Exudate detection in color retinal images for mass screening of diabetic retinopathy

Xiwei Zhang, Guillaume Thibault, Etienne Decencière, Beatriz Marcotegui, Bruno Laÿ, Ronan Danno, Guy Cazuguel, Gwénolé Quellec, Mathieu Lamard, Pascale Massin, Agnès Chabouis, Zeynep Victor, Ali Erginay

Research output: Contribution to journalArticle

132 Citations (Scopus)

Abstract

The automatic detection of exudates in color eye fundus images is an important task in applications such as diabetic retinopathy screening. The presented work has been undertaken in the framework of the TeleOphta project, whose main objective is to automatically detect normal exams in a tele-ophthalmology network, thus reducing the burden on the readers. A new clinical database, e-ophtha EX, containing precisely manually contoured exudates, is introduced. As opposed to previously available databases, e-ophtha EX is very heterogeneous. It contains images gathered within the OPHDIAT telemedicine network for diabetic retinopathy screening. Image definition, quality, as well as patients condition or the retinograph used for the acquisition, for example, are subject to important changes between different examinations. The proposed exudate detection method has been designed for this complex situation. We propose new preprocessing methods, which perform not only normalization and denoising tasks, but also detect reflections and artifacts in the image. A new candidates segmentation method, based on mathematical morphology, is proposed. These candidates are characterized using classical features, but also novel contextual features. Finally, a random forest algorithm is used to detect the exudates among the candidates. The method has been validated on the e-ophtha EX database, obtaining an AUC of 0.95. It has been also validated on other databases, obtaining an AUC between 0.93 and 0.95, outperforming state-of-the-art methods.

Original languageEnglish (US)
Pages (from-to)1026-1043
Number of pages18
JournalMedical Image Analysis
Volume18
Issue number7
DOIs
StatePublished - 2014
Externally publishedYes

Fingerprint

Mass Screening
Diabetic Retinopathy
Exudates and Transudates
Screening
Color
Databases
Area Under Curve
Ophthalmology
Mathematical morphology
Telemedicine
Eye Color
Artifacts

Keywords

  • Diabetic retinopathy screening
  • E-Ophtha EX database
  • Exudates segmentation
  • Mathematical morphology

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Radiology Nuclear Medicine and imaging
  • Health Informatics
  • Radiological and Ultrasound Technology
  • Medicine(all)

Cite this

Zhang, X., Thibault, G., Decencière, E., Marcotegui, B., Laÿ, B., Danno, R., ... Erginay, A. (2014). Exudate detection in color retinal images for mass screening of diabetic retinopathy. Medical Image Analysis, 18(7), 1026-1043. https://doi.org/10.1016/j.media.2014.05.004

Exudate detection in color retinal images for mass screening of diabetic retinopathy. / Zhang, Xiwei; Thibault, Guillaume; Decencière, Etienne; Marcotegui, Beatriz; Laÿ, Bruno; Danno, Ronan; Cazuguel, Guy; Quellec, Gwénolé; Lamard, Mathieu; Massin, Pascale; Chabouis, Agnès; Victor, Zeynep; Erginay, Ali.

In: Medical Image Analysis, Vol. 18, No. 7, 2014, p. 1026-1043.

Research output: Contribution to journalArticle

Zhang, X, Thibault, G, Decencière, E, Marcotegui, B, Laÿ, B, Danno, R, Cazuguel, G, Quellec, G, Lamard, M, Massin, P, Chabouis, A, Victor, Z & Erginay, A 2014, 'Exudate detection in color retinal images for mass screening of diabetic retinopathy', Medical Image Analysis, vol. 18, no. 7, pp. 1026-1043. https://doi.org/10.1016/j.media.2014.05.004
Zhang, Xiwei ; Thibault, Guillaume ; Decencière, Etienne ; Marcotegui, Beatriz ; Laÿ, Bruno ; Danno, Ronan ; Cazuguel, Guy ; Quellec, Gwénolé ; Lamard, Mathieu ; Massin, Pascale ; Chabouis, Agnès ; Victor, Zeynep ; Erginay, Ali. / Exudate detection in color retinal images for mass screening of diabetic retinopathy. In: Medical Image Analysis. 2014 ; Vol. 18, No. 7. pp. 1026-1043.
@article{94c7b5457106476aa99dbfb7aee20a7a,
title = "Exudate detection in color retinal images for mass screening of diabetic retinopathy",
abstract = "The automatic detection of exudates in color eye fundus images is an important task in applications such as diabetic retinopathy screening. The presented work has been undertaken in the framework of the TeleOphta project, whose main objective is to automatically detect normal exams in a tele-ophthalmology network, thus reducing the burden on the readers. A new clinical database, e-ophtha EX, containing precisely manually contoured exudates, is introduced. As opposed to previously available databases, e-ophtha EX is very heterogeneous. It contains images gathered within the OPHDIAT telemedicine network for diabetic retinopathy screening. Image definition, quality, as well as patients condition or the retinograph used for the acquisition, for example, are subject to important changes between different examinations. The proposed exudate detection method has been designed for this complex situation. We propose new preprocessing methods, which perform not only normalization and denoising tasks, but also detect reflections and artifacts in the image. A new candidates segmentation method, based on mathematical morphology, is proposed. These candidates are characterized using classical features, but also novel contextual features. Finally, a random forest algorithm is used to detect the exudates among the candidates. The method has been validated on the e-ophtha EX database, obtaining an AUC of 0.95. It has been also validated on other databases, obtaining an AUC between 0.93 and 0.95, outperforming state-of-the-art methods.",
keywords = "Diabetic retinopathy screening, E-Ophtha EX database, Exudates segmentation, Mathematical morphology",
author = "Xiwei Zhang and Guillaume Thibault and Etienne Decenci{\`e}re and Beatriz Marcotegui and Bruno La{\"y} and Ronan Danno and Guy Cazuguel and Gw{\'e}nol{\'e} Quellec and Mathieu Lamard and Pascale Massin and Agn{\`e}s Chabouis and Zeynep Victor and Ali Erginay",
year = "2014",
doi = "10.1016/j.media.2014.05.004",
language = "English (US)",
volume = "18",
pages = "1026--1043",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",
number = "7",

}

TY - JOUR

T1 - Exudate detection in color retinal images for mass screening of diabetic retinopathy

AU - Zhang, Xiwei

AU - Thibault, Guillaume

AU - Decencière, Etienne

AU - Marcotegui, Beatriz

AU - Laÿ, Bruno

AU - Danno, Ronan

AU - Cazuguel, Guy

AU - Quellec, Gwénolé

AU - Lamard, Mathieu

AU - Massin, Pascale

AU - Chabouis, Agnès

AU - Victor, Zeynep

AU - Erginay, Ali

PY - 2014

Y1 - 2014

N2 - The automatic detection of exudates in color eye fundus images is an important task in applications such as diabetic retinopathy screening. The presented work has been undertaken in the framework of the TeleOphta project, whose main objective is to automatically detect normal exams in a tele-ophthalmology network, thus reducing the burden on the readers. A new clinical database, e-ophtha EX, containing precisely manually contoured exudates, is introduced. As opposed to previously available databases, e-ophtha EX is very heterogeneous. It contains images gathered within the OPHDIAT telemedicine network for diabetic retinopathy screening. Image definition, quality, as well as patients condition or the retinograph used for the acquisition, for example, are subject to important changes between different examinations. The proposed exudate detection method has been designed for this complex situation. We propose new preprocessing methods, which perform not only normalization and denoising tasks, but also detect reflections and artifacts in the image. A new candidates segmentation method, based on mathematical morphology, is proposed. These candidates are characterized using classical features, but also novel contextual features. Finally, a random forest algorithm is used to detect the exudates among the candidates. The method has been validated on the e-ophtha EX database, obtaining an AUC of 0.95. It has been also validated on other databases, obtaining an AUC between 0.93 and 0.95, outperforming state-of-the-art methods.

AB - The automatic detection of exudates in color eye fundus images is an important task in applications such as diabetic retinopathy screening. The presented work has been undertaken in the framework of the TeleOphta project, whose main objective is to automatically detect normal exams in a tele-ophthalmology network, thus reducing the burden on the readers. A new clinical database, e-ophtha EX, containing precisely manually contoured exudates, is introduced. As opposed to previously available databases, e-ophtha EX is very heterogeneous. It contains images gathered within the OPHDIAT telemedicine network for diabetic retinopathy screening. Image definition, quality, as well as patients condition or the retinograph used for the acquisition, for example, are subject to important changes between different examinations. The proposed exudate detection method has been designed for this complex situation. We propose new preprocessing methods, which perform not only normalization and denoising tasks, but also detect reflections and artifacts in the image. A new candidates segmentation method, based on mathematical morphology, is proposed. These candidates are characterized using classical features, but also novel contextual features. Finally, a random forest algorithm is used to detect the exudates among the candidates. The method has been validated on the e-ophtha EX database, obtaining an AUC of 0.95. It has been also validated on other databases, obtaining an AUC between 0.93 and 0.95, outperforming state-of-the-art methods.

KW - Diabetic retinopathy screening

KW - E-Ophtha EX database

KW - Exudates segmentation

KW - Mathematical morphology

UR - http://www.scopus.com/inward/record.url?scp=84902983161&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902983161&partnerID=8YFLogxK

U2 - 10.1016/j.media.2014.05.004

DO - 10.1016/j.media.2014.05.004

M3 - Article

C2 - 24972380

AN - SCOPUS:84902983161

VL - 18

SP - 1026

EP - 1043

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 7

ER -