Automatic segmentation of subcortical brain structures in MR images using information fusion

This paper reports a new automated method for the segmentation of internal cerebral structures using an information fusion technique. The information is provided both by images and expert knowledge, and consists in morphologi cal, topological, and tissue constitution data. All this ambiguous, complem entary and redundant information is managed using a three-step fusion schem e based on fuzzy logic. The information is first modeled into a common theo retical frame managing its imprecision and incertitude. The models are then fused and a decision is taken in order to reduce the imprecision and to in crease the certainty in the location of the structures. The whole process i s illustrated on the segmentation of thalamus, putamen, and head of the cau date nucleus from expert knowledge and magnetic resonance images, in a prot ocol involving 14 healthy volunteers. The quantitative validation is achiev ed by comparing computed, manually segmented structures and published data by means of indexes assessing the accuracy of volume estimation and spatial location. Results suggest a consistent volume estimation with respect to t he expert quantification and published data, and a high spatial similarity of the segmented and computed structures. This method is generic and applic able to any structure that can be defined by expert knowledge and morpholog ical images.