GPU-Based Airway Segmentation and Centerline Extraction for Image Guided Bronchoscopy

Bronchoscopy is an important minimal-invasive procedure for both diagnosis and therapy of several lung disorders, including lung cancer. However, narrow airways and complex branching structure increases the difficulty of navigating to the target site inside the lungs. It is possible to improve navigation by extracting a map of the airways from CT images and tracking the tip of the bronchoscope. Most of the methods for extracting such maps are computationally expensive and have a long runtime. In this paper, we present an implementation of airway segmentation and centerline extraction, which utilizes the computational power of modern graphic processing units. We also present a novel parallel cropping algorithm which discards over 70% of the dataset as non-lung tissue, thus significantly reducing memory usage and processing time.