 5th Ed","author":"Born M","year":"1975"},{"key":"e_1_2_7_15_1","doi-asserted-by":"crossref","first-page":"1949","DOI":"10.1364\/JOSAA.11.001949","article-title":"Objective measurement of wave aberrations of the human eye with the use of a Hartmann\u2010Shack wave\u2010front sensor","volume":"11","author":"Liang J","year":"1994","journal-title":"J Opt Soc Am A Opt Image Sci Vis"},{"key":"e_1_2_7_16_1","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1364\/JOSAA.17.000955","article-title":"Corneal wave aberration from videokeratography: accuracy and limitations of the procedure","volume":"17","author":"Guirao A","year":"2000","journal-title":"J Opt Soc Am A Opt Image Sci Vis"},{"key":"e_1_2_7_17_1","doi-asserted-by":"crossref","first-page":"2006","DOI":"10.1016\/S0886-3350(02)01447-5","article-title":"Videokeratoscopes for dioptric power measurement during surgery","volume":"28","author":"Carvalho LA","year":"2002","journal-title":"J Cataract Refract Surg"},{"key":"e_1_2_7_18_1","doi-asserted-by":"crossref","first-page":"S652","DOI":"10.3928\/1081-597X-20020901-30","article-title":"Standards for reporting the optical aberrations of eyes","volume":"18","author":"Thibos LN","year":"2002","journal-title":"J Refract Surg"},{"key":"e_1_2_7_19_1","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1097\/01.OPX.0000139682.78272.f3","article-title":"Absolute accuracy of Placido\u2010based videokeratographs to measure the optical aberrations of the cornea","volume":"81","author":"Carvalho LA","year":"2004","journal-title":"Optom Vis Sci"},{"key":"e_1_2_7_20_1","doi-asserted-by":"crossref","unstructured":"WidrowB HoffMEJr.Adaptive switching circuits. 1960 IRE Western Electric Show and Convention Record 1960:96\u2013104.","DOI":"10.21236\/AD0241531"},{"key":"e_1_2_7_21_1","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/S1532-0464(02)00513-0","article-title":"Neural network\u2010based system for early keratoconus detection from corneal topography","volume":"35","author":"Accardo PA","year":"2002","journal-title":"J Biomed Inform"},{"key":"e_1_2_7_22_1","unstructured":"Wolfram Research.Mathworld: Calculus and Analysis\/Special Functions\/Orthogonal Polynomials\/Zernike Polynomial. Available at:http:\/\/mathworld.wolfram.com\/ZernikePolynomial.html. Accessed November 18 2004."},{"key":"e_1_2_7_23_1","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1097\/00006324-199511000-00008","article-title":"A spline surface algorithm for reconstruction of corneal topography from a videokeratographic reflection pattern","volume":"72","author":"Halstead MA","year":"1995","journal-title":"Optom Vis Sci"},{"key":"e_1_2_7_24_1","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1136\/bjo.82.1.35","article-title":"Reliable keratometry with a new hand held surgical keratometer: calibration of the keratoscopic astigmatic ruler","volume":"82","author":"Morlet N","year":"1998","journal-title":"Br J Ophthalmol"},{"key":"e_1_2_7_25_1","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1097\/00006324-199711000-00028","article-title":"Corneal topography reconstruction algorithm that avoids the skew ray ambiguity and the skew ray error","volume":"74","author":"Klein SA","year":"1997","journal-title":"Optom Vis Sci"},{"key":"e_1_2_7_26_1","first-page":"S920","article-title":"Zernike polynomial terms and corneal indices as neural network inputs for videokeratography classification","volume":"38","author":"Smolek MK","year":"1997","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"e_1_2_7_27_1","doi-asserted-by":"crossref","unstructured":"CampbellC. e\u2010Letter: inadequacy of Zernike polynomial fitting: case not made.Invest Opthalmol Vis Sci February 27 2004. Available at:http:\/\/www.iovs.org\/cgi\/eletters\/44\/11\/4676#114. Accessed November 18 2004.","DOI":"10.1167\/iovs.03-0190"},{"key":"e_1_2_7_28_1","doi-asserted-by":"crossref","first-page":"1467","DOI":"10.1016\/0002-9378(92)91621-G","article-title":"The use of a neural network for the ultrasonographic estimation of fetal weight in the macrosomic fetus","volume":"166","author":"Farmer RM","year":"1992","journal-title":"Am J Obstet Gynecol"},{"key":"e_1_2_7_29_1","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1093\/clinchem\/38.1.34","article-title":"Application of neural networks to the interpretation of laboratory data in cancer diagnosis","volume":"38","author":"Astion ML","year":"1992","journal-title":"Clin Chem"},{"key":"e_1_2_7_30_1","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/S0002-9394(02)01836-6","article-title":"Neural networks to identify glaucomatous visual field progression","volume":"135","author":"Lin A","year":"2003","journal-title":"Am J Ophthalmol"},{"key":"e_1_2_7_31_1","first-page":"1327","article-title":"Neural network classification of corneal topography. Preliminary demonstration","volume":"36","author":"Maeda N","year":"1995","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"e_1_2_7_32_1","first-page":"2290","article-title":"Current keratoconus detection methods compared with a neural network approach","volume":"38","author":"Smolek MK","year":"1997","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"e_1_2_7_33_1","doi-asserted-by":"crossref","first-page":"1926","DOI":"10.1016\/S0886-3350(01)01182-8","article-title":"Screening of prior refractive surgery by a wavelet\u2010based neural network","volume":"27","author":"Smolek MK","year":"2001","journal-title":"J Cataract Refract Surg"}],"container-title":["Optometry and Vision Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1097\/01.OPX.0000153193.41554.A1","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1097\/01.OPX.0000153193.41554.A1","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1097\/01.OPX.0000153193.41554.A1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T09:29:40Z","timestamp":1774949380000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1097\/01.OPX.0000153193.41554.A1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,2]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2005,2]]}},"alternative-id":["10.1097\/01.OPX.0000153193.41554.A1"],"URL":"https:\/\/doi.org\/10.1097\/01.opx.0000153193.41554.a1","archive":["Portico"],"relation":{},"ISSN":["1040-5488","1538-9235"],"issn-type":[{"value":"1040-5488","type":"print"},{"value":"1538-9235","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005,2]]}}}