Abstract

Prolonged duration of the diabetes may affect the tiny blood vessels of the retina causing diabetic retinopathy. Routine eye screening of patients with diabetes helps to detect diabetic retinopathy at the early stage. It is very laborious and time-consuming for the doctors to go through many fundus images continuously. Therefore, decision support system for diabetic retinopathy detection can reduce the burden of the ophthalmologists. In this work, we have used discrete wavelet transform and support vector machine classifier for automated detection of normal and diabetic retinopathy classes. The wavelet-based decomposition was performed up to the second level, and eight energy features were extracted. Two energy features from the approximation coefficients of two levels and six energy values from the details in three orientations (horizontal, vertical and diagonal) were evaluated. These features were fed to the support vector machine classifier with various kernel functions (linear, radial basis function, polynomial of orders 2 and 3) to evaluate the highest classification accuracy. We obtained the highest average classification accuracy, sensitivity and specificity of more than 99% with support vector machine classifier (polynomial kernel of order 3) using three discrete wavelet transform features. We have also proposed an integrated index called Diabetic Retinopathy Risk Index using clinically significant wavelet energy features to identify normal and diabetic retinopathy classes using just one number. We believe that this (Diabetic Retinopathy Risk Index) can be used as an adjunct tool by the doctors during the eye screening to cross-check their diagnosis.

Original languageEnglish
Pages (from-to)251-261
Number of pages11
JournalProceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine
Volume227
Issue number3
DOIs
Publication statusPublished - 03-2013

Fingerprint

Wavelet Analysis
Discrete wavelet transforms
Diabetic Retinopathy
Decision support systems
Support vector machines
Classifiers
Medical problems
Screening
Polynomials
Blood vessels
Decomposition
Blood Vessels
Retina
Sensitivity and Specificity

All Science Journal Classification (ASJC) codes

  • Medicine(all)
  • Mechanical Engineering

Cite this

@article{b090190b88ac434bba3f60e43daaa6c2,
title = "Decision support system for diabetic retinopathy using discrete wavelet transform",
abstract = "Prolonged duration of the diabetes may affect the tiny blood vessels of the retina causing diabetic retinopathy. Routine eye screening of patients with diabetes helps to detect diabetic retinopathy at the early stage. It is very laborious and time-consuming for the doctors to go through many fundus images continuously. Therefore, decision support system for diabetic retinopathy detection can reduce the burden of the ophthalmologists. In this work, we have used discrete wavelet transform and support vector machine classifier for automated detection of normal and diabetic retinopathy classes. The wavelet-based decomposition was performed up to the second level, and eight energy features were extracted. Two energy features from the approximation coefficients of two levels and six energy values from the details in three orientations (horizontal, vertical and diagonal) were evaluated. These features were fed to the support vector machine classifier with various kernel functions (linear, radial basis function, polynomial of orders 2 and 3) to evaluate the highest classification accuracy. We obtained the highest average classification accuracy, sensitivity and specificity of more than 99{\%} with support vector machine classifier (polynomial kernel of order 3) using three discrete wavelet transform features. We have also proposed an integrated index called Diabetic Retinopathy Risk Index using clinically significant wavelet energy features to identify normal and diabetic retinopathy classes using just one number. We believe that this (Diabetic Retinopathy Risk Index) can be used as an adjunct tool by the doctors during the eye screening to cross-check their diagnosis.",
author = "K. Noronha and Acharya, {U. R.} and Nayak, {K. P.} and S. Kamath and Bhandary, {S. V.}",
year = "2013",
month = "3",
doi = "10.1177/0954411912470240",
language = "English",
volume = "227",
pages = "251--261",
journal = "Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine",
issn = "0954-4119",
publisher = "SAGE Publications Ltd",
number = "3",

}

Decision support system for diabetic retinopathy using discrete wavelet transform. / Noronha, K.; Acharya, U. R.; Nayak, K. P.; Kamath, S.; Bhandary, S. V.

In: Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, Vol. 227, No. 3, 03.2013, p. 251-261.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Decision support system for diabetic retinopathy using discrete wavelet transform

AU - Noronha, K.

AU - Acharya, U. R.

AU - Nayak, K. P.

AU - Kamath, S.

AU - Bhandary, S. V.

PY - 2013/3

Y1 - 2013/3

N2 - Prolonged duration of the diabetes may affect the tiny blood vessels of the retina causing diabetic retinopathy. Routine eye screening of patients with diabetes helps to detect diabetic retinopathy at the early stage. It is very laborious and time-consuming for the doctors to go through many fundus images continuously. Therefore, decision support system for diabetic retinopathy detection can reduce the burden of the ophthalmologists. In this work, we have used discrete wavelet transform and support vector machine classifier for automated detection of normal and diabetic retinopathy classes. The wavelet-based decomposition was performed up to the second level, and eight energy features were extracted. Two energy features from the approximation coefficients of two levels and six energy values from the details in three orientations (horizontal, vertical and diagonal) were evaluated. These features were fed to the support vector machine classifier with various kernel functions (linear, radial basis function, polynomial of orders 2 and 3) to evaluate the highest classification accuracy. We obtained the highest average classification accuracy, sensitivity and specificity of more than 99% with support vector machine classifier (polynomial kernel of order 3) using three discrete wavelet transform features. We have also proposed an integrated index called Diabetic Retinopathy Risk Index using clinically significant wavelet energy features to identify normal and diabetic retinopathy classes using just one number. We believe that this (Diabetic Retinopathy Risk Index) can be used as an adjunct tool by the doctors during the eye screening to cross-check their diagnosis.

AB - Prolonged duration of the diabetes may affect the tiny blood vessels of the retina causing diabetic retinopathy. Routine eye screening of patients with diabetes helps to detect diabetic retinopathy at the early stage. It is very laborious and time-consuming for the doctors to go through many fundus images continuously. Therefore, decision support system for diabetic retinopathy detection can reduce the burden of the ophthalmologists. In this work, we have used discrete wavelet transform and support vector machine classifier for automated detection of normal and diabetic retinopathy classes. The wavelet-based decomposition was performed up to the second level, and eight energy features were extracted. Two energy features from the approximation coefficients of two levels and six energy values from the details in three orientations (horizontal, vertical and diagonal) were evaluated. These features were fed to the support vector machine classifier with various kernel functions (linear, radial basis function, polynomial of orders 2 and 3) to evaluate the highest classification accuracy. We obtained the highest average classification accuracy, sensitivity and specificity of more than 99% with support vector machine classifier (polynomial kernel of order 3) using three discrete wavelet transform features. We have also proposed an integrated index called Diabetic Retinopathy Risk Index using clinically significant wavelet energy features to identify normal and diabetic retinopathy classes using just one number. We believe that this (Diabetic Retinopathy Risk Index) can be used as an adjunct tool by the doctors during the eye screening to cross-check their diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=84877817999&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877817999&partnerID=8YFLogxK

U2 - 10.1177/0954411912470240

DO - 10.1177/0954411912470240

M3 - Article

VL - 227

SP - 251

EP - 261

JO - Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine

JF - Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine

SN - 0954-4119

IS - 3

ER -