Automated model-based rib cage segmentation and labeling in CT images

Authors:
Tobias Klinder;Cristian Lorenz;Jens Von Berg;Sebastian P. M. Dries;Thomas Bülow;Jörn Ostermann
Affiliations:
Institut für Informationsverarbeitung, University of Hannover, Germany and Philips Research Europe-Hamburg, Sector Medical Imaging Systems, Germany;Philips Research Europe-Hamburg, Sector Medical Imaging Systems, Germany;Philips Research Europe-Hamburg, Sector Medical Imaging Systems, Germany;Philips Research Europe-Hamburg, Sector Medical Imaging Systems, Germany;Philips Research Europe-Hamburg, Sector Medical Imaging Systems, Germany;Institut für Informationsverarbeitung, University of Hannover, Germany
Venue:
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
Year:
2007

Citing 3
Cited 3

A Method for Registration of 3-D Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Direct Least Square Fitting of Ellipses

IEEE Transactions on Pattern Analysis and Machine Intelligence
Approximate Thin Plate Spline Mappings

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III

Spine Segmentation Using Articulated Shape Models

MICCAI '08 Proceedings of the 11th international conference on Medical Image Computing and Computer-Assisted Intervention - Part I
Removal of abdominal wall for 3D visualization and segmentation of organs in CT volume

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Segmentation of the cartilage in the rib cage in 3d MRI

MICCAI'12 Proceedings of the 4th international conference on Abdominal Imaging: computational and clinical applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a new model-based approach for an automated labeling and segmentation of the rib cage in chest CT scans. A mean rib cage model including a complete vertebral column is created out of 29 data sets. We developed a ray search based procedure for rib cage detection and initial model pose. After positioning the model, it was adapted to 18 unseen CT data. In 16 out of 18 data sets, detection, labeling, and segmentation succeeded with a mean segmentation error of less than 1.3 mm between true and detected object surface. In one case the rib cage detection failed, in another case the automated labeling.