Automated anatomy detection in CT localizer images
Axel Saalbach, Martin Bergtholdt, Thomas Netsch, Julien Sénégas · 2015
In this paper we present a system for the automated detection of multiple anatomies in computer tomography (CT) localizer images. The proposed method employs classification cascades for the fast and accurate localization of individual anatomies. In order to facilitate the joint localization of multiple anatomies, their geometric relations are described in terms of a probabilistic model. This gives rise to a part-based detection approach which allows for the consolidation of multiple detections and the prediction of missed anatomies. The performance of the approach is quantitatively evaluated on a comprehensive set of 737 CT localizer images for five individual and three combined anatomies.