Share Email Print
cover

Proceedings Paper

Comparison of supervised pattern recognition techniques and unsupervised methods for MRI segmentation
Author(s): Laurence P. Clarke; Robert Paul Velthuizen; Lawrence O. Hall; James C. Bezdek; Amine M. Bensaid; Martin L. Silbiger
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The use of image intensity based segmentation techniques are proposed to improve MRI contrast and provide greater confidence levels in 3-D visualization of pathology. Pattern recognition methods are proposed using both supervised and unsupervised methods. This paper emphasizes the practical problems in the selection of training data sets for supervised methods that result in instability in segmentation. An unsupervised method, namely fuzzy c- means, that does not require training data sets and produces comparable results is proposed.

Paper Details

Date Published: 1 June 1992
PDF: 10 pages
Proc. SPIE 1652, Medical Imaging VI: Image Processing, (1 June 1992); doi: 10.1117/12.59477
Show Author Affiliations
Laurence P. Clarke, Univ. of South Florida Colleges of Engineering and Medicine (United States)
Robert Paul Velthuizen, Univ. of South Florida Colleges of Engineering and Medicine (United States)
Lawrence O. Hall, Univ. of South Florida Colleges of Engineering and Medicine (United States)
James C. Bezdek, Univ. of West Florida (United States)
Amine M. Bensaid, Univ. of South Florida Colleges of Engineering and Medicine (United States)
Martin L. Silbiger, Univ. of South Florida Colleges of Engineering and Medicine (United States)


Published in SPIE Proceedings Vol. 1652:
Medical Imaging VI: Image Processing
Murray H. Loew, Editor(s)

© SPIE. Terms of Use
Back to Top