Applying a visual segmentation algorithm to brain structures MR images.

A variation of the neural algorithm LEGION (Locally Excitatory Globally Inhibitory Network) has been developed for the automatic visual segmentation of T1-weighted 2-D head magnetic resonance images. The network obtains good performances segmenting skull, brain in all its ramifications as other structures within the skull, like cerebellum, Corpus Callosum and Brain Stem. These results can be used for MEG source modeling. Putting together the results on all the processed 2-D images of one volume we'll be able to have 3-D segmentation results which can be used to generate surface and volume tessellations suitable for FEM (Finite Element Method) forward field calculations. We have applied the algorithm to several MRI Images. Despite the diversity of the images the neural network shows good robustness.