NDA@SZTAKI

A Framework for Semi-automatic Fiducial Localization in Volumetric Images

Nagy, DÊnes Ákos

Haidegger, TamĂĄs

Yaniv, Ziv

2014

RD Surgery / sebĂŠszet

Fiducial localization in volumetric images is a common task
performed by image-guided navigation and augmented reality systems.
These systems often rely on fiducials for image-space to physical-space
registration, or as easily identifiable structures for registration validation
purposes. Automated methods for fiducial localization in volumetric im-
ages are available. Unfortunately, these methods are not generalizable as
they explicitly utilize strong a priori knowledge such as fiducial intensity
values in CT, or known spatial configurations as part of the algorithm.
Thus, manual localization has remained the most general approach, read-
ily applicable across fiducial types and imaging modalities. The main
drawbacks of manual localization are the variability and accuracy errors
associated with visual localization. We describe a semi-automatic fiducial
localization approach that combines the strengths of the human opera-
tor and an underlying computational system. The operator identifies the
rough location of the fiducial, and the computational system accurately
localizes it via intensity based registration using the mutual information
similarity measure. This approach is generic, implicitly accommodating
for all fiducial types and imaging modalities. The framework was evalu-
ated using five fiducial types and three imaging modalities. We obtained
a maximal localization accuracy error of 0.35mm, with a maximal preci-
sion variability of 0.5mm.

angol

Article

PeerReviewed

info:eu-repo/semantics/article

text

http://real.mtak.hu/16132/1/manuscript.pdf

Nagy, DÊnes Ákos and Haidegger, Tamås and Yaniv, Ziv (2014) A Framework for Semi-automatic Fiducial Localization in Volumetric Images. LNCS 8678, 8678. pp. 138-148. ISSN 0302-9743

http://real.mtak.hu/16132/

http://dx.doi.org/10.1007/978-3-319-10437-9_15

doi:10.1007/978-3-319-10437-9_15

-