Diagnosis of retinal health in digital fundus images using continuous wavelet transform (CWT) and entropies

Joel E.W. Koh, U. Rajendra Acharya, Yuki Hagiwara, U. Raghavendra, Jen Hong Tan, S. Vinitha Sree, Sulatha V. Bhandary, A. Krishna Rao, Sobha Sivaprasad, Kuang Chua Chua, Augustinus Laude, Louis Tong

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Vision is paramount to humans to lead an active personal and professional life. The prevalence of ocular diseases is rising, and diseases such as glaucoma, Diabetic Retinopathy (DR) and Age-related Macular Degeneration (AMD) are the leading causes of blindness in developed countries. Identifying these diseases in mass screening programmes is time-consuming, labor-intensive and the diagnosis can be subjective. The use of an automated computer aided diagnosis system will reduce the time taken for analysis and will also reduce the inter-observer subjective variabilities in image interpretation. In this work, we propose one such system for the automatic classification of normal from abnormal (DR, AMD, glaucoma) images. We had a total of 404 normal and 1082 abnormal fundus images in our database. As the first step, 2D-Continuous Wavelet Transform (CWT) decomposition on the fundus images of two classes was performed. Subsequently, energy features and various entropies namely Yager, Renyi, Kapoor, Shannon, and Fuzzy were extracted from the decomposed images. Then, adaptive synthetic sampling approach was applied to balance the normal and abnormal datasets. Next, the extracted features were ranked according to the significances using Particle Swarm Optimization (PSO). Thereupon, the ranked and selected features were used to train the random forest classifier using stratified 10-fold cross validation. Overall, the proposed system presented a performance rate of 92.48%, and a sensitivity and specificity of 89.37% and 95.58% respectively using 15 features. This novel system shows promise in detecting abnormal fundus images, and hence, could be a valuable adjunct eye health screening tool that could be employed in polyclinics, and thereby reduce the workload of specialists at hospitals.

Original languageEnglish
Pages (from-to)89-97
Number of pages9
JournalComputers in Biology and Medicine
Volume84
DOIs
Publication statusPublished - 01-05-2017

Fingerprint

Wavelet Analysis
Macular Degeneration
Entropy
Diabetic Retinopathy
Glaucoma
Wavelet transforms
Health
Mass Screening
Observer Variation
Eye Diseases
Screening
Blindness
Workload
Developed Countries
Computer aided diagnosis
Databases
Sensitivity and Specificity
Particle swarm optimization (PSO)
Classifiers
Personnel

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Health Informatics

Cite this

Koh, Joel E.W. ; Acharya, U. Rajendra ; Hagiwara, Yuki ; Raghavendra, U. ; Tan, Jen Hong ; Sree, S. Vinitha ; Bhandary, Sulatha V. ; Rao, A. Krishna ; Sivaprasad, Sobha ; Chua, Kuang Chua ; Laude, Augustinus ; Tong, Louis. / Diagnosis of retinal health in digital fundus images using continuous wavelet transform (CWT) and entropies. In: Computers in Biology and Medicine. 2017 ; Vol. 84. pp. 89-97.
@article{8cace3ab7938437dbffb6fe6d39645dd,
title = "Diagnosis of retinal health in digital fundus images using continuous wavelet transform (CWT) and entropies",
abstract = "Vision is paramount to humans to lead an active personal and professional life. The prevalence of ocular diseases is rising, and diseases such as glaucoma, Diabetic Retinopathy (DR) and Age-related Macular Degeneration (AMD) are the leading causes of blindness in developed countries. Identifying these diseases in mass screening programmes is time-consuming, labor-intensive and the diagnosis can be subjective. The use of an automated computer aided diagnosis system will reduce the time taken for analysis and will also reduce the inter-observer subjective variabilities in image interpretation. In this work, we propose one such system for the automatic classification of normal from abnormal (DR, AMD, glaucoma) images. We had a total of 404 normal and 1082 abnormal fundus images in our database. As the first step, 2D-Continuous Wavelet Transform (CWT) decomposition on the fundus images of two classes was performed. Subsequently, energy features and various entropies namely Yager, Renyi, Kapoor, Shannon, and Fuzzy were extracted from the decomposed images. Then, adaptive synthetic sampling approach was applied to balance the normal and abnormal datasets. Next, the extracted features were ranked according to the significances using Particle Swarm Optimization (PSO). Thereupon, the ranked and selected features were used to train the random forest classifier using stratified 10-fold cross validation. Overall, the proposed system presented a performance rate of 92.48{\%}, and a sensitivity and specificity of 89.37{\%} and 95.58{\%} respectively using 15 features. This novel system shows promise in detecting abnormal fundus images, and hence, could be a valuable adjunct eye health screening tool that could be employed in polyclinics, and thereby reduce the workload of specialists at hospitals.",
author = "Koh, {Joel E.W.} and Acharya, {U. Rajendra} and Yuki Hagiwara and U. Raghavendra and Tan, {Jen Hong} and Sree, {S. Vinitha} and Bhandary, {Sulatha V.} and Rao, {A. Krishna} and Sobha Sivaprasad and Chua, {Kuang Chua} and Augustinus Laude and Louis Tong",
year = "2017",
month = "5",
day = "1",
doi = "10.1016/j.compbiomed.2017.03.008",
language = "English",
volume = "84",
pages = "89--97",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

Diagnosis of retinal health in digital fundus images using continuous wavelet transform (CWT) and entropies. / Koh, Joel E.W.; Acharya, U. Rajendra; Hagiwara, Yuki; Raghavendra, U.; Tan, Jen Hong; Sree, S. Vinitha; Bhandary, Sulatha V.; Rao, A. Krishna; Sivaprasad, Sobha; Chua, Kuang Chua; Laude, Augustinus; Tong, Louis.

In: Computers in Biology and Medicine, Vol. 84, 01.05.2017, p. 89-97.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Diagnosis of retinal health in digital fundus images using continuous wavelet transform (CWT) and entropies

AU - Koh, Joel E.W.

AU - Acharya, U. Rajendra

AU - Hagiwara, Yuki

AU - Raghavendra, U.

AU - Tan, Jen Hong

AU - Sree, S. Vinitha

AU - Bhandary, Sulatha V.

AU - Rao, A. Krishna

AU - Sivaprasad, Sobha

AU - Chua, Kuang Chua

AU - Laude, Augustinus

AU - Tong, Louis

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Vision is paramount to humans to lead an active personal and professional life. The prevalence of ocular diseases is rising, and diseases such as glaucoma, Diabetic Retinopathy (DR) and Age-related Macular Degeneration (AMD) are the leading causes of blindness in developed countries. Identifying these diseases in mass screening programmes is time-consuming, labor-intensive and the diagnosis can be subjective. The use of an automated computer aided diagnosis system will reduce the time taken for analysis and will also reduce the inter-observer subjective variabilities in image interpretation. In this work, we propose one such system for the automatic classification of normal from abnormal (DR, AMD, glaucoma) images. We had a total of 404 normal and 1082 abnormal fundus images in our database. As the first step, 2D-Continuous Wavelet Transform (CWT) decomposition on the fundus images of two classes was performed. Subsequently, energy features and various entropies namely Yager, Renyi, Kapoor, Shannon, and Fuzzy were extracted from the decomposed images. Then, adaptive synthetic sampling approach was applied to balance the normal and abnormal datasets. Next, the extracted features were ranked according to the significances using Particle Swarm Optimization (PSO). Thereupon, the ranked and selected features were used to train the random forest classifier using stratified 10-fold cross validation. Overall, the proposed system presented a performance rate of 92.48%, and a sensitivity and specificity of 89.37% and 95.58% respectively using 15 features. This novel system shows promise in detecting abnormal fundus images, and hence, could be a valuable adjunct eye health screening tool that could be employed in polyclinics, and thereby reduce the workload of specialists at hospitals.

AB - Vision is paramount to humans to lead an active personal and professional life. The prevalence of ocular diseases is rising, and diseases such as glaucoma, Diabetic Retinopathy (DR) and Age-related Macular Degeneration (AMD) are the leading causes of blindness in developed countries. Identifying these diseases in mass screening programmes is time-consuming, labor-intensive and the diagnosis can be subjective. The use of an automated computer aided diagnosis system will reduce the time taken for analysis and will also reduce the inter-observer subjective variabilities in image interpretation. In this work, we propose one such system for the automatic classification of normal from abnormal (DR, AMD, glaucoma) images. We had a total of 404 normal and 1082 abnormal fundus images in our database. As the first step, 2D-Continuous Wavelet Transform (CWT) decomposition on the fundus images of two classes was performed. Subsequently, energy features and various entropies namely Yager, Renyi, Kapoor, Shannon, and Fuzzy were extracted from the decomposed images. Then, adaptive synthetic sampling approach was applied to balance the normal and abnormal datasets. Next, the extracted features were ranked according to the significances using Particle Swarm Optimization (PSO). Thereupon, the ranked and selected features were used to train the random forest classifier using stratified 10-fold cross validation. Overall, the proposed system presented a performance rate of 92.48%, and a sensitivity and specificity of 89.37% and 95.58% respectively using 15 features. This novel system shows promise in detecting abnormal fundus images, and hence, could be a valuable adjunct eye health screening tool that could be employed in polyclinics, and thereby reduce the workload of specialists at hospitals.

UR - http://www.scopus.com/inward/record.url?scp=85016033126&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016033126&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2017.03.008

DO - 10.1016/j.compbiomed.2017.03.008

M3 - Article

VL - 84

SP - 89

EP - 97

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -