A multilevel neural network model for density volumes classifications

In this paper we present an approach for the classification of tissue density in three dimensional brain tomographic scans. The proposed approach is based on a hierarchical neural network model able to classify the single voxel of the examined dataset. The results have shown that the method has a good effectiveness in practical applications and that it can be used for designing a full 3D instrument suitable to support the analysis of diseased diagnosis and follow-up.