Efficient Bronchoscopic Video Summarization
Guided by the bronchoscope’s video stream, a physician can navigate the complex three-dimensional (3-D) airway tree to collect tissue samples or administer a disease treatment. Unfortunately, physicians currently discard procedural video because of the overwhelming amount of data generated. We propose a robust automatic method for summarizing an endobronchial video stream. Overall, the method derives a true hierarchical decomposition from a procedural video, consisting of a shot set and constituent keyframe set. Results show that our method more efficiently covers the observed endobronchial regions than other keyframe-selection approaches and facilitates direct fusion with a patient’s 3-D chest computed-tomography scan.
Methods for 2D and 3D Endobronchial Ultrasound Image Segmentation
We propose computer-based methods for segmenting 2D EBUS (Endobronchial ultrasound) frames and 3D EBUS sequences. Both segmentation methods compare very favorably to ground-truth results for a human lung-cancer patient EBUS database. We also demonstrate the potential of the methods for EBUS localization in a multimodal image-guided bronchoscopy system.