Retrieving challenging vessel connections in retinal images by line co-occurrence statistics

TL;DR

This paper introduces a novel method using line co-occurrence statistics and probabilistic modeling to automatically recover disconnected blood vessel structures in retinal images, inspired by visual cortex connectivity patterns.

Contribution

It presents a new statistical approach for vessel connection recovery in retinal images, leveraging a probabilistic model trained on vessel centerlines and validated across datasets.

Findings

High similarity of statistical models across datasets

Successful grouping of interrupted vessels in challenging patches

Approximation of the model with less than 2% error

Abstract

Natural images contain often curvilinear structures, which might be disconnected, or partly occluded. Recovering the missing connection of disconnected structures is an open issue and needs appropriate geometric reasoning. We propose to find line co-occurrence statistics from the centerlines of blood vessels in retinal images and show its remarkable similarity to a well-known probabilistic model for the connectivity pattern in the primary visual cortex. Furthermore, the probabilistic model is trained from the data via statistics and used for automated grouping of interrupted vessels in a spectral clustering based approach. Several challenging image patches are investigated around junction points, where successful results indicate the perfect match of the trained model to the profiles of blood vessels in retinal images. Also, comparisons among several statistical models obtained from different datasets reveals their high similarity i.e., they are independent of the dataset. On top of that, the best approximation of the statistical model with the symmetrized extension of the probabilistic model on the projective line bundle is found with a least square error smaller than 2%. Apparently, the direction process on the projective line bundle is a good continuation model for vessels in retinal images.