Computer-assisted enhanced volumetric segmentation magnetic resonance imaging data using a mixture of artificial neural networks.

An accurate computer-assisted method able to perform regional segmentation on 3D single modality images and measure its volume is designed using a mixture of unsupervised and supervised artificial neural networks. Firstly, an unsupervised artificial neural network is used to estimate representative textures that appear in the images. The region of interest of the resultant images is selected by means of a multi-layer perceptron after a training using a single sample slice, which contains a central portion of the 3D region of interest. The method was applied to magnetic resonance imaging data collected from an experimental acute inflammatory model (T(2) weighted) and from a clinical study of human Alzheimer's disease (T(1) weighted) to evaluate the proposed method. In the first case, a high correlation and parallelism was registered between the volumetric measurements, of the injured and healthy tissue, by the proposed method with respect to the manual measurements (r = 0.82 and p < 0.05) and to the histopathological studies (r = 0.87 and p < 0.05). The method was also applied to the clinical studies, and similar results were derived of the manual and semi-automatic volumetric measurement of both hippocampus and the corpus callosum (0.95 and 0.88).

Monitoring acute inflammatory processes in mouse muscle by MR imaging and spectroscopy: a comparison with pathological results.

We have studied an animal model of acute local inflammation in muscle induced by Aspergillus fumigatus by using magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS). We have compared our data to those found using histopathology and segmentation maps obtained by the mathematical processing of three-dimensional T2-weighted MRI data via a neural network. The MRI patterns agreed satisfactorily with the clinical and biological evidence of the phases of acute local infection and its evolution towards chronicity. The MRS results show a statistically significant increase in inorganic phosphate and a significant decrease in phosphocreatine levels in the inflamed region. Image segmentation made with a self-organizing, neural-network map yielded a set of ordered representatives that remained constant for all animals during the inflammatory process, allowing a non-invasive, three-dimensional identification and quantification of the inflamed infected regions by MRI.