Texture feature selection with relevance learning to classify interstitial lung disease patterns

Mar, 2011

The Generalized Matrix Learning Vector Quantization (GMLVQ) is used to estimate the relevance of texture features in their ability to classify interstitial lung disease patterns in high-resolution computed tomography (HRCT) images. After a stochastic gradient descent, the GMLVQ algorithm provides a discriminative distance measure of relevance factors, which can account for pairwise correlations between different texture features and their importance for the classification of healthy and diseased patterns. Texture features were extracted from gray-level co-occurrence matrices (GLCMs), and were ranked and selected according to their relevance obtained by GMLVQ and, for comparison, to a mutual information (MI) criteria. A k-nearest-neighbor (kNN) classifier and a Support Vector Machine with a radial basis function kernel (SVMrbf) were optimized in a 10-fold crossvalidation for different texture feature sets. In our experiment with real-world data, the feature sets selected by the GMLVQ approach had a significantly better classification performance compared with feature sets selected by a MI ranking

Link

@INPROCEEDINGS{Huber2011,
author = {Markus~B. Huber and Kerstin Bunte and Mahesh~B. Nagarajan and Michael Biehl and L.~A. Ray and Axel Wism\"uller},
title = {Texture feature selection with relevance learning to classify interstitial lung disease patterns},
volume = {7963:43},
editor = {Ronald M. Summers M.D. and Bram van Ginneken},
booktitle = {SPIE Medical Imaging: Computer-Aided Diagnosis},
doi = {10.1117/12.877894},
url = {http://dx.doi.org/10.1117/12.877894},
month = {"Mar."},
year = {2011},
abstract = {The Generalized Matrix Learning Vector Quantization (GMLVQ) is used to estimate the relevance of texture features in their ability to classify interstitial lung disease patterns  in high-resolution computed tomography (HRCT) images.  After a stochastic gradient descent, the GMLVQ algorithm provides a discriminative distance measure of relevance factors,  which can account for pairwise correlations between different texture features and their importance for the classification of healthy and diseased patterns.  Texture features were extracted from gray-level co-occurrence matrices (GLCMs), and were ranked and selected according to their relevance obtained by GMLVQ and,  for comparison, to a mutual information (MI) criteria. A k-nearest-neighbor (kNN) classifier and a Support Vector Machine with a radial basis function kernel (SVMrbf)  were optimized in a 10-fold crossvalidation for different texture feature sets.  In our experiment with real-world data, the feature sets selected by the GMLVQ approach had a significantly better classification performance compared with feature sets selected by a MI ranking},
}