FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASE

Etienne Decencière (1) , Xiwei Zhang (1) , Guy Cazuguel (2) , Bruno Laÿ (3) , Béatrice Cochener (4, 5) , Caroline Trone (6) , Philippe Gain (6) , John-Richard Ordóñez-Varela (1) , Pascale Massin (7) , Ali Erginay (7) , Béatrice Charton (8) , Jean-Claude Klein (1)

1 CMM - Centre de Morphologie Mathématique
2 LaTIM - Laboratoire de Traitement de l'Information Medicale
3 ADCIS - Société ADCIS
4 Service d'ophtalmologie [Brest]
5 LaTIM - Laboratoire de Traitement de l'Information Medicale
6 Service d’Ophtalmologie [CHU Saint-Etienne]
7 Service d'Ophtalmologie - Service d'Ophtalmologie, Hôpital Lariboisière, AP-HP
8 CRIHAN - Centre de Ressources Informatiques de Haute-Normandie, France

The Messidor database, which contains hundreds of eye fundus images, has been publicly distributed since 2008. It was created by the Messidor project in order to evaluate automatic lesion segmentation and diabetic retinopathy grading methods. Designing, producing and maintaining such a database entails significant costs. By publicly sharing it, one hopes to bring a valuable resource to the public research community. However, the real interest and benefit of the research community is not easy to quantify. We analyse here the feedback on the Messidor database, after more than 6 years of diffusion. This analysis should apply to other similar research databases.

Mots clés: Image database; Messidor; diabetic retinopathy; image processing

Domaines: Traitement des images [eess.IV]

Etienne Decencière, Xiwei Zhang, Guy Cazuguel, Bruno Laÿ, Béatrice Cochener, et al.. FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASE. Image Analysis & Stereology, 2014, pp.231-234. ⟨10.5566/ias.1155⟩. ⟨hal-01082570⟩