A multi-modal approach to segmentation of tubular structures

Abstract

In this paper we describe a new paradigm for interactive segmentation of medical 3D volume data.We are using a 3D haptic device to enhance the segmentation process with additional sensory feedback. The segmentation of tubular structures in the human body serves as an initial case study for our system. The haptic interaction allows the user to extract the centerline of a tubular structure, even if the image data quality is insufficient. The segmented path is then used to reorient crosssections through the data volume, which helps to extract the boundary of the 3D object in a subsequent step.