A plug-and-play framework for curvilinear structure segmentation based on a learned reconnecting regularization

TL;DR

This paper introduces an unsupervised, plug-and-play segmentation framework for curvilinear structures that learns a reconnecting regularization operator from synthetic data, improving connectivity preservation in various imaging applications.

Contribution

The paper presents a novel unsupervised framework that learns a reconnecting regularization operator for curvilinear structure segmentation, applicable without annotations.

Findings

Achieves approximately 90% connectivity preservation in 2D vascular segmentation.

Attains about 70% connectivity preservation in 3D vascular segmentation.

Demonstrates good generalization on road cracks and porcine corneal cells.

Abstract

Curvilinear structures are present in various fields in image processing such as blood vessels in medical imaging or roads in remote sensing. Their detection is crucial for many applications. In this article, we propose an unsupervised plug-and-play framework for the segmentation of curvilinear structures that focuses on the preservation of their connectivity. This framework includes an algorithm for generating realistic pairs of connected/disconnected curvilinear structures and a reconnecting regularization operator that can be learned from a synthetic dataset. Once learned, this regularization operator can be plugged into a variational segmentation scheme and used to segment curvilinear structure images without requiring annotations. We demonstrate the interest of our approach on the segmentation of vascular images both in 2D and 3D and compare its results with classic unsupervised and deep learning-based approach. Comparative evaluations against unsupervised classic and deep learning-based methods highlight the superior performance of our approach, showcasing remarkable improvements in preserving the connectivity of curvilinear structures (approximately 90% in 2D and 70% in 3D). We finally showcase the good generalizability behavior of our approach on two different applications : road cracks and porcine corneal cells segmentations.