Segmentation of clinical structures for radiotherapy treatment planning: a comparison of two morphological approaches

Abstract

The segmentation of therapy-relevant structures is an important but time consuming stage in radiotherapy treatment planning. This paper compares the accuracy of two automatic approaches founded in mathematical morphology by examining their performance in segmenting the bladder in CT studies of the human pelvis. Both automatic approaches are evaluated with respect to a gold standard average manual segmentation derived from delineations produced by five clinical experts. The initial results show that although the segmentations produced by both morphological operators are similar there is still a need for manual interaction.