An end-to-end system to automate the well-known Tanner - Whitehouse (TW3) clinical procedure to estimate the skeletal age in childhood is proposed. The system comprises the detailed analysis of the two most important bones in TW3: the radius and ulna wrist bones. First, a modified version of an adaptive clustering segmentation algorithm is presented to properly semi-automatically segment the contour of the bones. Second, up to 89 features are defined and extracted from bone contours and gray scale information inside the contour, followed by some well-founded feature selection mathematical criteria, based on the ideas of maximizing the classes{\textquoteright} separability. Third, bone age is estimated with the help of a Generalized Softmax Perceptron (GSP) neural network (NN) that, after supervised learning and optimal complexity estimation via the application of the recently developed Posterior Probability Model Selection (PPMS) algorithm, is able to accurately predict the different development stages in both radius and ulna from which and with the help of the TW3 methodology, we are able to conveniently score and estimate the bone age of a patient in years, in what can be understood as a multiple-class (multiple stages) pattern recognition approach with posterior probability estimation. Finally, numerical results are presented to evaluate the system performance in predicting the bone stages and the final patient bone age over a private hand image database, with the help of the pediatricians and the radiologists expert diagnoses. {\^A}{\textcopyright} 2006 IEEE.

}, keywords = {Age Determination by Skeleton, Aging, Algorithms, Artificial Intelligence, Automated, Bone, Bone age assessment, Clustering algorithms, Computer-Assisted, Humans, Model selection, Neural networks, Pattern recognition, Radiographic Image Interpretation, Reproducibility of Results, Sensitivity and Specificity, Skeletal maturity, algorithm, article, artificial neural network, automation, bone age, bone maturation, childhood, instrumentation, radius, ulna}, issn = {00189294}, doi = {10.1109/TBME.2008.918554}, url = {http://www.scopus.com/inward/record.url?eid=2-s2.0-42249094547\&partnerID=40\&md5=2cecfea5f75a61b048611f2391b00aed}, author = {Antonio Trist{\'a}n-Vega and J I Arribas} } @conference {417, title = {A radius and ulna skeletal age assessment system}, booktitle = {2005 IEEE Workshop on Machine Learning for Signal Processing}, year = {2005}, address = {Mystic, CT}, abstract = {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 J I Arribas} }