This paper presents a general methodology for computer interpretation
and integration of medical images. Ai I explicit anatomical model, as
well as other domain knowledge, is used to facilitate feature extracti
on and the fusion of images from different modalities. A frame represe
ntation is used to implement the description of important anatomical f
eatures and other domain knowledge. Frames are also used to implement
the control mechanisms that establish communication between the image
data and the symbolic knowledge. A prototype system for reconstructing
the human cerebral vasculature is presented. (C) 1997 Elsevier Scienc
e Ltd. All rights reserved.