Robust CT to US 3D-3D Registration by Using Principal Component Analysis and Kalman Filtering

Resumen

Algorithms based on the unscented Kalman filter (UKF) have been proposed as an alternative for registration of point clouds obtained from vertebral ultrasound (US) and computerised tomography (CT) scans, effectively handling the US limited depth and low signaltonoise ratio -- Previously proposed methods are accurate, but their convergence rate is considerably reduced with initial misalignments of the datasets greater than or 30 mm -- We propose a novel method which increases robustness by adding a coarse alignment of the datasets’ principal components and batchbased point inclusions for the UKF -- Experiments with simulated scans with full coverage of a single vertebra show the method’s capability and accuracy to correct misalignments as large as and 90 mm -- Furthermore, the method registers datasets with varying degrees of missing data and datasets with outlier points coming from adjacent vertebrae

Descripción

Palabras clave

Citación

@Inbook{Echeverri2016, author={Echeverria, Rebeca and Cortes, Camilo and Bertelsen, Alvaro and Macia, Ivan and Ruiz, Oscar E. and Florez, Julian}, editor={Vrtovec, Tomaz and Yao, Jianhua and Glocker, Ben and Klinder, Tobias and Frangi, Alejandro and Zheng, Guoyan and Li, Shuo}, title={Robust CT to US 3D-3D Registration by Using Principal Component Analysis and Kalman Filtering}, bookTitle={Computational Methods and Clinical Applications for Spine Imaging: Third International Workshop and Challenge, CSI 2015, Held in Conjunction with MICCAI 2015, Munich, Germany, October 5, 2015, Proceedings}, year={2016}, publisher={Springer International Publishing}, address={Cham}, pages={52--63}, isbn={978-3-319-41827-8}, doi={10.1007/978-3-319-41827-8_5}, url={http://dx.doi.org/10.1007/978-3-319-41827-8_5}