Retinal vessel segmentation by probing adaptive to lighting variations

Guillaume Noyel (1, 2, 3) , Christine Vartin (4) , Peter Boyle (1, 2, 3) , Laurent Kodjikian (5, 4)

1 IPRI - International Prevention Research Institute
2 SIGPH@iPRI - University of Strathclyde Institute of Global Public Health
3 University of Strathclyde [Glasgow]
4 HCL - Hospices Civils de Lyon
5 MATEIS - Matériaux, ingénierie et science [Villeurbanne]

We introduce a novel method to extract the vessels in eye fundus images which is adaptive to lighting variations. In the Logarithmic Image Processing framework, a 3-segment probe detects the vessels by probing the topographic surface of an image from below. A map of contrasts between the probe and the image allows to detect the vessels by a threshold. In a lowly contrasted image, results show that our method better extract the vessels than another state-of the-art method. In a highly contrasted image database (DRIVE) with a reference , ours has an accuracy of 0.9454 which is similar or better than three state-of-the-art methods and below three others. The three best methods have a higher accuracy than a manual segmentation by another expert. Importantly, our method automatically adapts to the lighting conditions of the image acquisition.

Keywords: Eye fundus images; Vessel segmentation; Lighting variations; Mathematical Morphology; Logarithmic Image Processing; Diabetic Retinopathy

Domains: Signal and Image processing; Numerical Analysis [math.NA]; Computer Vision and Pattern Recognition [cs.CV]; Medical Physics [physics.med-ph]; Santé publique et épidémiologie

Guillaume Noyel, Christine Vartin, Peter Boyle, Laurent Kodjikian. Retinal vessel segmentation by probing adaptive to lighting variations. 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), IEEE, Apr 2020, Iowa City, United States. pp.1246-1249, ⟨10.1109/ISBI45749.2020.9098332⟩. ⟨hal-02556835⟩