Open Access Open Access  Restricted Access Subscription or Fee Access

Interaction among Brain Regions Using Feature Selection for Interaction-Based Clustering

B. Padmajaa, P. Asha, R. Karthikeyan

Abstract


Functional Magnetic Resonance Imaging (fMRI) is a technique for measuring brain activity that directly measures the blood flow in the brain. This is an important concept in medical field to detect the tumors. Tumors is an abnormal tissue which is grouped together to form into lumps. Tumor cells are grouped according to their growth of cells which has been graded by World Health Organisation.  To detect the tumor we take an fMRI using various techniques. K means algorithm is introduced in this field to cluster together the different regions of the brain according to the interaction between various regions. These results are compared to original image to get the exact location of the brain tumor rather than the region surrounding the tumor cells.


Keywords


Tumor, BOLD, Interaction K Means, Feature Selection.

Full Text:

PDF

References


Chuanjun Li, Latifur Khan (2007) , and Balakrishnan, Feature Selection for Classi_cation of Variable length Multi-attribute Motions

Elia Formisano and Rainer Goebel (2003), Tracking cognitive processes with functional MRI mental chronometry

Michael D. Fox and Marcus E. Raichle (2007), Spontaneous fluctuations in brain activity observed with functional magnetic resonance imaging.

S. Smith, P. Fox, K. Miller, D. Glahn, P. Fox, C. Mackay, N. Filippini, K. Watkins, R. Toro, A. Laird et al., “Correspondence of the brain’s functional architecture during activation and rest,” PNAS, vol. 106, p. 13040, 2009.

C. Li, L. Khan, and B. Prabhakaran, “Feature selection for classification of variable length multiattribute motions,” in Multimedia Data Mining and Knowledge Discovery, V. A. Petrushin and L. Khan, Eds. Springer, 2007.

C. Pamminger, Bayesian Clustering of Categorical Time Series, 2008.

T. W. Liao, “Clustering of time series data - a survey,” Pattern Recognition, vol. 38, no. 11, pp. 1857–1874, 2005.

E. Keogh and S. Kasetty, “On the need for time series data mining benchmarks: a survey and empirical demonstration,” 2002, pp. 102–111.

J. Lin, M. Vlachos, E. Keogh, and D. Gunopulos, “Iterative incremental clustering of time series,” in In EDBT, 2004, pp. 106–122.

M. Vlachos, J. Lin, E. Keogh, and D. Gunopulos, “A waveletbased anytime algorithm for k-means clustering of time series,” in In Proc. Workshop on Clustering High


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.