A Hierarchical Graph-Based Segmentation Technique for High-Resolution Volume Data

Abstract

This paper presents a novel interactive approach to the problem of segmenting high-resolution volume data. The segmentation process starts by constructing a hierarchical graph representation of a coarser resolution of the data that is small enough to fit in the video memory. This graph enables user to interactively sample and edit a feature of interest by drawing strokes on slices of the data while watching the images of the segmented volume. A subgraph representing the volumetric feature of interest is derived with a growing process, and can be used to extract the high-resolution version of the feature from the original volume data through an automatic mapping and refinement procedure performed based on the statistical properties of the voxels internal to the feature. Our hierarchical graph representation and the associated operations overcome the ambiguous boundary conditions called partial volume effects caused by down-sampling and provide three levels of details to support the segmentation of fine features. We demonstrate with several examples the effectiveness of such a highly interactive approach to challenging 3D segmentation tasks.

Cite this paper

@inproceedings{HuangAHG, title={A Hierarchical Graph-Based Segmentation Technique for High-Resolution Volume Data}, author={Runzhen Huang and Kwan-Liu Ma} }