A Fuzzy Inference System for Skeletal Age Assessment in Living Individual

Skeletal age assessment is applied as an indicator of skeletal development for finding out growth pathologies related to hormonal diseases, and in endocrine and nutritional diagnosis. Other more recent applied methods include the Tanner and Whitehouse method as well as the Greulich and Pyle method. However, both methods need an expert to manually compare and assess the stages of skeletal growth. This is a time-consuming process involving subjective decision-making in pediatric radiology. The objective of this research is to develop a new fully automated and highly accurate approach based on a fuzzy inference system for the assessment of skeletal age in a living individual. Fuzzy logic as an intelligent computing technique is presented to deal with uncertainty as well as incomplete data. The system is implemented using MATLAB’s fuzzy tool box. Our system attempts to quantify eight features that correlate highly with growth and maturity of skeletal age. The system was evaluated with standard cases of hand radiographs for subjects between 11 and 17 years old. It has conclusively been found that there was a high linear relation between the system age assessment and chronological age, and our new method provides reliable results in the estimation of the skeletal age.