EVALUATION OF RIDGE SEEKING OPERATORS FOR MULTIMODALITY MEDICAL IMAGEMATCHING

Ridge-like structures in digital images may be extracted by convolving the images with derivatives of Gaussians. The choice of the convoluti on operator and of the parameters involved defines a specific ridge im age. In this paper, various ridge measures related to isophote curvatu re are constructed, reviewed, and evaluated with respect to their usab ility in CT/MRI matching of human brain scans. construction is initial ly done using heuristics in two-dimensional images, and then establish ed firmly in a mathematical framework. Attention is paid to the necess ity of operator invariance, scale of the operator, extension to three- dimensional images, and relations to isophote and principal curvature. It will be shown that one of the ridge measures appears well suited f or the purpose of matching, despite the fact that the measure fails to detect ridges in a number of stylized scenes.