← Back to all news
arXiv Computer Vision By Salvatore Esposito, Daniel Rebain, Arno Onken, Changjian Li, Oisin Mac Aodha

VesselSDF: Distance Field Priors for Vascular Network Reconstruction

Read the original on arXiv Computer Vision →

VesselSDF introduces a new framework that transforms vessel segmentation into a signed distance field (SDF) regression task, enabling continuous representation of vascular geometry. By employing an adaptive Gaussian regularizer, the method suppresses common SDF artifacts such as floating segments while maintaining precise vessel boundaries. Experimental results show that VesselSDF outperforms existing approaches, preserving vessel geometry and connectivity for more reliable clinical vascular analysis.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Sep 28

ReG-SAM: Reference Graph-Driven SAM for 2D Foundational Vessel Segmentation

ReG-SAM is a SAM-based framework designed for 2D vessel segmentation in medical images. It introduces reference graph prompt embeddings (GPEs) and vascular prototype embeddings (VPEs) to capture global spatial and fine-grained modality-specific vessel features, respectively. By building a modality-wise vascular database and learning these embeddings from reference masks, ReG-SAM consistently outperforms existing baselines across 19 datasets, especially on thin vessels.

By Donghang Lyu, Zichen Zhang, Oleh Dzyubachyk, Marius Staring
ragcomputer-vision
More like this →
Hugging Face Trending Papers
Jul 25

Investigating the Visual Cues of CNNs for Vascular Segmentation: A Case Study in Microscopy and Fundus Imaging

Vascular segmentation is a standard procedure for clinical diagnosis, yet the specific visual features determining model decisions remain poorly understood. This paper investigates the visual cues Convolutional Neural Networks (CNNs) use to segment blood vessels across two distinct imaging domains: fluorescence microscopy and retinal fundus photography.

computer-vision
More like this →