Background: Regularized regression methods such as principal component or partial least squares regression perform well in learning tasks on high dimensional spectral data, but cannot explicitly eliminate irrelevant features. The random forest classifier with its associated Gini feature importance, on the other hand, allows for an explicit feature elimination, but may not be optimally adapted to spectral data due to the topology of its constituent classification trees which are based on orthogonal splits in feature space.Results: We propose to combine the best of both approaches, and evaluated the joint use of a feature selection based on a recursive feature elimination using the Gini importance of random forests' together with regularized classification methods on spectral data sets from medical diagnostics, chemotaxonomy, biomedical analytics, food science, and synthetically modified spectral data. Here, a feature selection using the Gini feature importance with a regularized classification by discriminant partial least squares regression performed as well as or better than a filtering according to different univariate statistical tests, or using regression coefficients in a backward feature elimination. It outperformed the direct application of the random forest classifier, or the direct application of the regularized classifiers on the full set of features.Conclusion: The Gini importance of the random forest provided superior means for measuring feature relevance on spectral data, but – on an optimal subset of features – the regularized classifiers might be preferable over the random forest classifier, in spite of their limitation to model linear dependencies only. A feature selection based on Gini importance, however, may precede a regularized linear classification to identify this optimal subset of features, and to earn a double benefit of both dimensionality reduction and the elimination of noise from the classification task.

Mean kurtosis and linearly related kurtosis tensor parameters are potential new noninvasive biomarkers in the grading of gliomas. PurposeTo assess the diagnostic accuracy of diffusion kurtosis magnetic resonance imaging parameters in grading gliomas.Materials and MethodsThe institutional review board approved this prospective study, and informed consent was obtained from all patients. Diffusion parameters—mean diffusivity (MD), fractional anisotropy (FA), mean kurtosis, and radial and axial kurtosis—were compared in the solid parts of 17 high-grade gliomas and 11 low-grade gliomas (P<.05 significance level, Mann-Whitney-Wilcoxon test, Bonferroni correction). MD, FA, mean kurtosis, radial kurtosis, and axial kurtosis in solid tumors were also normalized to the corresponding values in contralateral normal-appearing white matter (NAWM) and the contralateral posterior limb of the internal capsule (PLIC) after age correction and were compared among tumor grades.ResultsMean, radial, and axial kurtosis were significantly higher in high-grade gliomas than in low-grade gliomas (P = .02, P = .015, and P = .01, respectively). FA and MD did not...