Abstract
Many brain image processing algorithms require one or more well-chosen seed points because they need to be initialized close to an optimal solution. Anatomical point landmarks are useful for constructing initial conditions for these algorithms because they tend to be highly-visible and predictably-located points in brain image scans. We introduce an empirical training procedure that locates user-selected anatomical point landmarks within well-defined precisions using image data with different resolutions and MRI weightings. Our approach makes no assumptions on the structural or intensity characteristics of the images and produces results that have no tunable run-time parameters. We demonstrate the procedure using a Java GUI application (LONI ICE) to determine the MRI weighting of brain scans and to locate features in T1-weighted and T2-weighted scans.
Similar content being viewed by others
Notes
The superscript T denotes the transpose of a matrix.
References
Alker, M., Frantz, S., et al. (2001). Improving the robustness in extracting 3D point landmarks based on deformable models. In Proceedings of the 23rd DAGM-Symposium on pattern recognition (Vol. 2191, pp. 108–115).
Arun, K. S., Huang, T. S., et al. (1987). Least square fitting of two 3D point sets. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1987(9), 698–700.
Barrett, W. A., & Mortensen, E. N. (1997). Interactive live-wire boundary extraction. Medical Image Analysis, 1(4), 331–341.
Besl, P. J., & McKay, N. D. (1992). A method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2), 239–256.
Boykov, Y., & Jolly, M. (2001). Interactive graph cuts for optimal boundary and region segmentation of objects in N–D images. International Conference on Computer Vision, I, 105–112.
Bischoff-Grethe, A., Fischl, B., et al. (2004). A technique for the deidentification of structural brain MR images. Budapest, Hungary: Human Brain Mapping.
Chandra, D. V. S. (2002). Digital image watermarking using singular value decomposition. In Proc. 45th IEEE Midwest symp. on circuits and systems (Vol. 3, pp. 264–267).
Chen, P. C., & Pavlidis, T. (1983). Segmentation by textures using correlation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 5(1), 64–69.
Cox, I. J., Rao, S. B., et al. (1996). Ratio regions: A technique for image segmentation. Proc. International Conference on Pattern Recognition, 2, 557–564.
Daneels, D., Van Campenhout, D., et al. (1993). Interactive Outlining: An improved approach using active contours. SPIE Proceedings of Storage and Retrieval for Image and Video Databases, 1908, 226–233.
Davis, L. S., Johns, S. A., et al. (1979). Texture analysis using generalized cooccurrence matrices. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1, 251–259.
Ende, G., Treuer, H., et al. (1992). Optimization and evaluation of landmark-based image correlation. Physics in Medicine & Biology, 37(1), 261–271.
Falco, A. X., Udupa, J. K., et al. (1998). User-steered image segmentation paradigms: Live wire and live lane. Graphical Models and Image Processing, 60(4), 233–260.
Fang, S., Raghavan, R., et al. (1996). Volume morphing methods for landmark based 3D image deformation. SPIE International Symposium on Medical Imaging, 2710, 404–415.
Fischl, B., Salat, D. H., et al. (2002). Whole brain segmentation: Automated labeling of neuroanatomical structures in the human brain. Neuron, 33(3), 341–355.
Fitzpatrick, J. M., & Reinhardt, J. M. (2005). Automatic landmarking of magnetic resonance brain images. Proceedings SPIE, 1329, 1329–1340.
Frantz, S., Rohr, K., et al. (2000). Localization of 3d anatomical point landmarks in 3d tomographic images using deformable models. Proceedings on MICCAI, 2000, 492–501.
Gorodetski, V. I., Popyack, L. J., et al. (2001). SVD-based approach to transparent embedding data into digital images. Proceedings on International Workshop on Mathematical Methods, Models and Architectures for Computer Network Security, 2052, 263–274.
Han, Y., & Park, H. (2004). Automatic registration of brain magnetic resonance images based on talairach reference system. Journal of Magnetic Resonance Imaging 20(4), 572-80.
Hansen, P. C., & Jensen, S. H. (1998). FIR filter representation of reduced-rank noise reduction. IEEE Transactions on Signal Proceedings, 46(6), 1737–1741.
Hartkens, T., Rohr, K., et al. (2002). Evaluation of 3D operators for the detection of anatomical point landmarks in MR and CT Images. Computer Vision and Image Understanding, 86(2), 118–136.
Hill, D. L., Hawkes, D. J., et al. (1991). Registration of MR and CT images for skull base surgery using point-like anatomical features. British Journal of Radiology, 64(767), 1030–1035.
Huang, T., & Narendra, P. (1974). Image restoration by singular value decomposition. Applied Optics, 14(9), 2213–2216.
Kalman, D. (1996). A singularly valuable decomposition: The SVD of a matrix. The College Mathematics Journal, 27(1), 2–23.
Kass, M., Witkin, A., et al. (1987). Snakes: Active contour models. International Journal of Computer Vision, 1(4), 321–331.
Konstantinides, K., & Yovanof, G. S. (1995). Application of SVD-based spatial filtering to video sequences. IEEE International Conference on Acoustics, 4, 2193–2196.
Konstantinides, K., Natarajan, B., et al. (1997). Noise estimation and filtering using block-based singular value decomposition. IEEE Transactions on Image Process, 6(3), 479–483.
Le Briquer, L., Lachmann, F., et al. (1993). Using local extremum curvatures to extract anatomical landmarks from medical images. Proceedings on SPIE, 1898, 549–558.
MacDonald, D., Avis, D., & Evan, A. C. (1994). Multiple surface identification and matching in magnetic resonance imaging. Proceedings of the Society of Photo-optical Instrumentation Engineers, 2359, 160–169.
McInerney, T., & Dehmeshki, H. (2003). User-defined b-spline template-snakes. Medical Image Computing and Computer-Assisted Intervention, 2879, 746–753.
Meyer, F., & Beucher, S. (1990). Morphological segmentation. Journal of Visual Communications and Image Representation, 1(1), 21–46.
Mortensen, E. N., & Barrett, W. A. (1995). Intelligent scissors for image composition. In Proceedings of the ACM SIGGRAPH ‘95: Computer graphics and interactive techniques, (Vol. 191–198).
O’Leary, D. P., & Peleg, S. (1983). Digital image compression by outer product expansion. IEEE Transactions on Communications, 31(3), 441–444.
Pennec, X., Ayache, N., et al. (2000). Landmark-based registration using features identified through differential geometry. In Handbook of medical imaging (1st edn.). San Diego, CA: Academic.
Peters, T. M., Davey, B. L. K., et al. (1996). Three-dimensional multi-modal image-guidance for neurosurgery. IEEE Transactions on Medical Imaging, 15(2), 121–128.
Pohl, K. M., Wells, W. M., et al. (2002). Incorporating non-rigid registration into expectation maximization algorithm to segment MR Images. In Fifth international conference on medical image computing and computer assisted intervention. Tokyo, Japan.
Press, W. H., Teukolsky, S. A., Vetterling, W. T., & Flannery, B. P. (1995). Numerical recipies in C: The art of scientific computing (2nd edn.). Cambridge, UK: Cambridge University Press.
Rohr, K. (1997). On 3d differential operators for detecting point landmarks. Image and Vision Computing, 15(3), 219–233.
Rohr, K. (2001). Landmark-based image analysis using geometric and intensity models (1st edn.). Dordrecht, The Netherlands: Kluwer.
Russ, J. C. (2006). The image processing handbook (5th edn.). Boca Raton, FL: CRC Press.
Sethian, J. A. (1999). Level set methods and fast marching methods (2nd edn.). Cambridge, UK: Cambridge University Press.
Shattuck, D. W., Rex, D. E., et al. (2003). JohnDoe: Anonymizing MRI data for the protection of research subject confidentiality. In 9th annual meeting of the organization for human brain mapping. New York, New York.
Sirovich, L., & Kirby, M. (1987). Low dimensional procedure for the characterization of human faces. Journal of the Optical Society of America A, 4(3), 519–524.
Strasters, K. C., Little, J. A., et al. (1997). Anatomic landmark image registration: Validation and comparison. CVR Med/MRCAS, 1997, 161–170.
Thirion, J. (1994). Extremal points: Definition and application to 3D image registration. Proceedings of the Conference on Computer Vision and Pattern Recognition, 1994, 587–592.
Toga, A. W. (1999). Brain warping (1st edn.). San Diego, CA: Academic.
Turk, M. A., & Pentland, A. P. (1991). Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1), 71–86.
Woods, R. P., Grafton, S. T., et al. (1998). Automated image registration: I. General methods and intrasubject, intramodality validation. Journal of Computer Assisted Tomography, 22(1), 139–152.
Wörz, S., Rohr., K., et al. (2003). 3D parametric intensity models for the localization of different types of 3D anatomical point landmarks in tomographic images. DAGM-Symposium, 2003, 220–227.
Yushkevich, P. A., Piven, J., et al. (2006). User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability. Neuroimage, 31(3), 1116–1128.
Acknowledgements
This work was supported by the National Institutes of Health through the NIH Roadmap for Medical Research, grant U54 RR021813 entitled Center for Computational Biology (CCB). Information on the National Centers for Biomedical Computing can be obtained from http://nihroadmap.nih.gov/bioinformatics. Additional support was provided by the NIH research grants R01 MH071940 and P01 EB001955, the NIH/NCRR resource grant P41 RR013642, and the Biomedical Informatics Research Network (BIRN, http://www.nbirn.net).
The authors thank Edward Lau for manually producing brain surfaces from our image volumes and Cornelius Hojatkashani for directing the effort.
Author information
Authors and Affiliations
Corresponding author
Appendix: Relation to Cross-Correlation
Appendix: Relation to Cross-Correlation
Cross-correlation (Russ 2006) is a well-known method in image processing that is commonly used to find features within images. The shift required to align a target image with another image is determined by sliding the target image along the latter image and summing the products of all overlaid pixel values at each location. The sum is a maximum where the images are best matched.
In this Appendix we relate cross-correlation to the method described in this paper in one-dimension; it is straight-forward to extend this relation to two and three dimensions. If I is a one-dimensional image intensity function and is displaced a distance x relative to another function A, the cross-correlation is defined as
In the limit of small x, we approximate I(g + x) as I(g) + x I′(g) and note that Eq. 8 has the form
where D and C are constants. In particular, if we choose C = − 1, then in this limit the integral is equal to the distance between I and A (with D defined as the distance between them at x = 0).
In our case, we are choosing a function for the cross-correlation integral and solving for A (as opposed to being given I and A and computing the integral). We are then interested in finding a function A that makes
approximately true. The integral can be approximated by evaluating the integrand at n locations that are a distance δ apart
and if the range of x is evaluated in m steps of length Δ, we have the system of equations given in Eq. 1 where A j = A(jδ), I ij = I(jδ + iΔ), and D i = D − iΔ. The coefficients A j are determined using least-squares to minimize the differences between both sides of Eq. 10.
One advantage of using least-squares is that the solution is insensitive to constant changes in intensity. For example, let I 1(x) and I 2(x) be image intensities where I 2(x) = I 1(x) + I 0 and I 0 is a constant. Then the function A that minimizes the differences between both sides of the equations
is also the function that minimizes the differences between both sides of the equations
by subtracting the two equations. Equation 14 states that the contributions of constant intensity terms are minimized.
Rights and permissions
About this article
Cite this article
Neu, S.C., Toga, A.W. Automatic Localization of Anatomical Point Landmarks for Brain Image Processing Algorithms. Neuroinform 6, 135–148 (2008). https://doi.org/10.1007/s12021-008-9018-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12021-008-9018-x