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

• Published in: Medical image analysis Vol. 18; no. 7; pp. 1026 - 1043
• Main Authors: 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
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.10.2014; Elsevier
• Subjects: Algorithms; Calibration; Color; Computer Science; Diabetic Retinopathy - diagnosis; Diabetic retinopathy screening; e-Ophtha EX database; Exudates and Transudates; Exudates segmentation; Humans; Image Interpretation, Computer-Assisted - methods; Image Processing; Mass Screening - methods; Mathematical morphology; Reproducibility of Results; Sensitivity and Specificity; e-Ophtha EX database; Exudates segmentation; Diabetic retinopathy screening; Mathematical morphology; Diabetic Retinopathy screening; e-ophtha EX database; Exudates Segmentation; Mathematical Morphology
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2014.05.004

[Display omitted] •We introduce a new database, e-ophtha EX, with precisely manually contoured exudates.•We propose a new exudate segmentation method based on mathematical morphology.•The method preforms normalization, denoising and detecting reflections and artifacts.•New contextual features are used to train a random forest for the classification.•The method achieves an area under ROC curve of 0.95 on e-ophtha EX database. 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.