A MARKOV RANDOM-FIELD MODEL FOR BONY TISSUE CLASSIFICATION

3D biomedical images are a valuable source of information for clinical diagnosis. In areas such as bone remodeling, fracture prediction and prosthesis design, the external geometry of the bones needs to be prec isely defined and injuries identified. A system that automatically int erprets and presents a 3D reconstruction of the bone can be very usefu l, although this task cannot be carried out without specific knowledge of the domain. This knowledge may be represented by a set of constrai nts over properties and relationships between regions. In this work we present a Markov random field model for identification of injuries fo und in the proximal tibia. (C) 1998 Elsevier Science Ltd. All rights r eserved.