A Novel 3D Segmentation of Vertebral Bones from Volumetric CT Images Using Graph Cuts

Authors:
Melih S. Aslan;Asem Ali;Ham Rara;Ben Arnold;Aly A. Farag;Rachid Fahmi;Ping Xiang
Affiliations:
Computer Vision and Image Processing Laboratory (CVIP Lab), University of Louisville, Louisville 40292;Computer Vision and Image Processing Laboratory (CVIP Lab), University of Louisville, Louisville 40292;Computer Vision and Image Processing Laboratory (CVIP Lab), University of Louisville, Louisville 40292;Image Analysis, Inc, Columbia, USA 42728;Computer Vision and Image Processing Laboratory (CVIP Lab), University of Louisville, Louisville 40292;Computer Vision and Image Processing Laboratory (CVIP Lab), University of Louisville, Louisville 40292;Image Analysis, Inc, Columbia, USA 42728
Venue:
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part II
Year:
2009

Citing 5
Cited 1

An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision

IEEE Transactions on Pattern Analysis and Machine Intelligence
Correlation Pattern Recognition

Correlation Pattern Recognition
Automatic Lung Segmentation of Volumetric Low-Dose CT Scans Using Graph Cuts

ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing
Segmentation of trabecular bones from vertebral bodies in volumetric CT spine images

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Automated segmentation of acetabulum and femoral head from 3-d CT images

IEEE Transactions on Information Technology in Biomedicine

Heterogeneous computing for vertebra detection and segmentation in x-ray images

Journal of Biomedical Imaging - Special issue on Parallel Computation in Medical Imaging Applications

Quantified Score

Hi-index	0.01

Visualization

Abstract

Bone mineral density (BMD ) measurements and fracture analysis of the spine bones are restricted to the Vertebral bodies (VBs ). In this paper, we present a novel and fast 3D segmentation framework of VBs in clinical CT images using the graph cuts method. The Matched filter is employed to detect the VB region automatically. In the graph cuts method, a VB (object) and surrounding organs (background) are represented using a gray level distribution models which are approximated by a linear combination of Gaussians (LCG) to better specify region borders between two classes (object and background). Initial segmentation based on the LCG models is then iteratively refined by using MGRF with analytically estimated potentials. In this step, the graph cuts is used as a global optimization algorithm to find the segmented data that minimize a certain energy function, which integrates the LCG model and the MGRF model. Validity was analyzed using ground truths of data sets (expert segmentation) and the European Spine Phantom (ESP ) as a known reference. Experiments on the data sets show that the proposed segmentation approach is more accurate than other known alternatives.