Standardized evaluation methodology for 2-D-3-D registration

Abstract

In the past few years, a number of two-dimensional (2-D) to three-dimensional (3-D) (2-D-3-D) registration algorithms have been introduced. However, these methods have been developed and evaluated for specific applications, and have not been directly compared. Understanding and evaluating their performance is therefore an open and important issue. To address this challenge we introduce a standardized evaluation methodology, which can be used for all types of 2-D-3-D registration methods and for different applications and anatomies. Our evaluation methodology uses the calibrated geometry of a 3-D rotational X-ray (3DRX) imaging system (Philips Medical Systems, Best, The Netherlands) in combination with image-based 3-D-3-D registration for attaining a highly accurate gold standard for 2-D X-ray to 3-D MR/CT/3DRX registration. Furthermore, we propose standardized starting positions and failure criteria to allow future researchers to directly compare their methods. As an illustration, the proposed methodology has been used to evaluate the performance of two 2-D-3-D registration techniques, viz. a gradient-based and an intensity-based method, for images of the spine. The data and gold standard transformations are available on the internet (http://www.isi.uu.nl/Research/Databases/).

Effective Incorporation of Spatial Information in a Mutual Information Based 3D-2D Registration of a CT Volume to X-Ray Images

“…When the absolute parameter range is (12 o , 12mm), the average CPU time tested on a 3.0 GHz Pentium machine was 26.7 seconds. It was found that the capture range of the PW-MRF-VA-MI was much larger than those reported in [7] and in [14], although the attained accuracy was lower than that reported in [14]. This might be explained by the large inter-slice distance (2.5 mm in this work vs. 0.31 mm in [14]) and the region outliers in the X-ray images.…”

“…We then performed the registration starting from these perturbed positions and counted the success rate. Using a method similar to that reported in [14], we regarded a registration as successful if the mean target registration errors (mTRE) evaluated on the fiducial markers was smaller than 1.5 mm . The capture range was defined as the average of the initial mTRE when a 95% success rate is achieved.…”

High-performance GPU-based rendering for real-time, rigid 2D/3D-image registration and motion prediction in radiation oncology

“…Table 1 Mean rendering times (in ms) and their standard deviations (SD) for 27000 renderings using GPU based wobbled splat rendering and GPU based ray casting including several optimization techniques for them. Two reference datasets available to the public [36,37] were used for this validation. Table 2 Measured times including standard deviations for the overall registration process.…”

Multi-Modality Imaging: A Software Fusion and Image-Guided Therapy Perspective

“…The most important case is 2D/3D image registration of digitally rendered radiographs (DRRs) and X-ray images taken with a known projection geometry [68,[76][77][78][79][80][81][82]. This is widely used in image-guided surgery and image-guided radiotherapy.…”