A New Image Segmentation Method Based on Three-Dimensional Neural Network

Guo Fu Lin

doi:10.4028/www.scientific.net/AMR.490-495.157

Paper Titles

Adaptive Subdivision Surface Reconstruction for Scattered Data in Reverse Engineering Based on GPU
p.138

3D Model Reconstruction of the Broken Aeroengine Blade Based on the Laplacian of Guassian Detection
p.143

An Optimization Model for Aircraft Maintenance Scheduling Based on ABC Algorithm
p.147

Calculation of the Branching Ratio of the Process μ→eγ in a Model of Electroweak-Scale Right-Handed Neutrinos
p.152

A New Image Segmentation Method Based on Three-Dimensional Neural Network
p.157

Analysis on Fatigue Damage of Metal Rubber Vibration Isolator
p.162

Computation and Analysis of Frost Formation on Ground Aircraft
p.166

Analysis of Water Jet Trajectory of Auto-Targeting Fire Sprinkler System in Interior Large Space
p.171

Aero-Engine Condition Monitoring Based on Kalman Filter Theory
p.176

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 490-495A New Image Segmentation Method Based on...

A New Image Segmentation Method Based on Three-Dimensional Neural Network

Abstract:

In this paper, a three-dimensional probabilistic approach for MR brain image segmentation is proposed. Based on the noise-free representative reference vectors provided by SOM, the results of the 3D-PNN method are superior to other traditional algorithms. In addition to the 3D-PNN architecture, a fast three-step training method is proposed. The proposed approach also incorporates structure tensor to find appropriate feature sets for the 3D-PNN with respect to resulting classification accuracy. Computational results with simulated MR brain images have shown the promising performance of the proposed method.

You might also be interested in these eBooks

Mechatronics and Intelligent Materials II

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 490-495)

Pages:

157-161

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.490-495.157

Citation:

Cite this paper

Online since:

March 2012

Authors:

Guo Fu Lin

Keywords:

Image Segmentation, Structure Tensor, Three-Dimensional Neural Network

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] LI M, CAI W, TAN W. A region-based multi-sensor image fusion scheme using pulse-coupled neural network[J]. Pattern Recognition Letters, 2006, 27: 1948-(1956).

DOI: 10.1016/j.patrec.2006.05.004

Google Scholar

[2] PHAM D L, XU C Y, PRINCE J L. A survey of current methods in medical image segmentation, annual review of biomedical engineering[J]. Annu. Rev., 2009(2): 315–337.

DOI: 10.1146/annurev.bioeng.2.1.315

Google Scholar

[3] REDDICK W E, GLASS JOHN O, COOK E N, et al. Automated segmentation and classification of multispectral magnetic resonance images of brain using artificial neural networka[J]. IEEE Transaction On Medical Image, 1997, 16(6): 911-918.

DOI: 10.1109/42.650887

Google Scholar

[4] TIAN D, FAN L. A brain MR images segmentation method based on SOM neural network[J]. In the 1st International Conference on Bioinformatics and Biomedical Engineering, 2010: 686–689.

DOI: 10.1109/icbbe.2007.179

Google Scholar

[5] SONG T, JAMSHIDI M M, LEE R R, et al. A modified probabilistic neural network for partial volume segmentation in brain MR image[J]. IEEE Transactions On Neural Networks, 2009, 18(5): 1424-1432.

DOI: 10.1109/tnn.2007.891635

Google Scholar