Related Experiment Video
Updated: Aug 14, 2026
A Full Skin Defect Model to Evaluate Vascularization of Biomaterials In Vivo
Published on: August 28, 2014
Towards Fixing Vessel Segmentation Breakage: A Systematic Review
Sébastien Goffart1,2, Hervé Delingette1,3, Andrea Chierici2,4,5
1Epione Team, Inria, Université Côte d'Azur, Sophia Antipolis, 06000 Nice, France.
Insights
Accurate arterial tree reconstruction from computed tomography angiography (CTA) faces vessel discontinuity challenges. Hybrid deep learning and geodesic methods offer the best solutions for continuous vascular segmentation.
Area of Science:
- Medical Imaging
- Computational Anatomy
- Vascular Imaging
Background:
- Accurate arterial tree reconstruction from computed tomography angiography (CTA) is crucial for clinical applications.
- Vessel discontinuity, where thin branches appear disconnected, is a significant challenge in CTA segmentation.
- This problem arises from factors like bifurcations, noise, and imaging artifacts.
Purpose of the Study:
- To systematically review computational methods for addressing vessel discontinuity in CTA segmentation.
- To identify current gaps in research and methodologies for improving vascular segmentation accuracy.
Main Methods:
- A scoping review following PRISMA-ScR guidelines was performed.
- Searches were conducted on Google Scholar and PubMed for studies from March 2000 to March 2026.
- Eligible studies included peer-reviewed articles and conference proceedings on 3D vascular segmentation from CTA.
Main Results:
- Three generations of computational solutions were identified: geometric/geodesic methods, topology-aware deep learning, and hybrid post-processing frameworks.
- Topology-sensitive metrics (e.g., clDice, Topology Sensitivity) are preferred over standard metrics like Dice coefficient for evaluating clinical utility.
- Hybrid frameworks combining deep learning with geodesic restoration are the current state-of-the-art.
Conclusions:
- Vessel discontinuity remains a critical challenge in vascular CTA segmentation.
- Hybrid post-processing frameworks represent the most advanced solutions.
- Adopting topology-aware metrics is recommended for future studies to better assess clinical relevance.
Abstract:
Background/Objectives: Accurate arterial tree reconstruction from computed tomography angiography (CTA) is essential for vascular diagnosis, surgical planning, and hemodynamic modelling. A persistent and underappreciated problem is vessel discontinuity: thin distal branches appear as disconnected fragments rather than continuous structures, caused by bifurcations, image noise, contrast variation, arterial plaque, motion artifacts, and partial volume effects. This scoping review aimed to systematically characterize computational approaches addressing vessel breakage in CTA segmentation and identify methodological gaps warranting further investigation. Methods: This scoping review was conducted in accordance with PRISMA-ScR guidelines. Google Scholar and PubMed were queried for studies published between March 2000 and March 2026. Eligible studies included peer-reviewed journal articles and conference proceedings presenting original methodological contributions to three-dimensional vascular segmentation from CTA. Results: Three generations of computational solutions were identified: classical geometric and geodesic methods, deep learning approaches with topology-aware training, and hybrid post-processing frameworks. Topology-sensitive metrics (clDice, Topology Sensitivity) were identified as preferred metrics to better capture clinical utility than standard voxel-based metrics such as the Dice coefficient. Conclusions: Vessel discontinuity remains a clinically relevant and challenge in vascular CTA segmentation. Hybrid post-processing frameworks combining deep learning with geodesic connectivity restoration represent the current state of the art. Standardized adoption of topology-aware evaluation metrics is recommended to better reflect clinical utility in future studies.
