Literature DB >> 16357645

Automated decision tree classification of corneal shape.

Michael D Twa1, Srinivasan Parthasarathy, Cynthia Roberts, Ashraf M Mahmoud, Thomas W Raasch, Mark A Bullimore.   

Abstract

PURPOSE: The volume and complexity of data produced during videokeratography examinations present a challenge of interpretation. As a consequence, results are often analyzed qualitatively by subjective pattern recognition or reduced to comparisons of summary indices. We describe the application of decision tree induction, an automated machine learning classification method, to discriminate between normal and keratoconic corneal shapes in an objective and quantitative way. We then compared this method with other known classification methods.
METHODS: The corneal surface was modeled with a seventh-order Zernike polynomial for 132 normal eyes of 92 subjects and 112 eyes of 71 subjects diagnosed with keratoconus. A decision tree classifier was induced using the C4.5 algorithm, and its classification performance was compared with the modified Rabinowitz-McDonnell index, Schwiegerling's Z3 index (Z3), Keratoconus Prediction Index (KPI), KISA%, and Cone Location and Magnitude Index using recommended classification thresholds for each method. We also evaluated the area under the receiver operator characteristic (ROC) curve for each classification method.
RESULTS: Our decision tree classifier performed equal to or better than the other classifiers tested: accuracy was 92% and the area under the ROC curve was 0.97. Our decision tree classifier reduced the information needed to distinguish between normal and keratoconus eyes using four of 36 Zernike polynomial coefficients. The four surface features selected as classification attributes by the decision tree method were inferior elevation, greater sagittal depth, oblique toricity, and trefoil.
CONCLUSION: Automated decision tree classification of corneal shape through Zernike polynomials is an accurate quantitative method of classification that is interpretable and can be generated from any instrument platform capable of raw elevation data output. This method of pattern classification is extendable to other classification problems.

Mesh:

Year:  2005        PMID: 16357645      PMCID: PMC3073139          DOI: 10.1097/01.opx.0000192350.01045.6f

Source DB:  PubMed          Journal:  Optom Vis Sci        ISSN: 1040-5488            Impact factor:   1.973


  26 in total

1.  Automated keratoconus detection using the EyeSys videokeratoscope.

Authors:  P J Chastang; V M Borderie; S Carvajal-Gonzalez; W Rostène; L Laroche
Journal:  J Cataract Refract Surg       Date:  2000-05       Impact factor: 3.351

2.  Keratoconus detection with the KISA% method-another view.

Authors:  S D Klyce; M K Smolek; N Maeda
Journal:  J Cataract Refract Surg       Date:  2000-04       Impact factor: 3.351

3.  Decision tree induction in the diagnosis of otoneurological diseases.

Authors:  K Viikki; E Kentala; M Juhola; I Pyykkö
Journal:  Med Inform Internet Med       Date:  1999 Oct-Dec

4.  A pilot study for identifying at risk thyroid lesions by means of a decision tree run on clinicocytological variables.

Authors:  N Nagy; C Decaestecker; R Kiss; F Rypens; D Van Gansbeke; J Mockel; P Rocmans; I Salmon
Journal:  Int J Mol Med       Date:  1999-09       Impact factor: 4.101

5.  Preliminary results of neural networks and zernike polynomials for classification of videokeratography maps.

Authors:  Luis Alberto Carvalho
Journal:  Optom Vis Sci       Date:  2005-02       Impact factor: 1.973

6.  Ocular predictors of the onset of juvenile myopia.

Authors:  K Zadnik; D O Mutti; N E Friedman; P A Qualley; L A Jones; P Qui; H S Kim; J C Hsu; M L Moeschberger
Journal:  Invest Ophthalmol Vis Sci       Date:  1999-08       Impact factor: 4.799

7.  Data mining with decision trees for diagnosis of breast tumor in medical ultrasonic images.

Authors:  W J Kuo; R F Chang; D R Chen; C C Lee
Journal:  Breast Cancer Res Treat       Date:  2001-03       Impact factor: 4.872

8.  Two eyes or one? The data analyst's dilemma.

Authors:  J Katz
Journal:  Ophthalmic Surg       Date:  1988-08

9.  Between-eye asymmetry in keratoconus.

Authors:  Karla Zadnik; Karen Steger-May; Barbara A Fink; Charlotte E Joslin; Jason J Nichols; Carol E Rosenstiel; Julie A Tyler; Julie A Yu; Thomas W Raasch; Kenneth B Schechtman
Journal:  Cornea       Date:  2002-10       Impact factor: 2.651

10.  Standards for reporting the optical aberrations of eyes.

Authors:  Larry N Thibos; Raymond A Applegate; James T Schwiegerling; Robert Webb
Journal:  J Refract Surg       Date:  2002 Sep-Oct       Impact factor: 3.573

View more
  16 in total

Review 1.  [Application of wavefront analysis in clinical and scientific settings. From irregular astigmatism to aberrations of a higher order--Part II: examples].

Authors:  J Bühren; T Kohnen
Journal:  Ophthalmologe       Date:  2007-11       Impact factor: 1.059

2.  Four discriminant models for detecting keratoconus pattern using Zernike coefficients of corneal aberrations.

Authors:  Makoto Saika; Naoyuki Maeda; Yoko Hirohara; Toshifumi Mihashi; Takashi Fujikado; Kohji Nishida
Journal:  Jpn J Ophthalmol       Date:  2013-08-27       Impact factor: 2.447

3.  CLMI: the cone location and magnitude index.

Authors:  Ashraf M Mahmoud; Cynthia J Roberts; Richard G Lembach; Michael D Twa; Edward E Herderick; Timothy T McMahon
Journal:  Cornea       Date:  2008-05       Impact factor: 2.651

4.  Videokeratoscopic indices in relation to epidemiological exposure to keratoconus.

Authors:  Jose Luis Mato; Isabel Lema; Elío Díez-Feijoo
Journal:  Graefes Arch Clin Exp Ophthalmol       Date:  2010-03-07       Impact factor: 3.117

5.  Validity of autorefractor based screening method for irregular astigmatism compared to the corneal topography- a cross sectional study.

Authors:  Alicia Galindo-Ferreiro; Julita De Miguel-Gutierrez; Manuel González-Sagrado; Alberto Galvez-Ruiz; Rajiv Khandekar; Silvana Schellini; Julio Galindo-Alonso
Journal:  Int J Ophthalmol       Date:  2017-09-18       Impact factor: 1.779

6.  Morphometric analysis and classification of glaucomatous optic neuropathy using radial polynomials.

Authors:  Michael D Twa; Srinivasan Parthasarathy; Chris A Johnson; Mark A Bullimore
Journal:  J Glaucoma       Date:  2012 Jun-Jul       Impact factor: 2.503

7.  Template-based correction of high-order aberration in keratoconus.

Authors:  Jason D Marsack; Jos J Rozema; Carina Koppen; Marie-Jose Tassignon; Raymond A Applegate
Journal:  Optom Vis Sci       Date:  2013-04       Impact factor: 1.973

8.  Keratoconus diagnosis with optical coherence tomography pachymetry mapping.

Authors:  Yan Li; David M Meisler; Maolong Tang; Ake T H Lu; Vishakha Thakrar; Bibiana J Reiser; David Huang
Journal:  Ophthalmology       Date:  2008-11-05       Impact factor: 12.079

9.  Quantifying the effects of hydration on corneal stiffness with noncontact optical coherence elastography.

Authors:  Manmohan Singh; Zhaolong Han; Jiasong Li; Srilatha Vantipalli; Salavat R Aglyamov; Michael D Twa; Kirill V Larin
Journal:  J Cataract Refract Surg       Date:  2018-07-23       Impact factor: 3.351

10.  Screening Candidates for Refractive Surgery With Corneal Tomographic-Based Deep Learning.

Authors:  Yi Xie; Lanqin Zhao; Xiaonan Yang; Xiaohang Wu; Yahan Yang; Xiaoman Huang; Fang Liu; Jiping Xu; Limian Lin; Haiqin Lin; Qiting Feng; Haotian Lin; Quan Liu
Journal:  JAMA Ophthalmol       Date:  2020-05-01       Impact factor: 7.389

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.