Share Email Print
cover

Proceedings Paper

Effective classification of 3D image data using partitioning methods
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We propose partitioning-based methods to facilitate the classification of 3-D binary image data sets of regions of interest (ROIs) with highly non-uniform distributions. The first method is based on recursive dynamic partitioning of a 3-D volume into a number of 3-D hyper-rectangles. For each hyper-rectangle, we consider, as a potential attribute, the number of voxels (volume elements) that belong to ROIs. A hyper-rectangle is partitioned only if the corresponding attribute does not have high discriminative power, determined by statistical tests, but it is still sufficiently large for further splitting. The final discriminative hyper-rectangles form new attributes that are further employed in neural network classification models. The second method is based on maximum likelihood employing non-spatial (k-means) and spatial DBSCAN clustering algorithms to estimate the parameters of the underlying distributions. The proposed methods were experimentally evaluated on mixtures of Gaussian distributions, on realistic lesion-deficit data generated by a simulator conforming to a clinical study, and on synthetic fractal data. Both proposed methods have provided good classification on Gaussian mixtures and on realistic data. However, the experimental results on fractal data indicated that the clustering-based methods were only slightly better than random guess, while the recursive partitioning provided significantly better classification accuracy.

Paper Details

Date Published: 12 March 2002
PDF: 12 pages
Proc. SPIE 4665, Visualization and Data Analysis 2002, (12 March 2002); doi: 10.1117/12.458811
Show Author Affiliations
Vasileios Megalooikonomou, Temple Univ. (United States)
Dragoljub Pokrajac, Temple Univ. (United States)
Aleksandar Lazarevic, Temple Univ. (United States)
Zoran Obradovic, Temple Univ. (United States)


Published in SPIE Proceedings Vol. 4665:
Visualization and Data Analysis 2002
Robert F. Erbacher; Philip C. Chen; Matti Groehn; Jonathan C. Roberts; Craig M. Wittenbrink, Editor(s)

© SPIE. Terms of Use
Back to Top