Texture feature ranking with relevance learning to classify interstitial lung disease patterns.

OBJECTIVE: 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 images. METHODOLOGY: 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. 65 texture features were extracted from gray-level co-occurrence matrices (GLCMs). These features were ranked and selected according to their relevance obtained by GMLVQ and, for comparison, to a mutual information (MI) criteria. The classification performance for different feature subsets was calculated for a k-nearest-neighbor (kNN) and a random forests classifier (RanForest), and support vector machines with a linear and a radial basis function kernel (SVMlin and SVMrbf). RESULTS: For all classifiers, feature sets selected by the relevance ranking assessed by GMLVQ had a significantly better classification performance (p<0.05) for many texture feature sets compared to the MI approach. For kNN, RanForest, and SVMrbf, some of these feature subsets had a significantly better classification performance when compared to the set consisting of all features (p<0.05). CONCLUSION: While this approach estimates the relevance of single features, future considerations of GMLVQ should include the pairwise correlation for the feature ranking, e.g. to reduce the redundancy of two equally relevant features.

Performance of topological texture features to classify fibrotic interstitial lung disease patterns.

PURPOSE: Topological texture features were compared in their ability to classify "honeycombing," a morphological pattern that is considered indicative for the presence of fibrotic interstitial lung disease in high-resolution computed tomography (HRCT) images. METHODS: For 14 patients with known occurrence of honeycombing, a stack of 70 axial, lung kernel reconstructed images was acquired from HRCT chest exams. A set of 964 regions of interest of both healthy and pathological (356) lung tissue was identified by an experienced radiologist. Texture features were extracted using statistical features (Stat), six properties calculated from gray-level co-occurrence matrices (GLCMs), Minkowski dimensions (MDs), and three Minkowski functionals (MFs) (e.g., MF.Euler). A naïve Bayes (NB) and k-nearest-neighbor (k-NN) classifier, a multilayer radial basis functions network (RBFN), and a support vector machine with a radial basis function (SVMrbf) kernel were optimized in a tenfold cross-validation for each texture vector, and the classification accuracy was calculated on independent test sets as a quantitative measure of automated tissue characterization. A Wilcoxon signed-rank test was used to compare two accuracy distributions and the significance thresholds were adjusted for multiple comparisons by the Bonferroni correction. RESULTS: The best classification results were obtained by the MF features, which performed significantly better than all the standard Stat, GLCM, and MD features (p < 0.001) for both classifiers. The highest accuracies were found for MF.Euler (93.6%, 94.9%, 94.2%, and 95.0% for NB, k-NN, RBFN, and SVMrbf, respectively). The best groups of standard texture features were a Stat and GLCM ("homogeneity") feature set (up to 91.8%). CONCLUSIONS: The results indicate that advanced topological texture features derived from MFs can provide superior classification performance in computer-assisted diagnosis of fibrotic interstitial lung disease patterns when compared to standard texture analysis methods.