Discrete Wavelet Transform-Based Whole-Spectral and Subspectral Analysis for Improved Brain Tumor Clustering Using Single Voxel MR Spectroscopy

IEEE Transactions on Biomedical Engineering

Volumn 62, Issue 12, 2015, Pages 2860-2866

  Yang, Guang ^a,b   Nawaz, Tahir ^c,d   Barrick, Thomas R ^a   Howe, Franklyn A ^a   Slabaugh, Greg ^c  

^a ST GEORGE S HOSPITAL   (United Kingdom)

^b NATIONAL HEART AND LUNG INSTITUTE   (United Kingdom)

^c CITY UNIVERSITY   (United Kingdom)

^d UNIVERSITY OF READING   (United Kingdom)

Author keywords

Brain tumor; clustering; dimension reduction; discrete wavelet transform; glioma grade; magnetic resonance spectroscopy; unsupervised learning

Indexed keywords

BRAIN; CLUSTERING ALGORITHMS; DISCRETE WAVELET TRANSFORMS; GRADING; MAGNETIC RESONANCE; MAGNETIC RESONANCE SPECTROSCOPY; PATTERN RECOGNITION; REDUCTION; SPECTRUM ANALYSIS; TUMORS; UNSUPERVISED LEARNING;

BRAIN TUMORS; CLUSTERING; CLUSTERING ACCURACY; DIMENSION REDUCTION; DIMENSIONALITY REDUCTION; IMPROVED TECHNIQUES; MAGNETIC RESONANCE SPECTROSCOPIES (MRS); UNSUPERVISED CLUSTERING;

WAVELET TRANSFORMS;

ARTICLE; ASTROCYTOMA; BRAIN TISSUE; BRAIN TUMOR; CONTROLLED STUDY; DECOMPOSITION; DIAGNOSTIC ACCURACY; DIAGNOSTIC ERROR; DISCRETE WAVELET TRANSFORM; GLIOBLASTOMA; HUMAN; INFORMATION PROCESSING; MAJOR CLINICAL STUDY; NUCLEAR MAGNETIC RESONANCE SCANNER; NUCLEAR MAGNETIC RESONANCE SPECTROSCOPY; OLIGODENDROGLIOMA; SPECTROSCOPY; WAVELET ANALYSIS; NUCLEAR MAGNETIC RESONANCE IMAGING; PATHOLOGY; PROCEDURES; UNSUPERVISED MACHINE LEARNING;

BRAIN NEOPLASMS; HUMANS; MAGNETIC RESONANCE IMAGING; UNSUPERVISED MACHINE LEARNING; WAVELET ANALYSIS;

EID: 84960102491     PISSN: 00189294     EISSN: 15582531     Source Type: Journal    
DOI: 10.1109/TBME.2015.2448232     Document Type: Article

References (27)

1. V. P. Collins, "Brain tumours: Classification and genes," J. Neurol. Neurosurg. Psychiatry, vol. 75, pp. ii2-ii11, Jun. 2004.
2. D. N. Louis et al., "The 2007 WHO classification of tumours of the central nervous system," Acta Neuropathol., vol. 114, no. 2, pp. 97-109, Aug. 2007.
3. J. Faehndrich et al., "Neuroradiological viewpoint on the diagnostics of space-occupying brain lesions," Clin. Neuroradiol., vol. 21, no. 3, pp. 123-39, Sep. 2011.
4. M. Caulo et al., "Data-driven grading of brain gliomas: A multiparametric MR imaging study," Radiology, vol. 272, no. 2, pp. 494-503, 2014.
5. R. de Graaf, In Vivo NMR Spectroscopy. New York, NY, USA: Wiley, 2007.
6. A. Devos et al., "Classification of brain tumours using short echo time 1H MR spectra," J. Magn. Reson., vol. 170, no. 1, pp. 164-175, Sep. 2004.
7. L. T. Mainardi et al., "A wavelet packets decomposition algorithm for quantification of in vivo (1)H-MRS parameters," Med. Eng. Phys., vol. 24, no. 3, pp. 201-208, Apr. 2002.
8. S. Z. Mahmoodabadi et al., "A novelm CAD for pediatric metabolic brain diseases incorporating DW imaging and MR spectroscopy," Expert Syst., vol. 30, no. 1, pp. 21-33, Feb. 2013.
9. P. Tiwari et al., "Multimodal wavelet embedding representation for data combination (MaWERiC): Integrating magnetic resonance imaging and spectroscopy for prostate cancer detection," NMR Biomed., vol. 25, no. 4, pp. 607-19, Apr. 2012.
10. S. Mallat, "A theory formultiresolution signal decomposition: Thewavelet representation," IEEE Trans. Pattern Anal. Mach. Intell., vol. 11, no. 7, pp. 674-693, Jul. 1989.
11. L. Chen et al., "An efficient algorithm for automatic phase correction of NMR spectra based on entropy minimization," J. Magn. Reson., vol. 158, no. 1-2, pp. 164-168, Sep. 2002.
12. G. Yang et al., "Nonlinear Laplacian Eigenmaps dimension reduction of in-vivo magnetic resonance spectroscopic imaging analysis," in Proc. Int. Soc. Magnetic Resonance Med. 21st Annu. Meet., 2013, p. 1967.
13. G. Yang et al., "Classification of brain tumour 1H MR spectra: Extracting features by metabolite quantification or nonlinear manifold learning?," in Proc. Biomed. Imag. 11th Int. Symp., 2014, pp. 1039-1042.
14. G. Yang et al., "Manifold learning in MRspectroscopy using nonlinear dimensionality reduction and unsupervised clustering," Magn. Reson. Med., 2014. DOI: 10.1002/mrm.25447.
15. M. Weeks, Digital Signal Processing Using MATLAB and Wavelets. Boston, MA, USA: Jones & Bartlett, 2010.
16. H. Peng et al., "Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy," IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 8, pp. 1226-1238, Aug. 2005.
17. R. L. Somorjai et al., "Class prediction and discovery using gene microarray and proteomics mass spectroscopy data: Curses, caveats, cautions," Bioinformatics, vol. 19, no. 12, pp. 1484-1491, Aug. 2003.
18. K. S. Opstad et al., "Linear discriminant analysis of brain tumour 1H MR spectra: A comparison of classification using whole spectra versus metabolite quantification," NMR Biomed., vol. 20, no. 8, pp. 763-770, 2007.
19. H. Abdi, "The Bonferonni and Šidák corrections for multiple comparisons," in Encyclopedia of Measurement and Statistics. Newbury Park, CA, USA: Sage, 2007, pp. 103-107.
20. F. A. Howe and K. S. Opstad, "1H MR spectroscopy of brain tumours and masses," NMR Biomed., vol. 16, no. 3, pp. 123-131, May 2003.
21. T. Nawaz et al., "Trajectory clustering for motion pattern extraction in aerial videos," in Proc. IEEE Int. Conf. Image Process., 2014, pp. 1016-1020.
22. W. Press et al., "Section 16.4. Hierarchical clustering by phylogenetic trees," in Numerical Recipes: The Art of Scientific Computing. New York, NY, USA: Cambridge Univ. Press, 2007, pp. 868-881.
23. Y. Chen and C. Lin, "Combining SVMs with various feature selection strategies," in Feature Extraction: Foundations and Applications. Berlin, Germany: Springer, 2006, pp. 315-324.
24. P. J. Rousseeuw, "Silhouettes: A graphical aid to the interpretation and validation of cluster analysis," J. Comput. Appl. Math., vol. 20, pp. 53-65, Nov. 1987.
25. J. García-Gómez et al., "On the use of long TE and short TE SV MR spectroscopy to improve the automatic brain tumor diagnosis," Biomedical Data Mining Research Line, Katholieke Univ. Leuven, Leuven, Belgium, Tech. Rep. 07-55. pp. 1-25, 2007.
26. S. Ortega-Martorell et al., "Non-negative matrix factorisation methods for the spectral decomposition of MRS data from human brain tumours," BMC Bioinformat., vol. 13, no. 1, pp. 1-20, Jan. 2012.
27. F. Raschke et al., "1H 2D MRSI tissue type analysis of gliomas," Magn. Reson. Med., vol. 73, no. 4, pp. 1381-1389, Jun. 2014.