Texture analysis and classification of soft tissues in Computed Tomography (CT) images recently advanced with a new approach that disambiguates the checkboard problem where two distinctly different patterns produce identical co-occurrence matrices, but this method quadruples the size of the feature space. The feature space size problem is exacerbated by the use of varying sized texture operators for improving boundary segmentation. Dimensionality reduction motivates this investigation into systematic analysis of the power of feature categories (Haralick descriptors, distance, and direction) to differentiate between soft tissues. The within-organ variance explained by the individual components of feature categories offers a ranking of their potential power for between-organ discrimination. This paper introduces a technique for combining the Principal Component Analysis (PCA) results to compare and visualize the explanatory power of features with varying window sizes. We found that 1) the two Haralick features Cluster Tendency and Contrast contribute the most; 2) as distance increases, its contribution to overall variance decreases; and 3) direction is unimportant. We also evaluated the proposed technique with respect to its classification power. Linear Discriminant Analysis (LDA) and Decision Tree (DT) were used to produce two classification models based on the reduced data set. We found that using PCA either fails to improve or markedly degrades the classification performance of LDA as well as of the DT model. Though feature extraction for classification shows no promise, the proposed technique offers a systematic mechanism to compare feature reduction strategies for varying window sizes as well as other measurement techniques.
[1]
Jin Young Choi,et al.
PCA-based feature extraction using class information
,
2005,
2005 IEEE International Conference on Systems, Man and Cybernetics.
[2]
Mark A. Hall,et al.
Correlation-based Feature Selection for Machine Learning
,
2003
.
[3]
Ron Kohavi,et al.
Wrappers for Feature Subset Selection
,
1997,
Artif. Intell..
[4]
J. Furst,et al.
Pixel-Based Texture Classification of Tissues in Computed Tomography
,
2006
.
[5]
Jacob D. Furst,et al.
Classification of Tissues in Computed Tomography using Decision Trees
,
2004
.
[6]
Jacob D. Furst,et al.
Wavelet-based texture classification of tissues in computed tomography
,
2005,
18th IEEE Symposium on Computer-Based Medical Systems (CBMS'05).
[7]
Jacob D. Furst,et al.
Contrast enhancement of soft tissues in computed tomography images
,
2006,
SPIE Medical Imaging.
[8]
Jacob D. Furst,et al.
A classification approach for anatomical regions segmentation
,
2005,
IEEE International Conference on Image Processing 2005.
[9]
Horst Bischof,et al.
Why to Combine Reconstructive and Discriminative Information for Incremental Subspace Learning
,
2006
.
[10]
Robert M. Haralick,et al.
Textural Features for Image Classification
,
1973,
IEEE Trans. Syst. Man Cybern..