An end to end system to partially automate the TW3 bone age assessment procedure is proposed. The system comprises the detailed analysis of the two more important bones in TW3: the radius and ulna wrist bones. First, a generalization of K-means algorithm is presented to semi-automatically segment the contour of the bones and thus extract up to 89 features describing shapes and textures from bones. Second, a well-founded feature selection criterion based on the statistical properties of data is used in order to properly choose the most relevant features. Third, bone age is estimated with the help of a Generalized Softmax Perceptron (GSP) Neural Network (NN) whose optimal complexity is estimated via the Posterior Probability Model Selection (PPMS) algorithm. We can then predict the different development stages in both radius and ulna, from which we are able to score and estimate the bone age of a patient in years and finally we compare the NN results with those from the pediatrician expert discrepancies. {\^A}{\textcopyright} 2005 IEEE.

}, keywords = {Algorithms, Bone, Feature extraction, Generalized Softmax Perceptron (GSP), Living systems studies, Neural networks, Probability Model Selection (PPMS), Skeletal age assessment system}, isbn = {0780395174; 9780780395176}, doi = {10.1109/MLSP.2005.1532903}, url = {http://www.scopus.com/inward/record.url?eid=2-s2.0-33749052083\&partnerID=40\&md5=eefa29ac09f4efa304b613cf07ab8d10}, author = {Antonio Trist{\'a}n-Vega and Juan I. Arribas} }