Improving image contrast using principal component analysis for subsequentimage segmentation

This article presents a technique for improving MR image contrast by linear ly combining multiple MR images with different tissue contrast. The weighti ng coefficients of the linear combination are derived using principal compo nent analysis. The contrast-enhanced composite image is segmented subsequen tly using gray level-based ID segmentation methods. The technique reduces a multispectral image set to composite eigenimages and allows application of appropriate ID segmentation methods that do not have equivalent counterpar ts in multispectral methods.