2D Rigid Registration of MR Scans using the 1d Binary Projections
This paper presents the application of a signal
intensity independent registration criterion for 2D rigid body
registration of medical images using 1D binary projections. The
criterion is defined as the weighted ratio of two projections. The ratio
is computed on a pixel per pixel basis and weighting is performed by
setting the ratios between one and zero pixels to a standard high
value. The mean squared value of the weighted ratio is computed
over the union of the one areas of the two projections and it is
minimized using the Chebyshev polynomial approximation using
n=5 points. The sum of x and y projections is used for translational
adjustment and a 45deg projection for rotational adjustment. 20 T1-
T2 registration experiments were performed and gave mean errors
1.19deg and 1.78 pixels. The method is suitable for contour/surface
matching. Further research is necessary to determine the robustness
of the method with regards to threshold, shape and missing data.
[1] B.Zitova, J. Flusser, "Image registration methods: A survey", Image and
Vision Computing 21 (2003) pp977-1000
[2] J.West, JM Fitzpatrick, MY Wang, BM Dawant, CR Maurer et Al.
"Retrospective intermodality registration techniques for images of the
head: Surface-based versus Volume-Based", IEEE Transactions on
Medical Imaging, Vol. 18, No.2,February 1999, pp144-150.
[3] A.Roche, X.Pennec, G. Malandain and N. Ayache, "Rigid registration of
3-D Ultrasound with MR images: A new approach combining intensity
and gradient information", IEEE Transactions on Medical Imaging, Vol
20, No. 10, October 2001, pp1038-1049.
[4] E.B. van de Kraats, G.P.Penney, D.Tomazevic, T.van Walsum and
W.J.Niessen, "Standardized evaluation methodology for 2D-3D
registration", IEEE Transactions on Medical Imaging, Vol. 24, No.9,
Sept 2005, pp 1177-1189.
[5] R.A.McLaughlin, J.Hipwell, D.J.Hawkes, J.A.Noble, J.V.Byrne et. al. ,
"A comparison of a similarity-based and a feature-based 2d-3d
registration method for neurointerventional use", IEEE Transactions on
Medical Imaging, Vol.24, No.8 August 2005, pp1058-1066.
[6] C.R.Maurer, R.J.Maciunas, J.M.Fitzpatrick, " Registration of head CT
images to physical space using a weighted combination of points and
surfaces", IEEE Transactions on Medical Imaging, Vol. 17, No. 5,
October 1998, pp. 753-761.
[7] W.H.Press, S.A.Teukolsky, W.T.Vetterling, B.P.Flannery, Numerical
recipes in C, The art of scientific computing, 2nd edition, Cambridge
University Press, Cambridge 1992.
[8] P.Kotsas, "A new automated method for three dimensional registration
of MR images of the head", Master-s Thesis, Dept. of Biomedical
Engineering, The Ohio-State University.
[9] P.Kotsas, S. Malasiotis, M. Strintzis,D.W.Piraino and J.F.Cornhill, "A
fast and accurate method for registration of MR images of the head",
International Journal of Medical Informatics 52(1998) pp167-182.
[10] P.Kotsas, "Non-rigid registration of medical images using an automated
method",EnformatikaVolume7,August2005,pp199-201,
www.enformatika.org.
[11] R.Jain, R.Kasturi,B.G.Schunck,"Machine Vision", Mc Graw-Hill, New
York, 1995.
[1] B.Zitova, J. Flusser, "Image registration methods: A survey", Image and
Vision Computing 21 (2003) pp977-1000
[2] J.West, JM Fitzpatrick, MY Wang, BM Dawant, CR Maurer et Al.
"Retrospective intermodality registration techniques for images of the
head: Surface-based versus Volume-Based", IEEE Transactions on
Medical Imaging, Vol. 18, No.2,February 1999, pp144-150.
[3] A.Roche, X.Pennec, G. Malandain and N. Ayache, "Rigid registration of
3-D Ultrasound with MR images: A new approach combining intensity
and gradient information", IEEE Transactions on Medical Imaging, Vol
20, No. 10, October 2001, pp1038-1049.
[4] E.B. van de Kraats, G.P.Penney, D.Tomazevic, T.van Walsum and
W.J.Niessen, "Standardized evaluation methodology for 2D-3D
registration", IEEE Transactions on Medical Imaging, Vol. 24, No.9,
Sept 2005, pp 1177-1189.
[5] R.A.McLaughlin, J.Hipwell, D.J.Hawkes, J.A.Noble, J.V.Byrne et. al. ,
"A comparison of a similarity-based and a feature-based 2d-3d
registration method for neurointerventional use", IEEE Transactions on
Medical Imaging, Vol.24, No.8 August 2005, pp1058-1066.
[6] C.R.Maurer, R.J.Maciunas, J.M.Fitzpatrick, " Registration of head CT
images to physical space using a weighted combination of points and
surfaces", IEEE Transactions on Medical Imaging, Vol. 17, No. 5,
October 1998, pp. 753-761.
[7] W.H.Press, S.A.Teukolsky, W.T.Vetterling, B.P.Flannery, Numerical
recipes in C, The art of scientific computing, 2nd edition, Cambridge
University Press, Cambridge 1992.
[8] P.Kotsas, "A new automated method for three dimensional registration
of MR images of the head", Master-s Thesis, Dept. of Biomedical
Engineering, The Ohio-State University.
[9] P.Kotsas, S. Malasiotis, M. Strintzis,D.W.Piraino and J.F.Cornhill, "A
fast and accurate method for registration of MR images of the head",
International Journal of Medical Informatics 52(1998) pp167-182.
[10] P.Kotsas, "Non-rigid registration of medical images using an automated
method",EnformatikaVolume7,August2005,pp199-201,
www.enformatika.org.
[11] R.Jain, R.Kasturi,B.G.Schunck,"Machine Vision", Mc Graw-Hill, New
York, 1995.
@article{"International Journal of Medical, Medicine and Health Sciences:56843", author = "Panos D. Kotsas", title = "2D Rigid Registration of MR Scans using the 1d Binary Projections", abstract = "This paper presents the application of a signal
intensity independent registration criterion for 2D rigid body
registration of medical images using 1D binary projections. The
criterion is defined as the weighted ratio of two projections. The ratio
is computed on a pixel per pixel basis and weighting is performed by
setting the ratios between one and zero pixels to a standard high
value. The mean squared value of the weighted ratio is computed
over the union of the one areas of the two projections and it is
minimized using the Chebyshev polynomial approximation using
n=5 points. The sum of x and y projections is used for translational
adjustment and a 45deg projection for rotational adjustment. 20 T1-
T2 registration experiments were performed and gave mean errors
1.19deg and 1.78 pixels. The method is suitable for contour/surface
matching. Further research is necessary to determine the robustness
of the method with regards to threshold, shape and missing data.", keywords = "Medical image, projections, registration, rigid.", volume = "1", number = "9", pages = "512-5", }