Abstract:
Skeletal age assessment is a common and time-consuming task in pediatric radiology. In this work we describe a system which implements the TW2 method, using a neural netw...Show MoreMetadata
Abstract:
Skeletal age assessment is a common and time-consuming task in pediatric radiology. In this work we describe a system which implements the TW2 method, using a neural network architecture. Each bone complex is localized on the image, and preprocessed using either a Gabor transform or a multiscale difference of Gaussian filtering. The output of the preprocessing stage is fed to a set of neural networks trained to classify each bone accordingly to the TW2 method. Afterward, the skeletal age is estimated and compared with the classification of an expert radiologist.
Date of Conference: 14-17 September 2003
Date Added to IEEE Xplore: 24 November 2003
Print ISBN:0-7803-7750-8
Print ISSN: 1522-4880