Vol. 35, Issue 2, pp. 283-294 (2005)

Abstract

Skeletal age assessment is one of the important applications of hand radiography in the area of pediatric radiology. Feature analysis of the carpal-bones can reveal the important information for skeletal age assessment. The present work in this paper faces the problem of the detection of carpal -bone features from X-ray image. A novel and effective segmentation technique is presented in this work with carpal-bone image for skeletal age estimation. Carpal-bone segmentation is a critical operation of the automatic skeletal age assessment system. This method consists of two procedures. First, the original carpal-bone image is preprocessed via anisotropic diffusion filter. Then, the carpal-bone image is segmented by region based level set method. The basic idea of the region based level set method is to add a force that takes into account the information within the regions in order to add robustness and more efficiently separate homogeneous regions. Experiments are carried out on X-ray images of carpal-bone. The experimental results show that incorporating region statistical information into the level set method, an accurate and robust segmentation can be achieved.