獨立成分分析方法(Independent Component Analysis, ICA)原來是訊號處理
領域中，作為來分離盲信號(Blind Source Separation, BSS)的方法。然而最近亦應
用於核磁共振顯影像的分類上。在這篇論文中，我們應用獨立成分分析方法於多
頻譜的腦部及胸部核磁共振顯影像，作為腦部及胸部的組織分類。透過獨立成分
分析，各類的組織應從原來的頻譜影像中，被分類於各張成分影像。不過頻譜影
像的不足，可能造成多種組織混合於一張成分影像。
因此我們發展出一套藉由相關性的預測方法，得知頻譜影像的不足數目，
以幾可能混合在一起的組織。並且經由相關性來來進行維度擴張，以取得額外的
頻譜影像。經過獨立成分分析產生成分影像後，我們再應用等位階函數(Level Set)
方法來圈選最重要的區域。

Independent Component Analysis (ICA) is a Blind Source Separation (BSS)
method in signal processing field. And it is also applied in Magnetic Resonance Images
for classification. In this paper, we introduce ICA to multispectral brain MR images for
brain tissue classification. Through ICA, each brain tissue is supposed to be classified
into each component image from original band images. But deficiency of band images
would lead that more than one tissue are mixed in one component image.
We develop a prediction method by correlation to reveal how many band images
are deficient and which different tissues may be separated into one same component
image. Then extra band images are generated by Band Expansion Process (BEP) with
the nonlinear function we proposed. Then through ICA, the component images are
generated. At last, we introduce the level set method to indicate the most significant
section.

[1] T. Nakai, S.Muraki, E.Bagarinao, Y.Miki, Y Takehara, K. Matsuo, C.Kato,
H.Sakahara, H.Isoda. Application of independent component analysis to magnetic
resonance imaging for enhancing the contrast of gray and white matter. NeuroImage,
21: 251-260, 2004.
[2] Yen-Chieh Ouyang, Member, IEEE, Hsian-Min Chen, Jyh-Wen Chai, Clayton Chi-
Chang Chen*, Sek-Kwong Poon, Ching-Wen Yang, San-Kan Lee, and Chein-I Chang,
Senior Member, IEEE. Band Expansion-Based Over-Complete Independent Component
Analysis for Multispectral Processingof Magnetic Resonance Images. IEEE
Transactions on Biomedical Engineering, Vol. 55, No. 6, June 2008.
[3] H.Ren and C.-I Chang. A generalized orthogonal subspace projection approach to
unsupervised multispectral image classification.IEEE Trans. on Geoscience and Remote
Sensing, 38(6): 2515-2528, 2000.
[4] Lúcio F.A. Campos, Aristófanes C. Silva and Allan Kardec Barros, ”Diagnosis of
Brain Cancer in Digital Mammograms Using Independent Component Analysis and
Neural Networks,” Lecture Notes in Computer Science, Volume 3773, 2005.
[5] Aapo Hyvärinen and Erkki Oja. A Fast Fixed-Point Algorithm for Independent
component Analysis. Neural Computation, 9:1483-1492, 1997.
[6] Aapo Hyvärinen. Fast and Robust Fixed-Point Algorithms for Independent
Component Analysis. IEEE Transactions on Neural Networks, Vol. 10, No. 3, May
1999.
45
[7] Aapo Hyvärinen and Erkki Oja. Independent Component Analysis: Algorithms and
Applications. Neural Networks, 13(4-5):411-430, 2000.
[8] Aapo Hyvärinen. Gaussian Moments for Noisy Independent Component Analysis.
hrrp://www.cis.hut.fi/~aapo/, February 19,1999.
[9] Yen-Chieh Ouyang, Hsian-Min Chen, Jyh-Wen Chai, Cheng-Chieh Chen, Clayton
Chi-Chang Chen, Sek-Kwong Poon, Ching-Wen Yang, and San-Kan Lee. Independent
Component Analysis for Magnetic Resonance Image Analysis. EURASIP Journal on
Advances in Signal Processing, Vol. 2008, Article ID 780656, 14 pages.
[10] Tony F. Chan , Member, IEEE, and Luminita A. Vese. Active Contours Without
Edges. IEEE Trans. on Image Processing, Vol. 10, No.. 2, February 2001.
[11] Marian Stewart Bartlett, Member, IEEE, Javier R. Movellan, Member, IEEE, and
Terrence J. Sejnowski, Fellow, IEEE. Face Recognition by Independent Component
Analysis. IEEE Transactions on Neural Networks, Vol. 13, No. 6, November 2002.
[12] J. Karhunen, A. Hyvärinen, R. Vigario, J. Hurri, and E. Oja. Applications of neural
blind separation to signal and image processing. In Proc. IEEE Int. Conf. on Acoustics,
Speech and Signal Processing (ICASSP'97), pages 131-134, Munich, Germany, 1997
[13] G.A. Wright. Magnetic resonance imaging. Signal Process, Mag, pp.56-66,
January 1997.
[14] L. Clarke, R. Vethuizen, M.Camacho, J. Heine, M. Vaidyanathan, L.O. Hall, R.W.
Thatcher and M.K. Silbiger. MRI segmentation: methods and applications. Magnetic
Resonance Imageing, 13(3): 343-368, 1995.
[15] H.Soltanian-Zadeh, J.P. Windham, and A.E. Yagle. A comparative analysis of
several transformations for enhancement and segmentation of magnetic resonance
image scene sequences. IEEE Trans. Medical Imaging, 11(3): 302-316, 1992.
46
[16] H. Sotantian-Zadeh, R.Saigal, A.M. Haggar, J.P. Windham, A.E. Yagle and D.C.
Hearshen. Optimization of MRI protocol and pulse sequence parameters for eigenimage
filtering. IEEE Trans. Medical Imaging, 13(1): 161-175, 1994.
[17] H. Soltanian-Zadeh, J.P. Windham and D.J. Peck. Optimal linear transformation
for MRI feature extraction. ,IEEE Transaction on Medical Imaging, 15(6): 749-767,
1996.
[18] M.W. Vannier, R. Butterfield, D. Jordan, W.A. Murphy, R.G. Levitt and M. Gado.
Multispectral analysis of magnetic resonance images. Radiology, 154: 221-224 1985.
[19] M.W. Vannier, T.K. Pilgram, C.M. Speidel, L.R. Nermann, D.L. Rickman and L.D.
Schertz. Validation of magnetic resonance imaging (MRI) multispectral tissue
classification. Computer Medical Imaging and Graphics, 15: 217-223, 1991.
[20] T.taxt and A. Lundervold. Multispectral analysis of the brain using magnetic
resonance imaging. IEEE Trans. Medical Imaging, 13(3): 470-481,1994.
[21] H.S. Choi, D.R. Haynor and Y.Kim. Partial volume tissue classification of
multichannel magnetic resonance images-a mixed model. IEEE Trans. Medical Imaging,
10(3): 385-407, 1991.
[22] Aapo Hyvärinen, J. Karhunen and Erkki Oja. Independent Component Analysis.
John Wiley & Sons, 2001.
[23] Y.H. Kao, W.Y. Guo, Y.T. Wu, K.C.Liu, W.Y. Chai, C.Y. Lin, Y.H. Hwang,
A.J.K. Liou, H.M. Wu, H.C. Cheng, T.C. Yeh, J.C. Hsieh, and M.M. h. Teng.
Hemodynamic Segmentiation of MR Brain Perfusion Images Using Independent
Component Analsis, Thresholding, and Bayesian Estimation. Magnetic Resonance in
Medicine, 49: 885-894, 2003.
47
[24] M.J. McKeown, S. Makeig, G.G. Brown, T.P. Jung, S.S. Kindermann, A.J. Bell,
T.J. Segnowski. Analysis of fMRI data by blind separation into independent spatial
component. Hum. Brain Mapp., 6:160-188, 1998.
[25] V.D. Calhoun, T. Adali, G.D. Pearlson, P.C.M. van Zijl, and J.J. Pekar.
Independent Component Analysis of Fmri Data in the Complex Domain. Magnetic
Resonance in Medicine, 48: 180-192, 2002.
[26] A.J. Bell and T.KJ. Sejnowski. An information-maximization approach to blind
separation and blind deconvolution. Neural Computation, 7: 1129-1159, 1995.
[27] P.Comon. Independent component analysis-a new concept? Signal Prcissing, 36:
287-314,1994.
[28] S.Amari, A. Cichocki, and H.Yang. A new learning algorithm for blind source
separation. In Advances in Neural Information Processing 8 (Proc. NIPS’95).
Cambridge, MA:MIT Press, 1996.
[29] N.Delfosse, and P. Loubaton. Adaptive blind separation of independent sources: A
deflation approach. Signal Processing, 45: 59-83, 1995.
[30] C.Jutten, and J.Herault. Blind separation of sources, part I: An adaptive algorithm
based on neuromimetic architecture. Signal Prcessing, 24, 1-10,1991.
[31] S.Theodoridis and K. Koutroumbas. Pattern Recognition. Academic Press, 1999.
[32] R. Valdes-Cristerna, V. Medina Banuelos, O. Yanez-Suarez. Coupling of radial
basis networks and active contour model for Multispectral brain MR images. IEEE
Trans. Biomedical Eng., 51(3): 459-470,2004.