An Application Driven Comparison of Several Feature Extraction Algorithms in Bronchoscope Tracking During Navigated Bronchoscopy
نویسندگان
چکیده
This paper compares Kanade-Lucas-Tomasi (KLT), speeded up robust feature (SURF), and scale invariant feature transformation (SIFT) features applied to bronchoscope tracking. In our study, we first use KLT, SURF, or SIFT features and epipolar constraints to obtaininterframe translation (up to scale) and orientation displacements and Kalman filtering to recover an estimate for the magnitude of the motion (scale factor determination), and then multiply inter-frame motion parameters onto the previous pose of the bronchoscope camera to achieve the predicted pose, which is used to initialize intensity-based image registration to refine the current pose of the bronchoscope camera. We evaluate the KLT-, SURF-, and SIFT-based bronchoscope camera motion tracking methods on patient datasets. According to experimental results, we may conclude that SIFT features are more robust than KLT and SURF features at predicting the bronchoscope motion, and all methods for predicting the bronchoscope camera motion show a significant performance boost compared to sole intensity-based image registration without an additional position sensor.
منابع مشابه
Fiducial-Free Registration Procedure for Navigated Bronchoscopy
Navigated bronchoscopy has been developed by various groups within the last decades. Systems based on CT data and electromagnetic tracking enable the visualization of the position and orientation of the bronchoscope, forceps, and biopsy tools within CT data. Therefore registration between the tracking space and the CT volume is required. Standard procedures are based on point-based registration...
متن کاملManiSMC: A New Method Using Manifold Modeling and Sequential Monte Carlo Sampler for Boosting Navigated Bronchoscopy
This paper presents a new bronchoscope motion tracking method that utilizes manifold modeling and sequential Monte Carlo (SMC) sampler to boost navigated bronchoscopy. Our strategy to estimate the bronchoscope motions comprises two main stages: (1) bronchoscopic scene identification and (2) SMC sampling. We extend a spatial local and global regressive mapping (LGRM) method to Spatial-LGRM to le...
متن کاملA multimodal image guiding system for Navigated Ultrasound Bronchoscopy (EBUS): A human feasibility study
BACKGROUND Endobronchial ultrasound transbronchial needle aspiration (EBUS-TBNA) is the endoscopic method of choice for confirming lung cancer metastasis to mediastinal lymph nodes. Precision is crucial for correct staging and clinical decision-making. Navigation and multimodal imaging can potentially improve EBUS-TBNA efficiency. AIMS To demonstrate the feasibility of a multimodal image guid...
متن کاملReal-time motion compensation for EM bronchoscope tracking with smooth output - ex-vivo validation
Navigated bronchoscopy provides benefits for endoscopists and patients, but accurate tracking information is needed. We present a novel real-time approach for bronchoscope tracking combining electromagnetic (EM) tracking, airway segmentation, and a continuous model of output. We augment a previously published approach by including segmentation information in the tracking optimization instead of...
متن کاملGPU-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....
متن کامل