A New Coherence-Penalized Minimal Path Model with Application to Retinal Vessel Centerline Delineation

TL;DR

This paper introduces a novel coherence-penalized minimal path model for retinal vessel centerline extraction, improving accuracy by reducing short branch and shortcut issues through a new Riemannian metric.

Contribution

The paper presents a new coherence-penalized Riemannian metric in a lifted space for minimal path modeling, specifically designed for retinal vessel segmentation.

Findings

Achieves promising results on DRIVE and IOSTAR datasets.

Effectively reduces short branch and shortcut problems.

Outperforms existing minimal path models in retinal imaging.

Abstract

In this paper, we propose a new minimal path model for minimally interactive retinal vessel centerline extraction. The main contribution lies at the construction of a novel coherence-penalized Riemannian metric in a lifted space, dependently of the local geometry of tubularity and an external scalar-valued reference feature map. The globally minimizing curves associated to the proposed metric favour to pass through a set of retinal vessel segments with low variations of the feature map, thus can avoid the short branches combination problem and shortcut problem, commonly suffered by the existing minimal path models in the application of retinal imaging. We validate our model on a series of retinal vessel patches obtained from the DRIVE and IOSTAR datasets, showing that our model indeed get promising results.