Automated classifiers for early detection and diagnosis of retinopathy in diabetic eyes

Gábor M. Somfai, Erika Tátrai, Lenke Laurik, Boglárka Varga, Veronika Ölvedy, Hong Jiang, Jianhua Wang, William E Smiddy, Anikó Somogyi, Delia Cabrera DeBuc

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Background: Artificial neural networks (ANNs) have been used to classify eye diseases, such as diabetic retinopathy (DR) and glaucoma. DR is the leading cause of blindness in working-age adults in the developed world. The implementation of DR diagnostic routines could be feasibly improved by the integration of structural and optical property test measurements of the retinal structure that provide important and complementary information for reaching a diagnosis. In this study, we evaluate the capability of several structural and optical features (thickness, total reflectance and fractal dimension) of various intraretinal layers extracted from optical coherence tomography images to train a Bayesian ANN to discriminate between healthy and diabetic eyes with and with no mild retinopathy.Results: When exploring the probability as to whether the subject's eye was healthy (diagnostic condition, Test 1), we found that the structural and optical property features of the outer plexiform layer (OPL) and the complex formed by the ganglion cell and inner plexiform layers (GCL + IPL) provided the highest probability (positive predictive value (PPV) of 91% and 89%, respectively) for the proportion of patients with positive test results (healthy condition) who were correctly diagnosed (Test 1). The true negative, TP and PPV values remained stable despite the different sizes of training data sets (Test 2). The sensitivity, specificity and PPV were greater or close to 0.70 for the retinal nerve fiber layer's features, photoreceptor outer segments and retinal pigment epithelium when 23 diabetic eyes with mild retinopathy were mixed with 38 diabetic eyes with no retinopathy (Test 3).Conclusions: A Bayesian ANN trained on structural and optical features from optical coherence tomography data can successfully discriminate between healthy and diabetic eyes with and with no retinopathy. The fractal dimension of the OPL and the GCL + IPL complex predicted by the Bayesian radial basis function network provides better diagnostic utility to classify diabetic eyes with mild retinopathy. Moreover, the thickness and fractal dimension parameters of the retinal nerve fiber layer, photoreceptor outer segments and retinal pigment epithelium show promise for the diagnostic classification between diabetic eyes with and with no mild retinopathy.

Original languageEnglish
Article number106
JournalBMC Bioinformatics
Volume15
Issue number1
DOIs
StatePublished - Apr 12 2014

Fingerprint

Diabetic Retinopathy
Fractal dimension
Early Diagnosis
Classifiers
Retinal Pigments
Optical tomography
Classifier
Neural networks
Pigments
Structural properties
Diagnostics
Fractals
Optical properties
Fractal Dimension
Artificial Neural Network
Optical Coherence Tomography
Radial basis function networks
Fibers
Nerve
Retinal Pigment Epithelium

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics
  • Structural Biology

Cite this

Automated classifiers for early detection and diagnosis of retinopathy in diabetic eyes. / Somfai, Gábor M.; Tátrai, Erika; Laurik, Lenke; Varga, Boglárka; Ölvedy, Veronika; Jiang, Hong; Wang, Jianhua; Smiddy, William E; Somogyi, Anikó; Cabrera DeBuc, Delia.

In: BMC Bioinformatics, Vol. 15, No. 1, 106, 12.04.2014.

Research output: Contribution to journalArticle

Somfai, Gábor M. ; Tátrai, Erika ; Laurik, Lenke ; Varga, Boglárka ; Ölvedy, Veronika ; Jiang, Hong ; Wang, Jianhua ; Smiddy, William E ; Somogyi, Anikó ; Cabrera DeBuc, Delia. / Automated classifiers for early detection and diagnosis of retinopathy in diabetic eyes. In: BMC Bioinformatics. 2014 ; Vol. 15, No. 1.
@article{1cb5c7e539c341e2950ca5fcdc9740de,
title = "Automated classifiers for early detection and diagnosis of retinopathy in diabetic eyes",
abstract = "Background: Artificial neural networks (ANNs) have been used to classify eye diseases, such as diabetic retinopathy (DR) and glaucoma. DR is the leading cause of blindness in working-age adults in the developed world. The implementation of DR diagnostic routines could be feasibly improved by the integration of structural and optical property test measurements of the retinal structure that provide important and complementary information for reaching a diagnosis. In this study, we evaluate the capability of several structural and optical features (thickness, total reflectance and fractal dimension) of various intraretinal layers extracted from optical coherence tomography images to train a Bayesian ANN to discriminate between healthy and diabetic eyes with and with no mild retinopathy.Results: When exploring the probability as to whether the subject's eye was healthy (diagnostic condition, Test 1), we found that the structural and optical property features of the outer plexiform layer (OPL) and the complex formed by the ganglion cell and inner plexiform layers (GCL + IPL) provided the highest probability (positive predictive value (PPV) of 91{\%} and 89{\%}, respectively) for the proportion of patients with positive test results (healthy condition) who were correctly diagnosed (Test 1). The true negative, TP and PPV values remained stable despite the different sizes of training data sets (Test 2). The sensitivity, specificity and PPV were greater or close to 0.70 for the retinal nerve fiber layer's features, photoreceptor outer segments and retinal pigment epithelium when 23 diabetic eyes with mild retinopathy were mixed with 38 diabetic eyes with no retinopathy (Test 3).Conclusions: A Bayesian ANN trained on structural and optical features from optical coherence tomography data can successfully discriminate between healthy and diabetic eyes with and with no retinopathy. The fractal dimension of the OPL and the GCL + IPL complex predicted by the Bayesian radial basis function network provides better diagnostic utility to classify diabetic eyes with mild retinopathy. Moreover, the thickness and fractal dimension parameters of the retinal nerve fiber layer, photoreceptor outer segments and retinal pigment epithelium show promise for the diagnostic classification between diabetic eyes with and with no mild retinopathy.",
author = "Somfai, {G{\'a}bor M.} and Erika T{\'a}trai and Lenke Laurik and Bogl{\'a}rka Varga and Veronika {\"O}lvedy and Hong Jiang and Jianhua Wang and Smiddy, {William E} and Anik{\'o} Somogyi and {Cabrera DeBuc}, Delia",
year = "2014",
month = "4",
day = "12",
doi = "10.1186/1471-2105-15-106",
language = "English",
volume = "15",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Automated classifiers for early detection and diagnosis of retinopathy in diabetic eyes

AU - Somfai, Gábor M.

AU - Tátrai, Erika

AU - Laurik, Lenke

AU - Varga, Boglárka

AU - Ölvedy, Veronika

AU - Jiang, Hong

AU - Wang, Jianhua

AU - Smiddy, William E

AU - Somogyi, Anikó

AU - Cabrera DeBuc, Delia

PY - 2014/4/12

Y1 - 2014/4/12

N2 - Background: Artificial neural networks (ANNs) have been used to classify eye diseases, such as diabetic retinopathy (DR) and glaucoma. DR is the leading cause of blindness in working-age adults in the developed world. The implementation of DR diagnostic routines could be feasibly improved by the integration of structural and optical property test measurements of the retinal structure that provide important and complementary information for reaching a diagnosis. In this study, we evaluate the capability of several structural and optical features (thickness, total reflectance and fractal dimension) of various intraretinal layers extracted from optical coherence tomography images to train a Bayesian ANN to discriminate between healthy and diabetic eyes with and with no mild retinopathy.Results: When exploring the probability as to whether the subject's eye was healthy (diagnostic condition, Test 1), we found that the structural and optical property features of the outer plexiform layer (OPL) and the complex formed by the ganglion cell and inner plexiform layers (GCL + IPL) provided the highest probability (positive predictive value (PPV) of 91% and 89%, respectively) for the proportion of patients with positive test results (healthy condition) who were correctly diagnosed (Test 1). The true negative, TP and PPV values remained stable despite the different sizes of training data sets (Test 2). The sensitivity, specificity and PPV were greater or close to 0.70 for the retinal nerve fiber layer's features, photoreceptor outer segments and retinal pigment epithelium when 23 diabetic eyes with mild retinopathy were mixed with 38 diabetic eyes with no retinopathy (Test 3).Conclusions: A Bayesian ANN trained on structural and optical features from optical coherence tomography data can successfully discriminate between healthy and diabetic eyes with and with no retinopathy. The fractal dimension of the OPL and the GCL + IPL complex predicted by the Bayesian radial basis function network provides better diagnostic utility to classify diabetic eyes with mild retinopathy. Moreover, the thickness and fractal dimension parameters of the retinal nerve fiber layer, photoreceptor outer segments and retinal pigment epithelium show promise for the diagnostic classification between diabetic eyes with and with no mild retinopathy.

AB - Background: Artificial neural networks (ANNs) have been used to classify eye diseases, such as diabetic retinopathy (DR) and glaucoma. DR is the leading cause of blindness in working-age adults in the developed world. The implementation of DR diagnostic routines could be feasibly improved by the integration of structural and optical property test measurements of the retinal structure that provide important and complementary information for reaching a diagnosis. In this study, we evaluate the capability of several structural and optical features (thickness, total reflectance and fractal dimension) of various intraretinal layers extracted from optical coherence tomography images to train a Bayesian ANN to discriminate between healthy and diabetic eyes with and with no mild retinopathy.Results: When exploring the probability as to whether the subject's eye was healthy (diagnostic condition, Test 1), we found that the structural and optical property features of the outer plexiform layer (OPL) and the complex formed by the ganglion cell and inner plexiform layers (GCL + IPL) provided the highest probability (positive predictive value (PPV) of 91% and 89%, respectively) for the proportion of patients with positive test results (healthy condition) who were correctly diagnosed (Test 1). The true negative, TP and PPV values remained stable despite the different sizes of training data sets (Test 2). The sensitivity, specificity and PPV were greater or close to 0.70 for the retinal nerve fiber layer's features, photoreceptor outer segments and retinal pigment epithelium when 23 diabetic eyes with mild retinopathy were mixed with 38 diabetic eyes with no retinopathy (Test 3).Conclusions: A Bayesian ANN trained on structural and optical features from optical coherence tomography data can successfully discriminate between healthy and diabetic eyes with and with no retinopathy. The fractal dimension of the OPL and the GCL + IPL complex predicted by the Bayesian radial basis function network provides better diagnostic utility to classify diabetic eyes with mild retinopathy. Moreover, the thickness and fractal dimension parameters of the retinal nerve fiber layer, photoreceptor outer segments and retinal pigment epithelium show promise for the diagnostic classification between diabetic eyes with and with no mild retinopathy.

UR - http://www.scopus.com/inward/record.url?scp=84899472145&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899472145&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-15-106

DO - 10.1186/1471-2105-15-106

M3 - Article

C2 - 24725911

AN - SCOPUS:84899472145

VL - 15

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - 1

M1 - 106

ER -