Syntactic recognition of skeletal maturity

A hierarchical three-stage syntactic recognition algorithm using context-free grammars is described for automatic identification of skeletal maturity from X-rays of hand and wrist. The primitives considered are dot, straight line and arcs of three different curvatures (including both senses) in order to describe and interpret the structural development of epiphysis and metaphysis with growth of a child. 1. Introduction The classifier is based on a hierarchical syntactic approach (Fu (1982» which accepts contours of The paper describes an algorithm for syntactic the epiphysis and metaphysis as input. Its effec­ recognition of different stages of maturity of tiveness is demonstrated on an X-ray image of bones from X-rays of the hand and wrist. The ulti­ radius of a 10-12 year old boy when dot, line and mate aim is to be able to make computer-diagnosis arcs of three different curvature are considered as of diseases and effects of malnutrition on the primitives. skeletal growth of a child. During growth of a child, each of the bones of the hand and wriSt provides us with an invariant 2. Different stages of maturity sequence of events which invariably occur in the same order in all individuals and cover the develop­ Fig. 1 shows eight different stages of skeletal mental age-span evenly and completely. These maturity of radius of hand and wrist. This is con­ sequences therefore give us bases for defining di f­