Vertebral body segmentation with GrowCut: Initial experience, workflow and practical application

TL;DR

This paper explores the use of the GrowCut algorithm in 3D Slicer for vertebral body segmentation, demonstrating it as a faster alternative to manual segmentation with initial promising results.

Contribution

First study applying GrowCut to vertebral body segmentation, showing its potential as an efficient semi-automatic segmentation tool.

Findings

GrowCut segmentation times are consistently less than manual segmentation.

GrowCut offers a practical alternative to manual slice-by-slice segmentation.

Initial results support further development and validation.

Abstract

In this contribution, we used the GrowCut segmentation algorithm publicly available in three-dimensional Slicer for three-dimensional segmentation of vertebral bodies. To the best of our knowledge, this is the first time that the GrowCut method has been studied for the usage of vertebral body segmentation. In brief, we found that the GrowCut segmentation times were consistently less than the manual segmentation times. Hence, GrowCut provides an alternative to a manual slice-by-slice segmentation process.