3D Segmentation for Multi-Organs in CT Images

Authors

  • Mariusz Bajger Medical Devices Research Institute School of Computer Science, Engineering and Mathematics Flinders University
  • Gobert Lee Medical Devices Research Institute School of Computer Science, Engineering and Mathematics Flinders University
  • Martin Caon Medical Devices Research Institute School of Nursing and Midwifery Flinders University

Abstract

The study addresses the challenging problem of automatic segmentation of the human anatomy needed for radiation dose calculations.
Three-dimensional extensions of two well-known state-of-the art segmentation techniques are proposed and tested for usefulness on a set of clinical CT images.
The new techniques are 3D Statistical Region Merging (3D-SRM) and 3D Efficient Graph-based Segmentation (3D-EGS). Segmentations of eight representative tissues (lungs, stomach, liver, heart, kidneys, spleen, bones and the spinal cord)
were tested for accuracy using the Dice index, the Hausdorff distance and the $H_t$ index. The 3D-SRM outperformed 3D-EGS producing the average
(across the 8 tissues) Dice index, the Hausdorff distance, and the $H_2$ of $0.89$, $12.5$~mm and $0.93$, respectively.

Keywords

Voxel model, image segmentation, statistical region merging, efficient graph-based segmentation, full-body CT

Published

12-04-2013

Downloads

Download data is not yet available.