VEELA: A Clinically-Constrained Benchmark for Liver Vessel Segmentation in Computed Tomography Angiography

2026-05-21

AI Summary

This study addresses the challenges of segmenting hepatic vasculature and portal veins in contrast-enhanced CT angiography, where complex topology, poor peripheral enhancement, and imaging artifacts hinder accurate delineation. To tackle these issues, the authors introduce VEELA, a high-quality dataset comprising 40 CTA scans, annotated through a multi-expert consensus protocol with a visibility-driven strategy that avoids anatomical interpolation and explicitly incorporates clinical realism to capture anatomical variations and imaging uncertainty. A standardized benchmark framework is established via meticulous slice-by-slice manual annotation and comprehensive multi-dimensional evaluation using clDice, IoU, normalized surface dice (NSD), and geometric metrics. The publicly released dataset and evaluation platform demonstrate the complementary nature of these metrics in characterizing vascular completeness, thereby laying a foundation for reproducible and robust vascular segmentation research.

Abstract

Accurate segmentation of hepatic and portal vessels in contrast-enhanced computed tomography angiography (CTA) remains challenging due to complex vascular topology, peripheral visibility limitations, and acquisition-induced ambiguities. While existing public datasets offer valuable benchmarks, few include clinically realistic annotation constraints. We introduce VEELA (Vessel Extraction and Extrication for Liver Analysis), a rigorously curated liver vessel dataset derived from 40 CTA scans inherited from the CHAOS grand-challenge cohort. All vessels were manually delineated slice-by-slice under multi-expert consensus, using a strict visibility-driven annotation policy and avoiding anatomically inferred interpolation. This design explicitly captures anatomical variability and imaging-related uncertainty. As a continuation of the CHAOS challenge, VEELA enables reproducible cross-benchmark evaluation while extending the scope to fine-grained hepatic and portal vessel segmentation. We further establish a standardized benchmarking framework and analyze complementary evaluation metrics, including topology-aware (clDice), overlap-based (IoU), boundary-sensitive (NSD), and geometry-aware (area, length) measures. Our results demonstrate that different metrics capture distinct aspects of vascular integrity, underscoring the necessity of multi-perspective evaluation for clinically meaningful vessel segmentation. VEELA is publicly released to facilitate reproducible research and support the development of robust vascular segmentation methods. Researchers can access the evaluation metrics, dataset, and submission platform at https://www.synapse.org/Synapse:syn65471967.

Problem

• liver vessel segmentation
• computed tomography angiography
• clinical annotation constraints
• vascular topology
• imaging ambiguity

Innovation

• clinically-constrained annotation
• visibility-driven segmentation
• multi-metric vascular evaluation
• hepatic vessel benchmarking
• topology-aware metrics