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 language | English (US) |
---|---|
Pages (from-to) | 1026-1043 |
Number of pages | 18 |
Journal | Medical Image Analysis |
Volume | 18 |
Issue number | 7 |
DOIs | |
State | Published - 2014 |
Externally published | Yes |
Fingerprint
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
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 journal › Article
}
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 -