Wavelet Based Variational Level Set Approach to Segmentation and Bias Correction for Medical Images

Abstract:

This paper presents a wavelet energy map based on an active contour model for medical image segmentation and bias correction in a variational level set framework. In our model the wavelet transform amplifies the faint dissimilarities between regions, and we model the distribution of intensity belonging to each tissue as a Gaussian distribution with spatially varying mean and variance. In addition, we modify the intensity mean as the product of the bias field and true image. Tissue segmentation and bias correction are simultaneously achieved via a level set evolution process. Experiments on images of various modalities demonstrated the superior performance of the proposed approach.

• Periodical: Applied Mechanics and Materials (Volumes 568-570)
• Pages: 710-715
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.568-570.710
• Online since: June 2014
• Authors: Jian Jun Yuan*, Jian Jun Wang
• Keywords: Bias Correction, Level Set, Local Gaussian Fitting, Wavelet Transformation

References

[1] Li, C., Kao, C., Gore, J., et al.: Implicit active contours driven by local binary fitting energy, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition(CVPR). IEEE Computer Society, Washington, DC, USA, 1-7 (2007).

DOI: 10.1109/cvpr.2007.383014

[2] Li, C., Kao, C., Gore, J., et al.: Minimization of region-scalable fitting energy for image segmentation. IEEE Transactions on Image Processing 17(2008), 1940-(1949).

DOI: 10.1109/tip.2008.2002304

[3] S. G, Mallat: A theory for multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence 11(7), 1989, 674-693.

DOI: 10.1109/34.192463

[4] Wang, L., He, L., Mishra, A.,: Active contours driven by local Gaussian distribution fitting energy, Signal Processing 89 (2009), 2435-2447.

DOI: 10.1016/j.sigpro.2009.03.014