SIMULATION STUDY OF TISSUE TYPE DIFFERENTIATION USING NON-NEGATIVE MATRIX FACTORIZATION

Yuqian Li, Diana M. Sima, Sofie Van Cauter, Uwe Himmelreich, Yiming Pi, Sabine Van Huffel

2012

Abstract

Finding the brain tumor tissue-specific magnetic resonance spectra and their corresponding spatial distribution is a typical Blind Source Separation (BSS) problem. Non-negative Matrix Factorization (NMF), which only requires non-negativity constraints, has become popular because of its advantages compared to other BSS methods. A variety of algorithms based on traditional NMF have been recently proposed. This study focuses on the performance comparison of several NMF implementations, including some newly released methods, in brain glioma tissue differentiation using simulated magnetic resonance spectroscopic imaging (MRSI) signals. Experimental results demonstrate the possibility of finding typical tissue types and their distributions using NMF algorithms. The (accelerated) hierarchical alternating least squares algorithm was found to be the most accurate.

References

  1. Berry M, Browne M, Langville A, Pauca V, and Plemmons R, 2007. Algorithms and applications for approximate non-negative matrix factorization. Comput Stat Data Anal,52:155-173.
  2. Brown T, Kincaid B, Ugurbil K, 1982. NMR chemical shift imaging in three dimensions. PNAS, 79(11): 3523-3526.
  3. Cichocki A, Zdunek R, Amari S, 2007. Hierarchical ALS algorithms for nonnegative matrix and 3D tensor factorization. Lect Notes Comput Sci, 4666:169-176.
  4. Cichocki A, Phan AH, 2009. Fast local algorithms for large scale Nonegative Matrix and Tensor Factorizations. IEICE Trans Fund Electron Comm Comput Sci, 3:708-721.
  5. Croitor Sava AR, Sima DM, Martinez-Bisbal MC, Celda B, Van Huffel S, 2010. Non-negative Blind Source Separation Techniques for Tumor Tissue Typing Using HR-MAS signals. In Proceedings of the 32nd Annual International Conference of the IEEE EMBS, Buenos Aires, Argentina.
  6. Gillis N, 2011. Nonnegative matrix factorization complexity, algorithms and applications. PhD Thesis, Louvan-La-Neuve, Belgium.
  7. Gonzalez EF, Zhang Y, 2005. Accelerating the Lee-Seung algorithm for non-negative matrix factorization. Tech Report, Rice University.
  8. Grippo L, Sciandrone M, 2000. On the convergence of the block nonlinear Gauss-Seidel method under convex constraints. Oper Res Letter, 26:127-136.
  9. Howe FA, Barton SJ, Cudlip SA, Stubbs M, Saunders DE, Murphy JR, Opstad KS, Doyle VL, McLean MA, Bell BA, Griffiths JR, 2003. Metabolic profiles of human brain tumours using quantitative in vivo 1H magnetic resonance spectroscopy. Magn Res Med,49:223-232.
  10. Jolliffe IT. Principal Component Analysis. Second edition, New York: Springer-Verlag 2002. 487 p.
  11. Kim D, Sra S., Dhillon IS, 2007. Fast Newton-type Methods for the Least Squares Nonnegative Batrix Approximation Problem. In Proceedings of the 2007 SIAM International Conference on Data Mining (ICDM), Pisa, Italy.
  12. Ladroue C, Howe FA, Griffiths JR, Tate AR, 2003. Independent component analysis for automated decomposition of in vivo magnetic resonance spectra. Magn Reson Med, 50:697-703.
  13. Lee DD, Seung HS, 1999. Learning the parts of objects by non-negative matrix factorization. Nature, 401:788- 791.
  14. Lee DD, Seung HS, 2001. Algorithms for Non-negative Matrix Factorization, Advances in Neural Information Processing Systems, 13:556-562.
  15. Lin CJ, 2007. Projected Gradient Methods for Nonnegative Matix Factorization, Neural Comput, 19:2756-2779.
  16. Poullet JB, Sima DM, Simonetti AW, De Neuter B, Vanhamme L, Lemmerling P, Van Huffel S, 2006. An automated quantitation of short echo time MRS spectra in an open source software environment: AQSES. NMR Biomed, 20: 493-504.
  17. Stoyanova R, Brown TR, 2001. NMR spectral quantitation by principal component analysis. NMR Biomed, 14:260-264.
  18. Su Y, Thakur SB., Karimi S, Du S, Sajda P, Huang W, Parra LC, 2008. Spectrum separation resolves partialvolume effect of MRSI as demonstrated on brain tumor scans. NMR Biomed, 21:1030-1042.
  19. Szabo de Edelenyi F, Simonetti AW, Postma G, Huo R, Buydens LMC, 2005. Application of independent component analysis to 1H MR spectroscopic imaging exams of brain tumours. Anal. Chim. Acta, 544:36-46.
Download


Paper Citation


in Harvard Style

Li Y., Sima D., Van Cauter S., Himmelreich U., Pi Y. and Van Huffel S. (2012). SIMULATION STUDY OF TISSUE TYPE DIFFERENTIATION USING NON-NEGATIVE MATRIX FACTORIZATION . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2012) ISBN 978-989-8425-89-8, pages 212-217. DOI: 10.5220/0003734702120217


in Bibtex Style

@conference{biosignals12,
author={Yuqian Li and Diana M. Sima and Sofie Van Cauter and Uwe Himmelreich and Yiming Pi and Sabine Van Huffel},
title={SIMULATION STUDY OF TISSUE TYPE DIFFERENTIATION USING NON-NEGATIVE MATRIX FACTORIZATION},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2012)},
year={2012},
pages={212-217},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003734702120217},
isbn={978-989-8425-89-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2012)
TI - SIMULATION STUDY OF TISSUE TYPE DIFFERENTIATION USING NON-NEGATIVE MATRIX FACTORIZATION
SN - 978-989-8425-89-8
AU - Li Y.
AU - Sima D.
AU - Van Cauter S.
AU - Himmelreich U.
AU - Pi Y.
AU - Van Huffel S.
PY - 2012
SP - 212
EP - 217
DO - 10.5220/0003734702120217