Automatic classification of diabetic macular edema in digital fundus images

S. T. Lim, Wan Mimi Diyana Wan Zaki, Aini Hussain, S. L. Lim, S. Kusalavan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

31 Citations (Scopus)

Abstract

Diabetic macular edema is a common complication of diabetic retinopathy due to the presence of exudates in proximity with the fovea. In this paper, an automated method to classify diabetic macular edema is presented. The fovea is localized and the regions of macula are marked based on the Early Treatment Diabetic Retinopathy Studies (ETDRS) grading scale. Extraction method using marker-controlled watershed transformation is adopted and modified from the previous research. The location of the extracted exudates on the marked macular regions is computed to classify diabetic macular edema into normal, stage 1 and stage 2 diabetic macular edema. The performance of the proposed method is evaluated using 88 images of publicly available MESSIDOR database. The overall sensitivity, specificity and accuracy of the proposed method are 80.9%, 90.2% and 85.2%, respectively.

Original languageEnglish
Title of host publication2011 IEEE Colloquium on Humanities, Science and Engineering, CHUSER 2011
Pages265-269
Number of pages5
DOIs
Publication statusPublished - 2011
Event2011 IEEE Colloquium on Humanities, Science and Engineering, CHUSER 2011 - Penang
Duration: 5 Dec 20116 Dec 2011

Other

Other2011 IEEE Colloquium on Humanities, Science and Engineering, CHUSER 2011
CityPenang
Period5/12/116/12/11

Fingerprint

Digital Image
Complications
Specificity
Data Base
Controlled
Proximity
Grading

Keywords

  • Exudates
  • Fovea localization
  • Severity level
  • Watershed transformation

ASJC Scopus subject areas

  • Arts and Humanities(all)

Cite this

Lim, S. T., Wan Zaki, W. M. D., Hussain, A., Lim, S. L., & Kusalavan, S. (2011). Automatic classification of diabetic macular edema in digital fundus images. In 2011 IEEE Colloquium on Humanities, Science and Engineering, CHUSER 2011 (pp. 265-269). [6163730] https://doi.org/10.1109/CHUSER.2011.6163730

Automatic classification of diabetic macular edema in digital fundus images. / Lim, S. T.; Wan Zaki, Wan Mimi Diyana; Hussain, Aini; Lim, S. L.; Kusalavan, S.

2011 IEEE Colloquium on Humanities, Science and Engineering, CHUSER 2011. 2011. p. 265-269 6163730.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lim, ST, Wan Zaki, WMD, Hussain, A, Lim, SL & Kusalavan, S 2011, Automatic classification of diabetic macular edema in digital fundus images. in 2011 IEEE Colloquium on Humanities, Science and Engineering, CHUSER 2011., 6163730, pp. 265-269, 2011 IEEE Colloquium on Humanities, Science and Engineering, CHUSER 2011, Penang, 5/12/11. https://doi.org/10.1109/CHUSER.2011.6163730
Lim ST, Wan Zaki WMD, Hussain A, Lim SL, Kusalavan S. Automatic classification of diabetic macular edema in digital fundus images. In 2011 IEEE Colloquium on Humanities, Science and Engineering, CHUSER 2011. 2011. p. 265-269. 6163730 https://doi.org/10.1109/CHUSER.2011.6163730
Lim, S. T. ; Wan Zaki, Wan Mimi Diyana ; Hussain, Aini ; Lim, S. L. ; Kusalavan, S. / Automatic classification of diabetic macular edema in digital fundus images. 2011 IEEE Colloquium on Humanities, Science and Engineering, CHUSER 2011. 2011. pp. 265-269
@inproceedings{b9d3309ea218437db554d6dd0fb59ada,
title = "Automatic classification of diabetic macular edema in digital fundus images",
abstract = "Diabetic macular edema is a common complication of diabetic retinopathy due to the presence of exudates in proximity with the fovea. In this paper, an automated method to classify diabetic macular edema is presented. The fovea is localized and the regions of macula are marked based on the Early Treatment Diabetic Retinopathy Studies (ETDRS) grading scale. Extraction method using marker-controlled watershed transformation is adopted and modified from the previous research. The location of the extracted exudates on the marked macular regions is computed to classify diabetic macular edema into normal, stage 1 and stage 2 diabetic macular edema. The performance of the proposed method is evaluated using 88 images of publicly available MESSIDOR database. The overall sensitivity, specificity and accuracy of the proposed method are 80.9{\%}, 90.2{\%} and 85.2{\%}, respectively.",
keywords = "Exudates, Fovea localization, Severity level, Watershed transformation",
author = "Lim, {S. T.} and {Wan Zaki}, {Wan Mimi Diyana} and Aini Hussain and Lim, {S. L.} and S. Kusalavan",
year = "2011",
doi = "10.1109/CHUSER.2011.6163730",
language = "English",
isbn = "9781467300193",
pages = "265--269",
booktitle = "2011 IEEE Colloquium on Humanities, Science and Engineering, CHUSER 2011",

}

TY - GEN

T1 - Automatic classification of diabetic macular edema in digital fundus images

AU - Lim, S. T.

AU - Wan Zaki, Wan Mimi Diyana

AU - Hussain, Aini

AU - Lim, S. L.

AU - Kusalavan, S.

PY - 2011

Y1 - 2011

N2 - Diabetic macular edema is a common complication of diabetic retinopathy due to the presence of exudates in proximity with the fovea. In this paper, an automated method to classify diabetic macular edema is presented. The fovea is localized and the regions of macula are marked based on the Early Treatment Diabetic Retinopathy Studies (ETDRS) grading scale. Extraction method using marker-controlled watershed transformation is adopted and modified from the previous research. The location of the extracted exudates on the marked macular regions is computed to classify diabetic macular edema into normal, stage 1 and stage 2 diabetic macular edema. The performance of the proposed method is evaluated using 88 images of publicly available MESSIDOR database. The overall sensitivity, specificity and accuracy of the proposed method are 80.9%, 90.2% and 85.2%, respectively.

AB - Diabetic macular edema is a common complication of diabetic retinopathy due to the presence of exudates in proximity with the fovea. In this paper, an automated method to classify diabetic macular edema is presented. The fovea is localized and the regions of macula are marked based on the Early Treatment Diabetic Retinopathy Studies (ETDRS) grading scale. Extraction method using marker-controlled watershed transformation is adopted and modified from the previous research. The location of the extracted exudates on the marked macular regions is computed to classify diabetic macular edema into normal, stage 1 and stage 2 diabetic macular edema. The performance of the proposed method is evaluated using 88 images of publicly available MESSIDOR database. The overall sensitivity, specificity and accuracy of the proposed method are 80.9%, 90.2% and 85.2%, respectively.

KW - Exudates

KW - Fovea localization

KW - Severity level

KW - Watershed transformation

UR - http://www.scopus.com/inward/record.url?scp=84858985774&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858985774&partnerID=8YFLogxK

U2 - 10.1109/CHUSER.2011.6163730

DO - 10.1109/CHUSER.2011.6163730

M3 - Conference contribution

AN - SCOPUS:84858985774

SN - 9781467300193

SP - 265

EP - 269

BT - 2011 IEEE Colloquium on Humanities, Science and Engineering, CHUSER 2011

ER -