DocumentCode :
83972
Title :
Robustness and Accuracy of Feature-Based Single Image 2-D–3-D Registration Without Correspondences for Image-Guided Intervention
Author :
Xin Kang ; Armand, Mehran ; Otake, Yoshito ; Wai-Pan Yau ; Cheung, P.Y.S. ; Yong Hu ; Taylor, Russell H.
Author_Institution :
Dept. of Orthopaedics & Traumatology, Univ. of Hong Kong, Hong Kong, China
Volume :
61
Issue :
1
fYear :
2014
fDate :
Jan. 2014
Firstpage :
149
Lastpage :
161
Abstract :
2-D-to-3-D registration is critical and fundamental in image-guided interventions. It could be achieved from single image using paired point correspondences between the object and the image. The common assumption that such correspondences can readily be established does not necessarily hold for image guided interventions. Intraoperative image clutter and an imperfect feature extraction method may introduce false detection and, due to the physics of X-ray imaging, the 2-D image point features may be indistinguishable from each other and/or obscured by anatomy causing false detection of the point features. These create difficulties in establishing correspondences between image features and 3-D data points. In this paper, we propose an accurate, robust, and fast method to accomplish 2-D-3-D registration using a single image without the need for establishing paired correspondences in the presence of false detection. We formulate 2-D-3-D registration as a maximum likelihood estimation problem, which is then solved by coupling expectation maximization with particle swarm optimization. The proposed method was evaluated in a phantom and a cadaver study. In the phantom study, it achieved subdegree rotation errors and submillimeter in-plane ( X- Y plane) translation errors. In both studies, it outperformed the state-of-the-art methods that do not use paired correspondences and achieved the same accuracy as a state-of-the-art global optimal method that uses correct paired correspondences.
Keywords :
diagnostic radiography; feature extraction; image registration; maximum likelihood estimation; medical image processing; particle swarm optimisation; phantoms; 2D image point features; 3D data points; X-Y plane translation errors; X-ray imaging; correct paired correspondences; expectation maximization; false detection; feature extraction method; feature-based single image 2D-3D registration; image-guided interventions; intraoperative image clutter; maximum likelihood estimation problem; paired point correspondences; particle swarm optimization; phantom; robustness; state-of-the-art global optimal method; subdegree rotation errors; submillimeter in-plane translation errors; Educational institutions; Feature extraction; Maximum likelihood estimation; Robustness; Solid modeling; X-ray imaging; 2-D–3-D registration; feature-based registration; image-guided interventions (IGIs); particle swarm optimization (PSO);
fLanguage :
English
Journal_Title :
Biomedical Engineering, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9294
Type :
jour
DOI :
10.1109/TBME.2013.2278619
Filename :
6579709
Link To Document :
بازگشت