Supervised classification of brain tissues through local multi-scale texture analysis by coupling DIR and FLAIR MR sequences

Abstract

The automatic segmentation of brain tissues in magnetic resonance (MR) is usually performed on T1-weighted images, due to their high spatial resolution. T1w sequence, however, has some major downsides when brain lesions are present: the altered appearance of diseased tissues causes errors in tissues classification. In order to overcome these drawbacks, we employed two different MR sequences: fluid attenuated inversion recovery (FLAIR) and double inversion recovery (DIR). The former highlights both gray matter (GM) and white matter (WM), the latter highlights GM alone.We propose here a supervised classification scheme that does not require any anatomical a priori information to identify the 3 classes, "GM", "WM", and "background". Features are extracted by means of a local multi-scale texture analysis, computed for each pixel of the DIR and FLAIR sequences. The 9 textures considered are average, standard deviation, kurtosis, entropy, contrast, correlation, energy, homogeneity, and skewness, evaluated on a neighborhood of 3x3, 5x5, and 7x7 pixels. Hence, the total number of features associated to a pixel is 56 (9 textures ×3 scales ×2 sequences +2 original pixel values). The classifier employed is a Support Vector Machine with Radial Basis Function as kernel.From each of the 4 brain volumes evaluated, a DIR and a FLAIR slice have been selected and manually segmented by 2 expert neurologists, providing 1 st and 2 nd human reference observations which agree with an average accuracy of 99.03%. SVM performances have been assessed with a 4-fold cross-validation, yielding an average classification accuracy of 98.79%.

3D volume reconstruction of brain tissues using nonlinear filters, k-means clustering, and Bland-Altman analysis

“…I is an image with dimension L x L, µ is mean the 1 st moment, σ is standard deviation, square of the 2 nd central moment and are defined as [17]:…”

Differentiation of brain metastases in MRI image using the first and second-order statistical features

“…b) The first-order features The skewness and the kurtosis are intensity features and measure the asymmetry and the peakedness (or the heaviness of the tails) of the distribution, respectively [13,14]. The skewness is defined as,…”

“…c) The second-order features are devoted to the joint probability occurrence of a specific pair of gray values for a pair of pixels randomly placed. Usually, the 2 nd order features are computable from the gray level co-occurrence matrices being texture features C d (i, j) constructed for an image I with the pair of gray levels i, j that are placed at a distance d [13],…”

“…x y otherwise (9) here, d = (dx, dy) denotes the displacement vector. Entropy (E) and energy (EN) are features related to orderliness (regularity or commonness) of the data and are defined as [13].…”

Automatic Generation of Synthetic Retinal Fundus Images: Vascular Network

“…3 (a)) we computed five statistical texture descriptors 12,13 (Mean, Std, Skewness, Kurtosis and Entropy) on two near-circular windows of 6 pixel radii. The ensemble of these data, 6 EMHM parameters (X n×6 ) and 5 × 2 background texture descriptors (Y n×10 ) for each profile, for a total of 975 artery and 1593 vein profiles, collected from the 15 healthy subjects of the HRF dataset, constitute the measurements for the procedure proposed below.…”