Results

Introduction

So far, a total of two 2D-3D registration methods have been tested on this ground truth. Each method is referenced on this page by a number and the name of the first author of the paper in which the method was presented. At the end of this page, references are provided for further information.

Performance measurements

Performance is given as accuracy and capture range of the method. Links to graphs of the results are provided.

Results

The table below shows an overview of the performance of the different methods. The average accuracy within the capture range (2 mm mTRE) is reported, along with the capture range (see [1]).

2 fluoroscopic images on Dataset 1

3DRX

CT

MR

Method

Ev. Meas.

E. (mm)

C.R. (mm)

E. (mm)

C.R. (mm)

E. (mm)

C.R. (mm)

[2] Tomazevic

mTRE

0.18

6

0.30

3

0.45

1

[3] Penney

mTRE

0.13

4

0.65

3

Graphs of the results can be found in the following pdf file, 2fluoro.pdf.

1 fluoroscopic image on Dataset 1

3DRX

CT

MR

Method

Ev. Meas.

E. (mm)

C.R. (mm)

E. (mm)

C.R. (mm)

E. (mm)

C.R. (mm)

[2] Tomazevic

mTRE

0.46

1

0.53

1

[2] Tomazevic

mPD

0.29

5

0.42

3

[2] Tomazevic

mRPD

0.20

5

0.30

5

[3] Penney

mTRE

0.84

1

0.84

2

[3] Penney

mPD

0.22

6

0.61

2

[3] Penney

mRPD

0.15

6

0.52

3

Graphs of the results can be found in the following pdf file, 1fluoro.pdf.

References

[1] E.B. van de Kraats, G.P. Penney, D. Tomazevic, Th. van Walsum, W.J. Niessen, "Standardized Evaluation Methodology for 2D-3D Registration", IEEE Transactions on Medical Imaging, 2005, vol. 24, pp. 1177-1190.

[2] D. Tomazevic, B. Likar, T. Slivnik, and F. Pernus, 3-D/2-D registration of CT and MR to X-ray images, IEEE Transactions on Medical Imaging, vol. 22, no. 11, pp. 1407-1416, 2003.

[3] G.P. Penney, J. Weese, J.A. Little, P. Desmedt, D.L.G. Hill, and D.J. Hawkes, A comparison of similarity measures for use in 2-D-3-D medical image registration, IEEE Transactions on Medical Imaging, vol. 17, no. 4, pp. 586-595, 1998.