Abstract
A method that considerably reduces the computational and memory complexities associated with the generation of high-dimensional (≥3) feature maps for image segmentation is described. The method is based on the K-nearest neighbor (KNN) classification and consists of two parts: preprocessing of feature space and fast KNN. This technique is implemented on a PC and applied for generating 3D and 4D feature maps for segmenting MR brain images of multiple sclerosis patients.
Similar content being viewed by others
References
Amato, U., M. Larobina, A. Antoniadis, and B. Alfano. Segmentation of magnetic resonance brain images through discriminant analysis. J. Neurosci. Methods 131(1–2):65–74, 2003.
Anbeek, P., K. L. Vincken, M. J. P. van Osch, R. H. C. Bisschops, and J. Grond. Probabilistic segmentation of white matter lesions in MR imaging. Neuroimage 21:1037–1044, 2004.
Ashburner, J. Another MRI bias correction approach. In: The 8th International Conference on Functional Mapping of the Human Brain, Sendai, Japan, June 2–6, 2002. Available on CD-Rom, also appeared in Neuroimage 16(Suppl. 2).
Bedell, B. J., and P. A. Narayana. Volumetric analysis of white matter, gray matter, and CSF using fractional volume analysis. Magn. Reson. Med. 39:961–969, 1998.
Bedell, B. J., P. A. Narayana, and J. S. Wolinsky. A dual approach for minimizing false lesions classifications on magnetic resonance images. Magn. Reson. Med. 37:94–102, 1997.
Borgefors, G. Distance transformation in arbitrary dimensions. Comput. Vis. Graph. Image Process. 27:321–145, 1984.
Cárdenes, R., S. K. Warfield, E. Macìas, J. A. Santana, and J. Ruiz-Alzola. An efficient algorithm for multiple sclerosis lesion segmentation from brain MRI. In: Computer Aided Systems Theory—EUROCAST 2003, 9th International Workshop on Computer Aided Systems Theory, Las Palmas de Gran Canaria, Spain, February 24–28, 2003, Lecture Notes in Computer Science 2809 Springer, Springer-Verlag, Berlin, Hedelberg, edited by R. Moreno-Dìaz and F. Pichler. 2003, pp. 542– 551.
Clarke, L. P., R. P. Velthuizen, S. Phuphanich, J. D. Schellenberg, J. A. Arrington, and M. Silbiger. MRI: Stability of three supervised segmentation techniques. Magn. Reson. Imaging 11:95–106, 1993.
Cline, H. E., W. E. Lorenson, R. Kikinis, and F. Jolesz. Three-dimensional segmentation of MR images of the head using probability and connectivity. J. Comput. Assist. Tomogr. 14(6):1037–1045, 1990.
Cuisenaire, O. Distance transformations: Fast algorithms and applications to medical image processing, Thèse présentée en vue de l'obtention du grade de Docteur en Sciences Appliquées, UCL/TELE, Louvain-la-Neuve, October 1999.
Cuisenaire, O., and B. Macq. Fast k-NN classification with an optimal k-distance transformation algorithm. In: Proceedings of the 10th European Signal Processing Conference (EUSIPCO), September 2000, pp. 1365–1368.
Fukunaga, K., and P. Narendra. A branch and bound algorithm for k-nearest neighbors. IEEE Trans. Comput. 24:750–753, 1975.
Gerig, G., J. Martin, R. Kikinis, O. Kübler, M. Shenton, and F. Jolesz. Automatic segmentation of dual-echo MR head data. In: Proceedings of the 12th International Conference on Information Processing in Medicine Imaging, Wye, UK, July 1991. Berlin: Springer, 1991, pp. 175–187.
He, R., and P. A. Narayana. Global optimization of mutual information: Application to three-dimensional retrospective registration of magnetic resonance images. Comp. Med. Imaging Graph. 26(4):277–292, 2002.
The MathWorks, Inc., Image Processing Toolbox User's Guide: Objects, Regions, and Feature Measurement, http://www.mathworks.com/access/helpdesk/help/toolbox/images/morph15.html
Research Systems, Inc., IDL-Interactive Data Language, http://www.rsinc.com/
Jiang, Q., and W. Zhang. An improved method for finding nearest neighbors. Pattern Recognit. Lett. 14:531–535, 1993.
Kamgar-Parsi, B., and L. N. Kanal. An improved branch and bound algorithm for computing k-nearest neighbours. Pattern Recognit. Lett. 3:7–12, 1985.
Kim, B. S., and S. B. Park. A fast K nearest neighbor finding algorithm based on the ordered partition. IEEE Trans. PAMI 8:761–766, 1986.
Meier, D. S., and C. R. G. Guttmann. Time-series analysis of MRI intensity pattern in multiple sclerosis. Neuroimage 20:1193–1209, 2003.
Niemann, H., and R. Goppert. An efficient branch-and-bound nearest neighbor classifier. Pattern Recognit. Lett. 7:67–72, 1988.
Nyul, L. G., J. K. Udupa, and X. Zhang. New variants of a method of MRI scale standardization. IEEE Trans. Med. Imaging 19(2):143–150, 2000.
Ragnelmam, I. The euclidean distance transformation in arbitrary dimensions. Pattern Recognit. Lett. 14:883–888, 1993.
Romero, E., J.-M. Raymackers, B. Macq, and O. Cuisenaire. Automatic fibrosis quantification using a k-NN classificatory. In: 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2001), Istanbul, October 25–28, 2001.
Vaidyanathan, R. P., L. P. Clarke, R. P. Velthuizen, S. Phuphanich, L. O. Hall, and J. C. Bezdek. Comparison of supervised MRI segmentation methods for tumor volume determination during therapy. Magn. Reson. Imaging 13(5):719–728, 1996.
Warfield, S. K. Fast k-NN classification for multichannel image data. Pattern Recognit. Lett. 17:713–721, 1996.
Weickert, J. Anisotropic Diffusion in Image Processing. Teubner: Stuttgart, 1998.
Weisenfeld, N. I., and S. K. Warfield. Normalization of joint image-intensity statistics in MRI using the Kullback–Leibler divergence. Preprint, IEEE ISBI, 2004.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
He, R., Sajja, B.R. & Narayana, P.A. Implementation of High-Dimensional Feature Map for Segmentation of MR Images. Ann Biomed Eng 33, 1439–1448 (2005). https://doi.org/10.1007/s10439-005-5888-3
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s10439-005-5888-3