On determining a signature for skeletal maturity

We present a computational framework for semi-automated assessment of skeletal age based on a multi-scale image analysis approach. Through 2D digital X-ray images of the left hand, maturity indicators are searched by means of a two-step process: the user interactively indicates a point inside the middle finger, and the computational method analyzes the image intensity profile along this line, searching for physiological signatures related to different epiphyseal events (ossification, cartilage stage, early fusion and complete fusion). A scale-space approach is used to select the best scale to enhance the edges between the bones and soft tissues. Initial results indicate that this approach could be useful to facilitate the analysis of growth disorders in pediatrics