Abstract
Accurate extraction of curve skeletons provides a compact one-dimensional representation of complex three-dimensional structures and plays a fundamental role in numerous medical image analysis and machine intelligence applications. Despite its importance, robust centerline extraction from volumetric medical images remains challenging, particularly in the presence of segmentation artifacts, small vessels, and complex vascular topology. In this work, we propose a fully automated framework for centerline detection of complex branching airway trees from 3D segmentation masks. Starting from a root node in the trachea, the method propagates two wavefronts with distinct cost functions: the first is used to identify terminal endpoints, while the second is used to trace the centerline paths back towards the root by following the medial structure of the airway tree. The proposed approach accurately recovers full airway topology, including branching points and tree hierarchy at arbitrary depth, and provides a robust out-of-the-box implementation applicable to any arbitrary 3D airway segmentation without additional adaptation. The source code is publicly available at https: //github.com/maltesilber/AirwayParser.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/TIA_031.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: Not Available
BibTex
@InProceedings{SilMal_MinimumCost_MICCAISAT2026,
author = { Silbernagel, Malte AND Petersen, Jens AND de Bruijne, Marleen},
title = { { Minimum-Cost Path Framework for 3D Airway Centerline Extraction } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17269},
month = {pending},
page = {pending}
}