BRANCH:Bifurcation Recognition for Airway Navigation based on struCtural cHaracteristics

Abstract

Bronchoscopic navigation is challenging, especially at the level of peripheral airways due to the complicated bronchial structures and the large respiratory motion. The aim of this paper is to propose a localisation approach tailored for navigation in the distal airway branches. Salient regions are detected on the depth maps of video images and CT virtual projections to extract anatomically meaningful areas that represent airway bifurcations. An airway descriptor based on shape context is introduced which encodes both the structural characteristics of the bifurcations and their spatial distribution. The bronchoscopic camera is localised in the airways by minimising the cost of matching the region features in video images to the pre-computed CT depth maps considering both the shape and temporal information. The method has been validated on phantom and in vivo data and the results verify its robustness to tissue deformation and good performance in distal airways.

Generative Localization With Uncertainty Estimation Through Video-CT Data for Bronchoscopic Biopsy

“…Various similarity measures based on image intensity [1], gradient [15][2], depth [3] or airway lumen features [16][17] [4] have been investigated to improve the registration accuracy.…”

Context-Aware Depth and Pose Estimation for Bronchoscopic Navigation

“…The imagebased registration approaches are more robust to respiratory motion because the scope moves with the airway simultaneously [6]. The similarity metric can be based on image intensity [6], [7], gradient [8], [14], depth [9] or airway lumen features [15]. The similarity in terms of image intensity proposed in [6], [7] requires the generation of realistic renderings from the CT airway model.…”

“…Instead of using image intensity, several attempts transform the registration into pq space [8], [14] or depth maps [9] which are more texture-independent while better preserving the morphology of airway bifurcations. Since pixel-based image registration is computationally expensive, more efficient localization methods based on airway lumen detection [15], [16] are developed for navigation at distal airways where multiple bifurcations can be observed. Among these methods, 2D/3D registration based on depth is invariant to surface texture and it preserves the rich morphological information of the scene.…”

Autonomous Driving in the Lung using Deep Learning for Localization

“…Methods like SIFT and ORBSLAM have been used, but the airways have insufficient features and tracked features often drop out [11], [12]. Anatomical landmarks have been tracked, like bifurcations [13], lumen centers [14], centerline paths [15], or similar image regions [16], but these approaches may not operate in real-time and tend make assumptions about the airway geometries using traditional computer vision techniques.…”