Automated retinal health diagnosis using pyramid histogram of visual words and Fisher vector techniques

Joel E.W. Koh, Eddie Y.K. Ng, Sulatha V. Bhandary, Yuki Hagiwara, Augustinus Laude, U. Rajendra Acharya

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Untreated age-related macular degeneration (AMD), diabetic retinopathy (DR), and glaucoma may lead to irreversible vision loss. Hence, it is essential to have regular eye screening to detect these eye diseases at an early stage and to offer treatment where appropriate. One of the simplest, non-invasive and cost-effective techniques to screen the eyes is by using fundus photo imaging. But, the manual evaluation of fundus images is tedious and challenging. Further, the diagnosis made by ophthalmologists may be subjective. Therefore, an objective and novel algorithm using the pyramid histogram of visual words (PHOW) and Fisher vectors is proposed for the classification of fundus images into their respective eye conditions (normal, AMD, DR, and glaucoma). The proposed algorithm extracts features which are represented as words. These features are built and encoded into a Fisher vector for classification using random forest classifier. This proposed algorithm is validated with both blindfold and ten-fold cross-validation techniques. An accuracy of 90.06% is achieved with the blindfold method, and highest accuracy of 96.79% is obtained with ten-fold cross-validation. The highest classification performance of our system shows the potential of deploying it in polyclinics to assist healthcare professionals in their initial diagnosis of the eye. Our developed system can reduce the workload of ophthalmologists significantly.

Original languageEnglish
Pages (from-to)204-209
Number of pages6
JournalComputers in Biology and Medicine
Volume92
DOIs
Publication statusPublished - 01-01-2018

Fingerprint

Health
Macular Degeneration
Diabetic Retinopathy
Glaucoma
Eye Diseases
Screening
Classifiers
Workload
Imaging techniques
Delivery of Health Care
Costs and Cost Analysis
Costs
Ophthalmologists
Therapeutics

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Health Informatics

Cite this

Koh, Joel E.W. ; Ng, Eddie Y.K. ; Bhandary, Sulatha V. ; Hagiwara, Yuki ; Laude, Augustinus ; Acharya, U. Rajendra. / Automated retinal health diagnosis using pyramid histogram of visual words and Fisher vector techniques. In: Computers in Biology and Medicine. 2018 ; Vol. 92. pp. 204-209.
@article{c4a9131785ba4b5ab48dda36f1ca0f47,
title = "Automated retinal health diagnosis using pyramid histogram of visual words and Fisher vector techniques",
abstract = "Untreated age-related macular degeneration (AMD), diabetic retinopathy (DR), and glaucoma may lead to irreversible vision loss. Hence, it is essential to have regular eye screening to detect these eye diseases at an early stage and to offer treatment where appropriate. One of the simplest, non-invasive and cost-effective techniques to screen the eyes is by using fundus photo imaging. But, the manual evaluation of fundus images is tedious and challenging. Further, the diagnosis made by ophthalmologists may be subjective. Therefore, an objective and novel algorithm using the pyramid histogram of visual words (PHOW) and Fisher vectors is proposed for the classification of fundus images into their respective eye conditions (normal, AMD, DR, and glaucoma). The proposed algorithm extracts features which are represented as words. These features are built and encoded into a Fisher vector for classification using random forest classifier. This proposed algorithm is validated with both blindfold and ten-fold cross-validation techniques. An accuracy of 90.06{\%} is achieved with the blindfold method, and highest accuracy of 96.79{\%} is obtained with ten-fold cross-validation. The highest classification performance of our system shows the potential of deploying it in polyclinics to assist healthcare professionals in their initial diagnosis of the eye. Our developed system can reduce the workload of ophthalmologists significantly.",
author = "Koh, {Joel E.W.} and Ng, {Eddie Y.K.} and Bhandary, {Sulatha V.} and Yuki Hagiwara and Augustinus Laude and Acharya, {U. Rajendra}",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.compbiomed.2017.11.019",
language = "English",
volume = "92",
pages = "204--209",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

Automated retinal health diagnosis using pyramid histogram of visual words and Fisher vector techniques. / Koh, Joel E.W.; Ng, Eddie Y.K.; Bhandary, Sulatha V.; Hagiwara, Yuki; Laude, Augustinus; Acharya, U. Rajendra.

In: Computers in Biology and Medicine, Vol. 92, 01.01.2018, p. 204-209.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated retinal health diagnosis using pyramid histogram of visual words and Fisher vector techniques

AU - Koh, Joel E.W.

AU - Ng, Eddie Y.K.

AU - Bhandary, Sulatha V.

AU - Hagiwara, Yuki

AU - Laude, Augustinus

AU - Acharya, U. Rajendra

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Untreated age-related macular degeneration (AMD), diabetic retinopathy (DR), and glaucoma may lead to irreversible vision loss. Hence, it is essential to have regular eye screening to detect these eye diseases at an early stage and to offer treatment where appropriate. One of the simplest, non-invasive and cost-effective techniques to screen the eyes is by using fundus photo imaging. But, the manual evaluation of fundus images is tedious and challenging. Further, the diagnosis made by ophthalmologists may be subjective. Therefore, an objective and novel algorithm using the pyramid histogram of visual words (PHOW) and Fisher vectors is proposed for the classification of fundus images into their respective eye conditions (normal, AMD, DR, and glaucoma). The proposed algorithm extracts features which are represented as words. These features are built and encoded into a Fisher vector for classification using random forest classifier. This proposed algorithm is validated with both blindfold and ten-fold cross-validation techniques. An accuracy of 90.06% is achieved with the blindfold method, and highest accuracy of 96.79% is obtained with ten-fold cross-validation. The highest classification performance of our system shows the potential of deploying it in polyclinics to assist healthcare professionals in their initial diagnosis of the eye. Our developed system can reduce the workload of ophthalmologists significantly.

AB - Untreated age-related macular degeneration (AMD), diabetic retinopathy (DR), and glaucoma may lead to irreversible vision loss. Hence, it is essential to have regular eye screening to detect these eye diseases at an early stage and to offer treatment where appropriate. One of the simplest, non-invasive and cost-effective techniques to screen the eyes is by using fundus photo imaging. But, the manual evaluation of fundus images is tedious and challenging. Further, the diagnosis made by ophthalmologists may be subjective. Therefore, an objective and novel algorithm using the pyramid histogram of visual words (PHOW) and Fisher vectors is proposed for the classification of fundus images into their respective eye conditions (normal, AMD, DR, and glaucoma). The proposed algorithm extracts features which are represented as words. These features are built and encoded into a Fisher vector for classification using random forest classifier. This proposed algorithm is validated with both blindfold and ten-fold cross-validation techniques. An accuracy of 90.06% is achieved with the blindfold method, and highest accuracy of 96.79% is obtained with ten-fold cross-validation. The highest classification performance of our system shows the potential of deploying it in polyclinics to assist healthcare professionals in their initial diagnosis of the eye. Our developed system can reduce the workload of ophthalmologists significantly.

UR - http://www.scopus.com/inward/record.url?scp=85037699892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037699892&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2017.11.019

DO - 10.1016/j.compbiomed.2017.11.019

M3 - Article

VL - 92

SP - 204

EP - 209

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -