Automatic segmentation of the pelvic bones from CT data based on a statistical shape model

Authors:
H. Seim;D. Kainmueller;M. Heller;H. Lamecker;S. Zachow;H.-C. Hege
Affiliations:
Medical Planning Group, Zuse-Institute Berlin, Berlin, Germany;Medical Planning Group, Zuse-Institute Berlin, Berlin, Germany;Julius Wolff Institut and Center for Musculoskeletal Surgery Charité-Universitätsmedizin Berlin, Germany;Medical Planning Group, Zuse-Institute Berlin, Berlin, Germany;Medical Planning Group, Zuse-Institute Berlin, Berlin, Germany;Medical Planning Group, Zuse-Institute Berlin, Berlin, Germany
Venue:
EG VCBM'08 Proceedings of the First Eurographics conference on Visual Computing for Biomedicine
Year:
2008

Citing 6
Cited 6

A survey of the Hough transform

Computer Vision, Graphics, and Image Processing
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision

IEEE Transactions on Pattern Analysis and Machine Intelligence
Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Hip Bone Segmentation Using Non-Rigid Registration

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Coupling Deformable Models for Multi-object Segmentation

ISBMS '08 Proceedings of the 4th international symposium on Biomedical Simulation
Statistical atlases of bone anatomy: construction, iterative improvement and validation

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I

Automatic Extraction of Mandibular Nerve and Bone from Cone-Beam CT Data

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Automated Segmentation of the Femur and Pelvis from 3D CT Data of Diseased Hip Using Hierarchical Statistical Shape Model of Joint Structure

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Automatic extraction of anatomical landmarks from medical image data: an evaluation of different methods

ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Improving deformable surface meshes through omni- directional displacements and MRFs

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
Interactive segmentation of volumetric medical images for collaborative telemedicine

3DPH'09 Proceedings of the 2009 international conference on Modelling the Physiological Human
Simultaneous segmentation and correspondence establishment for statistical shape models

3DPH'09 Proceedings of the 2009 international conference on Modelling the Physiological Human

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an algorithm for automatic segmentation of the human pelvic bones from CT datasets that is based on the application of a statistical shape model. The proposed method is divided into three steps: 1) The averaged shape of the pelvis model is initially placed within the CT data using the Generalized Hough Transform, 2) the statistical shape model is then adapted to the image data by a transformation and variation of its shape modes, and 3) a final free-form deformation step based on optimal graph searching is applied to overcome the restrictive character of the statistical shape representation. We thoroughly evaluated the method on 50 manually segmented CT datasets by performing a leave-one-out study. The Generalized Hough Transform proved to be a reliable method for an automatic initial placement of the shape model within the CT data. Compared to the manual gold standard segmentations, our automatic segmentation approach produced an average surface distance of 1.2 ± 0.3mm after the adaptation of the statistical shape model, which could be reduced to 0.7±0.3mm using a final free-form deformation step. Together with an average segmentation time of less than 5 minutes, the results of our study indicate that our method meets the requirements of clinical routine.