Search

This work investigates the capability of supervised classification methods in detecting both major tissues and subcortical structures using multispectral brain magnetic resonance images. First, by means of a realistic digital brain phantom, we investigated the classification performance of various Discriminant Analysis methods, K-Nearest Neighbor and Support Vector Machine. Then, using phantom and real data, we quantitatively assessed the benefits of integrating anatomical information in the classification, in the form of voxels coordinates as additional features to the intensities or tissue probabilistic atlases as priors. In addition we tested the effect of spatial correlations between neighboring voxels and image denoising. For each brain tissue we measured the classification performance in terms of global agreement percentage, false positive and false negative rates and kappa coefficient. The effectiveness of integrating spatial information or a tissue probabilistic atlas has been demonstrated for the aim of accurately classifying brain magnetic resonance images., (Copyright © 2014 Elsevier Ltd. All rights reserved.)

Knowledge of the exact spatial distribution of brain tissues in images acquired by magnetic resonance imaging (MRI) is necessary to measure and compare the performance of segmentation algorithms. Currently available physical phantoms do not satisfy this requirement. State-of-the-art digital brain phantoms also fall short because they do not handle separately anatomical structures (e.g. basal ganglia) and provide relatively rough simulations of tissue fine structure and inhomogeneity. We present a software procedure for the construction of a realistic MRI digital brain phantom. The phantom consists of hydrogen nuclear magnetic resonance spin-lattice relaxation rate (R1), spin-spin relaxation rate (R2), and proton density (PD) values for a 24 × 19 × 15.5 cm volume of a "normal" head. The phantom includes 17 normal tissues, each characterized by both mean value and variations in R1, R2, and PD. In addition, an optional tissue class for multiple sclerosis (MS) lesions is simulated. The phantom was used to create realistic magnetic resonance (MR) images of the brain using simulated conventional spin-echo (CSE) and fast field-echo (FFE) sequences. Results of mono-parametric segmentation of simulations of sequences with different noise and slice thickness are presented as an example of possible applications of the phantom. The phantom data and simulated images are available online at http://lab.ibb.cnr.it/., (Copyright © 2011 Elsevier B.V. All rights reserved.)

Segmentation (tissue classification) of medical images obtained from a magnetic resonance (MR) system is a primary step in most applications of medical image post-processing. This paper describes nonparametric discriminant analysis methods to segment multispectral MR images of the brain. Starting from routinely available spin-lattice relaxation time, spin-spin relaxation time, and proton density weighted images (T1w, T2w, PDw), the proposed family of statistical methods is based on: (i) a transform of the images into components that are statistically independent from each other; (ii) a nonparametric estimate of probability density functions of each tissue starting from a training set; (iii) a classic Bayes 0-1 classification rule. Experiments based on a computer built brain phantom (brainweb) and on eight real patient data sets are shown. A comparison with parametric discriminant analysis is also reported. The capability of nonparametric discriminant analysis in improving brain tissue classification of parametric methods is demonstrated. Finally, an assessment of the role of multispectrality in classifying brain tissues is discussed.