Abstract
The thesis describes the construction of a carpal ossified model, and its applications to carpal bone age assessment and bone growth estimation procedures based on fuzzy criterion and statistical analysis. The growth model is focused on the childhood, i.e., the main growth stage of carpals. It’s composed of the statistics of morphological features of carpals, and the growth descriptors—weighting matrices. The morphological features we extracted are five kinds—T-Ratio, Ratio-I and II, and Compactness-I and II, and they are calculated from the preprocessed digital carpal images by hand and image processing methods. They can quantify the carpal ossified status in different ages. The weighting matrices include the longitudinal and transverse descriptions of the increase rate of a bone in each one-year-old growth stages. The weighting matrices we evaluated can indicate the overall dynamic processes and trends of the ossification of each part of carpals. Combining the geometric features, we can obtain the carpal growth model that can cover many aspects and benefit for the analysis of the ossification. In thesis, we also developed procedures for the bone ossification estimation and the bone age assessment based on the constructed model. The bone estimation procedures are investigated by the weighting matrices. The users can use a carpal image file that in well-known age and bone type, to estimate the status of its bone in all the other ages. Besides, we develop the carpal bone age assessment procedures based on fuzzy concept for the linearity of the morphological features. We combine the principle component analysis and the evaluation of correlation coefficients between feature value and age, to develop three categories of the bone age assessment procedures. The purpose is to make an attempt to acquire high-performed procedures that can provide reasonable results for helping the doctors or users judge the bone age. In clinic, error within 1.5 years old is acceptable. After simulations, the best correct rates within 1.5 years old error are 92.4% in female and 89.5% in male, respectively. The assessment by the proposed procedures is satisfactory for practice.