Blind Separation of Multichannel Biomedical Image Patterns by Non-negative Least-Correlated Component Analysis
Cellular and molecular imaging promises powerful tools for the visualization and elucidation of important disease-causing biological processes. Recent research aims to simultaneously assess the spatial-spectral/temporal distributions of multiple biomarkers, where the signals often represent a composite of more than one distinct source independent of spatial resolution. We report here a blind source separation method for quantitative dissection of mixed yet correlated biomarker patterns. The computational solution is based on a latent variable model, whose parameters are estimated using the non-negative least-correlated component analysis (nLCA) proposed in this paper. We demonstrate the efficacy of the nLCA with real bio-imaging data. With accurate and robust performance, it has powerful features which are of considerable widespread applicability.
KeywordsIndependent Component Analysis Blind Source Separation Latent Variable Model Blind Separation Blind Source Separation Algorithm
- 3.Armato, S.G.: Enhanced visualization and quantification of lung cancers and other diseases of the chest. Experimental Lung Res. 30, 72–77 (2004)Google Scholar
- 4.Wang, Y., Zhang, J., Huang, K., Khan, J., Szabo, Z.: Independent component imaging of disease signatures. In: Proc. IEEE Intl. Symp. Biomed. Imaging, Washington DC, July 7-10, pp. 457–460 (2002)Google Scholar
- 5.Wang, Y., Srikanchana, R., Choyke, P., Xuan, J., Szabo, Z.: Computed simultaneous imaging of multiple functional biomarkers. In: Proc. IEEE Intl. Symp. Biomed. Imaging, Arlington, VA, April 15-18, pp. 225–228 (2004)Google Scholar
- 7.Wang, Y., Xuan, J., Srikanchana, R., Choyke, P.L.: Modeling and reconstruction of mixed functional and molecular patterns. Intl. J. Biomed. Imaging (in press, 2005)Google Scholar