Skip to Main content Skip to Navigation
New interface
Conference papers

Learning fully-connected CRFs for blood vessel segmentation in retinal images

Abstract : In this work, we present a novel method for blood vessel segmentation in fundus images based on a discriminatively trained, fully connected conditional random field model. Retinal image analysis is greatly aided by blood vessel segmentation as the vessel structure may be considered both a key source of signal, e.g. in the diagnosis of diabetic retinopathy, or a nuisance, e.g. in the analysis of pigment epithelium or choroid related abnormalities. Blood vessel segmentation in fundus images has been considered extensively in the literature, but remains a challenge largely due to the desired structures being thin and elongated, a setting that performs particularly poorly using standard segmentation priors such as a Potts model or total variation. In this work, we overcome this difficulty using a discriminatively trained conditional random field model with more expressive potentials. In particular, we employ recent results enabling extremely fast inference in a fully connected model. We find that this rich but computationally efficient model family, combined with principled discriminative training based on a structured output support vector machine yields a fully automated system that achieves results statistically indistinguishable from an expert human annotator. Implementation details are available at
Complete list of metadata

Cited literature [29 references]  Display  Hide  Download
Contributor : Matthew Blaschko Connect in order to contact the contributor
Submitted on : Thursday, July 17, 2014 - 10:35:41 AM
Last modification on : Friday, January 21, 2022 - 3:01:24 AM
Long-term archiving on: : Monday, November 24, 2014 - 1:21:20 PM


Files produced by the author(s)




José Ignacio Orlando, Matthew Blaschko. Learning fully-connected CRFs for blood vessel segmentation in retinal images. Medical Image Computing and Computer Assisted Intervention (MICCAI), Sep 2014, Boston, United States. ⟨10.1007/978-3-319-10404-1_79⟩. ⟨hal-01024226⟩



Record views


Files downloads