Abstract
We present a framework for robustly estimating registration between a 3D volume image and a 2D projection image and evaluate its precision and robustness in spine interventions for vertebral localization in the presence of anatomical deformation. The framework employs a normalized gradient information similarity metric and multi-start covariance matrix adaptation evolution strategy optimization with local-restarts, which provided improved robustness against deformation and content mismatch. The parallelized implementation allowed orders-of-magnitude acceleration in computation time and improved the robustness of registration via multi-start global optimization. Experiments involved a cadaver specimen and two CT datasets (supine and prone) and 36 C-arm fluoroscopy images acquired with the specimen in four positions (supine, prone, supine with lordosis, prone with kyphosis), three regions (thoracic, abdominal, and lumbar), and three levels of geometric magnification (1.7, 2.0, 2.4). Registration accuracy was evaluated in terms of projection distance error (PDE) between the estimated and true target points in the projection image, including 14 400 random trials (200 trials on the 72 registration scenarios) with initialization error up to ±200 mm and ±10°. The resulting median PDE was better than 0.1 mm in all cases, depending somewhat on the resolution of input CT and fluoroscopy images. The cadaver experiments illustrated the tradeoff between
More>>
Otake, Yoshito;
Wang, Adam S;
Webster Stayman, J;
Siewerdsen, Jeffrey H;
[1]
Uneri, Ali;
[2]
Kleinszig, Gerhard;
Vogt, Sebastian;
[3]
Khanna, A Jay;
[4]
Gokaslan, Ziya L, E-mail: jeff.siewerdsen@jhu.edu
[5]
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore MD (United States)
- Department of Computer Science, Johns Hopkins University, Baltimore MD (United States)
- Siemens Healthcare, Erlangen (Germany)
- Department of Orthopaedic Surgery, Johns Hopkins University, Baltimore MD (United States)
- Department of Neurosurgery, Johns Hopkins University, Baltimore MD (United States)
Citation Formats
Otake, Yoshito, Wang, Adam S, Webster Stayman, J, Siewerdsen, Jeffrey H, Uneri, Ali, Kleinszig, Gerhard, Vogt, Sebastian, Khanna, A Jay, and Gokaslan, Ziya L, E-mail: jeff.siewerdsen@jhu.edu.
Robust 3D–2D image registration: application to spine interventions and vertebral labeling in the presence of anatomical deformation.
United Kingdom: N. p.,
2013.
Web.
doi:10.1088/0031-9155/58/23/8535.
Otake, Yoshito, Wang, Adam S, Webster Stayman, J, Siewerdsen, Jeffrey H, Uneri, Ali, Kleinszig, Gerhard, Vogt, Sebastian, Khanna, A Jay, & Gokaslan, Ziya L, E-mail: jeff.siewerdsen@jhu.edu.
Robust 3D–2D image registration: application to spine interventions and vertebral labeling in the presence of anatomical deformation.
United Kingdom.
https://doi.org/10.1088/0031-9155/58/23/8535
Otake, Yoshito, Wang, Adam S, Webster Stayman, J, Siewerdsen, Jeffrey H, Uneri, Ali, Kleinszig, Gerhard, Vogt, Sebastian, Khanna, A Jay, and Gokaslan, Ziya L, E-mail: jeff.siewerdsen@jhu.edu.
2013.
"Robust 3D–2D image registration: application to spine interventions and vertebral labeling in the presence of anatomical deformation."
United Kingdom.
https://doi.org/10.1088/0031-9155/58/23/8535.
@misc{etde_22437647,
title = {Robust 3D–2D image registration: application to spine interventions and vertebral labeling in the presence of anatomical deformation}
author = {Otake, Yoshito, Wang, Adam S, Webster Stayman, J, Siewerdsen, Jeffrey H, Uneri, Ali, Kleinszig, Gerhard, Vogt, Sebastian, Khanna, A Jay, and Gokaslan, Ziya L, E-mail: jeff.siewerdsen@jhu.edu}
abstractNote = {We present a framework for robustly estimating registration between a 3D volume image and a 2D projection image and evaluate its precision and robustness in spine interventions for vertebral localization in the presence of anatomical deformation. The framework employs a normalized gradient information similarity metric and multi-start covariance matrix adaptation evolution strategy optimization with local-restarts, which provided improved robustness against deformation and content mismatch. The parallelized implementation allowed orders-of-magnitude acceleration in computation time and improved the robustness of registration via multi-start global optimization. Experiments involved a cadaver specimen and two CT datasets (supine and prone) and 36 C-arm fluoroscopy images acquired with the specimen in four positions (supine, prone, supine with lordosis, prone with kyphosis), three regions (thoracic, abdominal, and lumbar), and three levels of geometric magnification (1.7, 2.0, 2.4). Registration accuracy was evaluated in terms of projection distance error (PDE) between the estimated and true target points in the projection image, including 14 400 random trials (200 trials on the 72 registration scenarios) with initialization error up to ±200 mm and ±10°. The resulting median PDE was better than 0.1 mm in all cases, depending somewhat on the resolution of input CT and fluoroscopy images. The cadaver experiments illustrated the tradeoff between robustness and computation time, yielding a success rate of 99.993% in vertebral labeling (with ‘success’ defined as PDE <5 mm) using 1,718 664 ± 96 582 function evaluations computed in 54.0 ± 3.5 s on a mid-range GPU (nVidia, GeForce GTX690). Parameters yielding a faster search (e.g., fewer multi-starts) reduced robustness under conditions of large deformation and poor initialization (99.535% success for the same data registered in 13.1 s), but given good initialization (e.g., ±5 mm, assuming a robust initial run) the same registration could be solved with 99.993% success in 6.3 s. The ability to register CT to fluoroscopy in a manner robust to patient deformation could be valuable in applications such as radiation therapy, interventional radiology, and an assistant to target localization (e.g., vertebral labeling) in image-guided spine surgery. (paper)}
doi = {10.1088/0031-9155/58/23/8535}
journal = []
issue = {23}
volume = {58}
journal type = {AC}
place = {United Kingdom}
year = {2013}
month = {Dec}
}
title = {Robust 3D–2D image registration: application to spine interventions and vertebral labeling in the presence of anatomical deformation}
author = {Otake, Yoshito, Wang, Adam S, Webster Stayman, J, Siewerdsen, Jeffrey H, Uneri, Ali, Kleinszig, Gerhard, Vogt, Sebastian, Khanna, A Jay, and Gokaslan, Ziya L, E-mail: jeff.siewerdsen@jhu.edu}
abstractNote = {We present a framework for robustly estimating registration between a 3D volume image and a 2D projection image and evaluate its precision and robustness in spine interventions for vertebral localization in the presence of anatomical deformation. The framework employs a normalized gradient information similarity metric and multi-start covariance matrix adaptation evolution strategy optimization with local-restarts, which provided improved robustness against deformation and content mismatch. The parallelized implementation allowed orders-of-magnitude acceleration in computation time and improved the robustness of registration via multi-start global optimization. Experiments involved a cadaver specimen and two CT datasets (supine and prone) and 36 C-arm fluoroscopy images acquired with the specimen in four positions (supine, prone, supine with lordosis, prone with kyphosis), three regions (thoracic, abdominal, and lumbar), and three levels of geometric magnification (1.7, 2.0, 2.4). Registration accuracy was evaluated in terms of projection distance error (PDE) between the estimated and true target points in the projection image, including 14 400 random trials (200 trials on the 72 registration scenarios) with initialization error up to ±200 mm and ±10°. The resulting median PDE was better than 0.1 mm in all cases, depending somewhat on the resolution of input CT and fluoroscopy images. The cadaver experiments illustrated the tradeoff between robustness and computation time, yielding a success rate of 99.993% in vertebral labeling (with ‘success’ defined as PDE <5 mm) using 1,718 664 ± 96 582 function evaluations computed in 54.0 ± 3.5 s on a mid-range GPU (nVidia, GeForce GTX690). Parameters yielding a faster search (e.g., fewer multi-starts) reduced robustness under conditions of large deformation and poor initialization (99.535% success for the same data registered in 13.1 s), but given good initialization (e.g., ±5 mm, assuming a robust initial run) the same registration could be solved with 99.993% success in 6.3 s. The ability to register CT to fluoroscopy in a manner robust to patient deformation could be valuable in applications such as radiation therapy, interventional radiology, and an assistant to target localization (e.g., vertebral labeling) in image-guided spine surgery. (paper)}
doi = {10.1088/0031-9155/58/23/8535}
journal = []
issue = {23}
volume = {58}
journal type = {AC}
place = {United Kingdom}
year = {2013}
month = {Dec}
}