Automatic generation of synthetic retinal fundus images

Samuele Fiorini, Lucia Ballerini, Emanuele Trucco, Alfredo Ruggeri

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


This study aims to generate synthetic and realistic retinal fundus colour images, similar in characteristics to a given dataset, as well as the values of all morphological parameters. A representative task could be, for example, the synthesis of a retinal image with the corresponding vessel tree and optic nerve head binary map, measurement of vessel width in any position, fovea localisation and so on. The presented paper mainly focuses on the generation of non vascular regions (i.e. retinal background, fovea and optic disc) and it is complemented by a parallel study on the generation of structure and texture of the vessel network. To synthesise convincing retinal backgrounds and foveae, a patch-based algorithm has been developed; model-based texture synthesis techniques have also been implemented for the generation of realistic optic discs. The validity of our synthetic retinal images has been demonstrated by visual inspection and quantitative experiments.
Original languageEnglish
Title of host publicationMedical Image Understanding and Analysis 2014
Subtitle of host publicationProceedings of the 18th Conference on Medical Image Understanding and Analysis
EditorsConstantino Carlos Reyes-Aldasoro, Greg Slabaugh
Place of PublicationLondon
PublisherBMVA Press
Number of pages6
ISBN (Print)1901725510
Publication statusPublished - 2014
Event18th Annual Conference in Medical Image Understanding and Analysis - Moore Complex, Royal Holloway, London, United Kingdom
Duration: 9 Jul 201411 Jul 2014


Conference18th Annual Conference in Medical Image Understanding and Analysis
Abbreviated titleMIUA 2014
Country/TerritoryUnited Kingdom
Internet address


Dive into the research topics of 'Automatic generation of synthetic retinal fundus images'. Together they form a unique fingerprint.

Cite this