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 neighbouring 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.

A Riemannian manifold optimization strategy is proposed to facilitate the relaxation of the orthonormality constraint in a more natural way in the course of performing independent component analysis (ICA) that employs a mutual information-based source-adaptive contrast function. Despite the extensive development of manifold techniques catering to the orthonormality constraint, only a limited number of works have been dedicated to oblique manifold (OB) algorithms to intrinsically handle the normality constraint, which has been empirically shown to be superior to other Riemannian and Euclidean approaches. Imposing the normality constraint implicitly, in line with the ICA definition, essentially guarantees a substantial improvement in the solution accuracy, by way of increased degrees of freedom while searching for an optimal unmixing ICA matrix, in contrast with the orthonormality constraint. Designs of the steepest descent, conjugate gradient with Hager-Zhang or a hybrid update parameter, quasi-Newton, and cost-effective quasi-Newton methods intended for OB are presented in this paper. Their performance is validated using natural images and systematically compared with the popular state-of-the-art approaches in order to assess the performance effects of the choice of algorithm and the use of a Riemannian rather than Euclidean framework. We surmount the computational challenge associated with the direct estimation of the source densities using the improved fast Gauss transform in the evaluation of the contrast function and its gradient. The proposed OB schemes may find applications in the offline image/signal analysis, wherein, on one hand, the computational overhead can be tolerated, and, on the other, the solution quality holds paramount interest.

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 x 19 x 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/.