Share Email Print
cover

Proceedings Paper

Interactive surface correction for 3D shape based segmentation
Author(s): Tobias Schwarz; Tobias Heimann; Ralf Tetzlaff; Anne-Mareike Rau; Ivo Wolf; Hans-Peter Meinzer
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Statistical shape models have become a fast and robust method for segmentation of anatomical structures in medical image volumes. In clinical practice, however, pathological cases and image artifacts can lead to local deviations of the detected contour from the true object boundary. These deviations have to be corrected manually. We present an intuitively applicable solution for surface interaction based on Gaussian deformation kernels. The method is evaluated by two radiological experts on segmentations of the liver in contrast-enhanced CT images and of the left heart ventricle (LV) in MRI data. For both applications, five datasets are segmented automatically using deformable shape models, and the resulting surfaces are corrected manually. The interactive correction step improves the average surface distance against ground truth from 2.43mm to 2.17mm for the liver, and from 2.71mm to 1.34mm for the LV. We expect this method to raise the acceptance of automatic segmentation methods in clinical application.

Paper Details

Date Published: 11 March 2008
PDF: 8 pages
Proc. SPIE 6914, Medical Imaging 2008: Image Processing, 69143O (11 March 2008); doi: 10.1117/12.770350
Show Author Affiliations
Tobias Schwarz, German Cancer Research Ctr. (Germany)
Tobias Heimann, German Cancer Research Ctr. (Germany)
Ralf Tetzlaff, German Cancer Research Ctr. (Germany)
Anne-Mareike Rau, German Cancer Research Ctr. (Germany)
Ivo Wolf, German Cancer Research Ctr. (Germany)
Hans-Peter Meinzer, German Cancer Research Ctr. (Germany)


Published in SPIE Proceedings Vol. 6914:
Medical Imaging 2008: Image Processing
Joseph M. Reinhardt; Josien P. W. Pluim, Editor(s)

© SPIE. Terms of Use
Back to Top