Retinal artery/vein classification via graph cut optimization

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

158 Downloads (Pure)


In many diseases with a cardiovascular component, the geometry of microvascular blood vessels changes. These changes are specific to arteries and veins, and can be studied in the microvasculature of the retina using retinal photography. To facilitate large-scale studies of artery/vein-specific changes in the retinal vasculature, automated classification of the vessels is required. Here we present a novel method for artery/vein classification based on local and contextual feature analysis of retinal vessels. For each vessel, local information in the form of a transverse intensity profile is extracted. Crossings and bifurcations of vessels provide contextual information. The local and contextual features are integrated into a non-submodular energy function, which is optimized exactly using graph cuts. The method was validated on a ground truth data set of 150 retinal fundus images, achieving an accuracy of 88.0% for all vessels and 94.0% for the six arteries and six veins with highest caliber in the image.
Original languageEnglish
Title of host publicationProceedings of the Ophthalmic Medical Image Analysis Second International Workshop, OMIA 2015
EditorsX. Chen, M.K. Garvin, J. Liu, E. Trucco, Y. Xu
Publication statusPublished - 2015
Event2015 Ophthalmic Medical Image Analysis Second International Workshop (OMIA 2015) - Munich, Germany
Duration: 9 Oct 20159 Oct 2015
Conference number: 2


Conference2015 Ophthalmic Medical Image Analysis Second International Workshop (OMIA 2015)
Abbreviated titleOMIA 2015
Internet address


Dive into the research topics of 'Retinal artery/vein classification via graph cut optimization'. Together they form a unique fingerprint.

Cite this