Coordinate-based fast lightweight path search algorithm for electromagnetic navigation bronchoscopy

Area of Science:

• Medical Imaging
• Computer-Aided Diagnosis
• Pulmonary Medicine

Background:

• Electromagnetic navigation bronchoscopy (ENB) requires precise path planning for accurate lesion targeting.
• High-resolution lung CT data and complex bronchial anatomy pose challenges for existing path search algorithms.

Purpose of the Study:

• To develop and evaluate a novel, fast, and lightweight path search algorithm for ENB.
• To address the computational challenges in planning navigation paths within the bronchial tree.

Main Methods:

• A coordinate-based fast lightweight path search (CPS) algorithm was developed.
• Topological thinning was used to extract bronchial tree centerlines.
• Euclidean distance was employed for efficient pathfinding along the extracted centerlines.

Main Results:

• The CPS algorithm achieved 100% accuracy in path search.
• Average search time was 88.5 ms, a significant reduction compared to Dijkstra and A* algorithms.
• Average memory consumption was 166.0 MB, substantially lower than traditional methods.

Conclusions:

• The CPS algorithm offers a highly accurate and efficient solution for path planning in ENB.
• This method is well-suited for navigating the multilevel branching bronchial tree using high-resolution lung CT images.
• CPS demonstrates superior performance in terms of speed and memory efficiency for ENB applications.