Abstract
Hyperspectral images have shown promising performance in many applications, especially extracting information from remotely sensed geometric images. One obvious advantage is its good ability to reflect the physical meaning from a point view of spectrum, since even two very similar materials would present an obvious difference by a hyperspectral imaging system. Recent work has made great progress on the hyperspectral fluorescence imaging techniques, which makes the elaborate spectral observation of cancer areas possible. Cancer cells would be distinguishable with normal ones when the living body is injected with fluorescence, which helps organs inside the living body emit lights, and then the signals can be obtained by the passive imaging sensor. This paper discusses the ability to screen the cancers by means of hyperspectral bioluminescence images. A rotational independent component analysis method is proposed to solve the problem. Experiments evaluate the superior performance of the proposed ICA-based method to other blind source separation methods: 1) The ICA-based methods do perform well in detect the cancer areas inside the living body; 2) The proposed method presents more accurate cancer areas than other state-of-the-art algorithms.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Wang, X., Rosol, M., Ge, S., et al.: Dynamic tracking of human hematopoietic stem cell engraftment using in vivo bioluminescence imaging. Blood 102, 3478–3482 (2003)
Levenson, R.M., Lynch, D.T., Kobayashi, H., et al.: Multiplexing with Multispectral Imaging: From Mice to Microscopy. ILAR Journal 49(1), 78–88 (2008)
Zhang, Y., Han, Y., Zhao, C.L., et al.: Current developments in animal in vivo optical imaging technologies with bioluminescence and fluorescence. Chinese Bull. Life Sci. 18(1), 25–30 (2006)
Mansfield, J.R., Hoyt, C., Levenson, R.M.: Visualization of Microscopy-Based Spectral Imaging Data from Multi-Label Tissue Sections. Current Protocols in Molecular Biology 14(19), 1–14 (2008)
Ntziachristos, V., Ripoll, J., Wang, L.V., et al.: Looking and listening to light the evolution of whole - body photonic imaging. Nat. Biotechnol. 23(3), 313–320 (2005)
Harris, S., Wallace, R.: Acousto-optic tunable filter. Journal of the Optical Society of America 59, 744–747 (1969)
Gebhart, S.C., Thompson, R.C., Mahadevan-Jansen, A.: Liquid-crystal tunable filter spectral imaging for brain tumor demarcation. Applied Optics 46, 1896–1910 (2007)
Cai, W., Chen, X.: Preparation of peptide-conjugated quantum dots for tumor vasculature-targeted imaging. Nature Protocols 3, 89–96 (2008)
Plaza, A., Martinez, P., Perez, R., Plaza, J.: Spatial/spectral endmember extraction by multidimensional morphological operations. IEEE Trans. Geosci. Remote Sens. 40(9), 2025–2041 (2002)
Bioucas-Dias, J.M.: A variable splitting augmented Lagrangian approach to linear spectral unmixing. In: First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2009, pp. 1–4 (2009)
Hyvarinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. Wiley, New York (2001)
Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorization. Adv. Neural Inf. Process. Syst. 13, 556–562 (2000)
Donoho, D., Stodden, V.: When Does Non-Negative Matrix Factorization Give a Correct Decomposition Into Parts (2003)
Zhou, G.X., Xie, S.L., Ding, S.X., Yang, J.M., Zhang, J.: Blind Spectral Unmixing Based on Sparse Nonnegative Matrix Factorization. IEEE Trans. Image Process. 20, 1112–1125 (2011)
Huck, A., Guillaume, M., Blanc-Talon, J.: Minimum Dispersion Constrained Nonnegative Matrix Factorization to Unmix Hyperspectral Data. IEEE Trans. Geosci. Remote Sens. 48, 2590–2602 (2010)
Miao, L., Qi, H.: Endmember extraction from highly mixed data using minimum volume constrained nonnegative matrix factorization. IEEE Trans. Geosci. Remote Sens. 45(3), 765–777 (2007)
Jia, S., Qian, Y.T.: Constrained Nonnegative Matrix Factorization for Hyperspectral Unmixing. IEEE Trans. Geosci. Remote Sens. 47, 161–173 (2009)
Liu, X.S., Xia, W., Wang, B., Zhang, L.M.: An Approach Based on Constrained Nonnegative Matrix Factorization to Unmix Hyperspectral Data. IEEE Trans. Geosci. Remote Sens. 49, 757–772 (2011)
Bayliss, J., Gualtieri, J.A., Cromp, R.F.: Analyzing hyperspectral data with independent component analysis. In: Proc. SPIE, vol. 3240, pp. 133–143 (1997)
Chen, C., Zhang, X.: Independent component analysis for remote sensing study. In: Proc. SPIE, vol. 3871, pp. 150–158 (1999)
Moussaoui, S., Hauksdottir, H., Schmidt, F., Jutten, C., Chanussot, J., Brie, D., Doute, S., Benediktsson, J.A.: On the decomposition of Mars hyperspectral data by ICA and Bayesian positive source separation. Neurocomputing 71(10-12), 2194–2208 (2008)
Nascimento, J., Bioucas-Dias, J.: Hyperspectral unmixing algorithm via dependent component analysis. In: Proc. IEEE IGARSS, pp. 4033–4036 (July 2007)
Xia, W., Liu, X., Wang, B., Zhang, L.: Independent Component Analysis for Blind Unmixing of Hyperspectral Imagery with Additional Constraints. IEEE Transactions on Geoscience and Remote Sensing 49(6), 2165–2179 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Du, B., Wang, N., Zhang, L., Tao, D. (2013). Hyperspectral Medical Images Unmixing for Cancer Screening Based on Rotational Independent Component Analysis. In: Sun, C., Fang, F., Zhou, ZH., Yang, W., Liu, ZY. (eds) Intelligence Science and Big Data Engineering. IScIDE 2013. Lecture Notes in Computer Science, vol 8261. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-42057-3_43
Download citation
DOI: https://doi.org/10.1007/978-3-642-42057-3_43
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-42056-6
Online ISBN: 978-3-642-42057-3
eBook Packages: Computer ScienceComputer Science (R0)