Stable Anatomical Structure Tracking for Video-Bronchoscopy Navigation

Bronchoscopy allows to examine the patient airways for detection of lesions and sampling of tissues without surgery. A main drawback in lung cancer diagnosis is the difficulty to check whether the exploration is following the correct path to the nodule that has to be biopsied. The most extended guidance uses fluoroscopy which implies repeated radiation of clinical staff and patients. Alternatives such as virtual bronchoscopy or electromagnetic navigation are very expensive and not completely robust to blood, mocus or deformations as to be extensively used. We propose a method that extracts and tracks stable lumen regions at different levels of the bronchial tree. The tracked regions are stored in a tree that encodes the anatomical structure of the scene which can be useful to retrieve the path to the lesion that the clinician should follow to do the biopsy. We present a multi-expert validation of our anatomical landmark extraction in 3 intra-operative ultrathin explorations.