Online Topological Localization for Navigation Assistance in Bronchoscopy

2025-10-10

AI Summary

During bronchoscopy, real-time anatomical localization remains challenging due to the complex airway geometry and absence of intraoperative anatomical landmarks. Existing navigation systems rely on preoperative patient-specific CT reconstructions and auxiliary sensors, resulting in high cost and limited clinical accessibility. This paper proposes a CT-free, image-driven topological localization method. Leveraging a deep learning–based image matching framework trained exclusively on synthetic bronchial tree phantom data, it achieves end-to-end topological localization directly from real bronchoscopy video. An online inference pipeline maps observed frames to hierarchical anatomical locations on a generic airway model. Crucially, the approach eliminates dependence on patient-specific CT scans and manual annotations. Evaluated on real bronchoscopy sequences, it demonstrates significantly higher localization accuracy and robustness compared to state-of-the-art methods, thereby enhancing the clinical feasibility, real-time performance, and broad applicability of navigation-assisted bronchoscopy.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Video bronchoscopy is a fundamental procedure in respiratory medicine, where medical experts navigate through the bronchial tree of a patient to diagnose or operate the patient. Surgeons need to determine the position of the scope as they go through the airway until they reach the area of interest. This task is very challenging for practitioners due to the complex bronchial tree structure and varying doctor experience and training. Navigation assistance to locate the bronchoscope during the procedure can improve its outcome. Currently used techniques for navigational guidance commonly rely on previous CT scans of the patient to obtain a 3D model of the airway, followed by tracking of the scope with additional sensors or image registration. These methods obtain accurate locations but imply additional setup, scans and training. Accurate metric localization is not always required, and a topological localization with regard to a generic airway model can often suffice to assist the surgeon with navigation. We present an image-based bronchoscopy topological localization pipeline to provide navigation assistance during the procedure, with no need of patient CT scan. Our approach is trained only on phantom data, eliminating the high cost of real data labeling, and presents good generalization capabilities. The results obtained surpass existing methods, particularly on real data test sequences.

Problem

• Online topological localization for bronchoscopy navigation assistance
• Eliminating dependency on patient CT scans during procedures
• Training solely on phantom data to reduce costs

Innovation

• Image-based topological localization without CT scans
• Trained solely on phantom data for cost efficiency
• Generalizes well to real bronchoscopy procedures