No Access

HYBRID APPROACH FOR BRAIN TUMOR SEGMENTATION IN MAGNETIC RESONANCE IMAGES USING CELLULAR NEURAL NETWORKS AND OPTIMIZATION TECHNIQUES

D. SELVATHI

Department of ECE Mepco Schlenk Engineering College, Sivakasi, Tamil Nadu, India

Search for more papers by this author

HENRY SELVARAJ

Department of Electrical and Computer Engineering, University of Nevada, Las Vegas, USA

Search for more papers by this author

, and

S. THAMARAI SELVI

Professor & Head, Department of IT, Anna University, MIT Campus, Chennai, Tamil Nadu, India

Search for more papers by this author

https://doi.org/10.1142/S1469026810002781Cited by:2 (Source: Crossref)

Abstract

Tumor segmentation from brain magnetic resonance image data is an important but time consuming task performed manually by medical experts. Automating this process is challenging due to the high diversity in appearance of tumor tissue among different patients and in many cases, similarity between tumor and normal tissue. This paper deals with an efficient segmentation algorithm for extracting brain tumors in magnetic resonance images using Cellular Neural Networks (CNN). Learning CNN templates values are formulated as an optimization problem. The template coefficients (weights) of an CNN which will give a desired performance, can be derived by learning genetic algorithm and simulated annealing optimization techniques. The objective of this work is to compare the performance of genetic algorithm (GA) and simulated annealing (SA) for finding the optimum template values in the CNN which is used for segmenting the tumor region in the abnormal MR images. The method is applied on real data of MRI images of thirty patients with four different types of tumors. The results are compared with radiologist labeled ground truth. Quantitative analysis between ground truth and segmented tumor is presented in terms of segmentation efficiency. From the analysis and performance measures like segmentation accuracy, it is inferred that the brain tumor segmentation is best done using CNN with genetic algorithm template optimization than CNN with simulated annealing template optimization. An average accuracy rate of above 95% was obtained using this segmentation algorithm.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

M. A. G. Ballester, A. Zisserman and M. Brady, Med. Image Anal. 4, 189 (2000). Crossref, Google Scholar
M. R. Patel and V. Tse, Seminars in Roentgenology 39, 347 (2004), DOI: 10.1016/j.ro.2004.05.005. Crossref, Google Scholar
M. Schmidt, Automatic brain tumor segmentation, Master Thesis, University of Alberta, Canada (2005) . Google Scholar
W. M. Wellset al., IEEE Trans. Med. Image 15, 429 (1996), DOI: 10.1109/42.511747. Crossref, Google Scholar
J. C. Bezdek, L. O. Hall and L. P. Clark, Med. Phys. 20, 1033 (1993), DOI: 10.1118/1.597000. Crossref, Google Scholar
R. V. Cristerna and V. M. Banuelos, IEEE Trans. Biomed. Eng. 51, 45 (2004). Google Scholar
C. R. Muller, H. Benoit and Y. Carillon, IEEE Trans. Nucl. Sci. 49, 65 (2002). Google Scholar
H. H. Chang, D. J. Valentino and G. R. Duckwiler, IEEE Trans. Biomed. Eng. 54, 243 (2007). Google Scholar
R. Xu and D. Wunsch II., IEEE Trans. Neural Network. 16, 645 (2005), DOI: 10.1109/TNN.2005.845141. Crossref, Google Scholar
A. W.-C. Liew and H. Yan, Curr. Med. Imag. Rev. 2, 1 (2006). Google Scholar
D. L. Pham, C. Xu and J. L. Prince, A survey of current methods in medical image segmentation, Technical Report No. JHU/ECE 99-01, The Johns Hopkins University, Baltimore (1998) . Google Scholar
N. R. Pal and S. K. Pal, Pattern Recogn. 26, 1277 (1993), DOI: 10.1016/0031-3203(93)90135-J. Crossref, Google Scholar
L. M. Fletcher-Heathet al., Artif. Intell. Med. 21, 43 (2001). Crossref, Google Scholar
M. C. Clarket al., IEEE Trans. Med. Imag. 17, 187 (1998), DOI: 10.1109/42.700731. Crossref, Google Scholar
J. C. Bezdek, L. O. Hall and L. P. Clarke, Med. Phys. 20, 1033 (1993), DOI: 10.1118/1.597000. Crossref, Google Scholar
L. P. Clarkeet al., Magn. Reson. Imag. 13, 343 (1995), DOI: 10.1016/0730-725X(94)00124-L. Crossref, Google Scholar
G. P. Mazzaraet al., Int. J. Radiat. Oncol. Biol. Phys. 59, 300 (2004). Crossref, Google Scholar
D. T. Gering, W. E. L. Grimson and R. Kikinis, Medical Image Computing and Computer-Assisted Intervention MICCAI (2002) pp. 388–395. Google Scholar
M. B. Cuadraet al., Medical Image Computing and Computer-Assisted Intervention MICCAI (2002) pp. 380–387. Google Scholar
M. Prastawaet al., Acad. Radiol. 10, 1341 (2003), DOI: 10.1016/S1076-6332(03)00506-3. Crossref, Google Scholar
S. Dickson, B. T. Thomas and P. Goddard, Int. J. Neural Syst. 8, 91 (1997), DOI: 10.1142/S0129065797000124. Link, Google Scholar
L. O. Chua and L. Yang, IEEE Trans. Circuit Syst. 35, 1273 (1988), DOI: 10.1109/31.7601. Crossref, Google Scholar
L. O. Chua and K. R. Crounse, IEEE Trans. Circuit Syst. 42, 583 (1998). Google Scholar
B. Cigale and D. Zazula, Int. J. Pattern Recogn. Artif. Intell. 18, 563 (2004), DOI: 10.1142/S0218001404003368. Link, Google Scholar
L. O. Chua and L. Yang, IEEE Trans. Circuit Syst. 35, 1257 (1988), DOI: 10.1109/31.7600. Crossref, Google Scholar
C.-H. Haung, W.-K. Leow and D. Racoceanu, A cellular neural network as a principal component analyzer, Proc. Int. Joint Conf. Neural Networks (2009) pp. 1163–1170. Google Scholar
L. Ingber, Math. Comput. Model. 18, 29 (1993), DOI: 10.1016/0895-7177(93)90204-C. Crossref, Google Scholar
L. Ingber and B. Rosen, Math. Comput. Model. 16, 87 (1992), DOI: 10.1016/0895-7177(92)90108-W. Crossref, Google Scholar
S. Krikpatrick, C. D. Gelatt and M. P. Vecchi, Optimization by simulated annealing, Science New Series, Vol. 220, (1983), pp. 671–680 . Google Scholar
J. Korst and E. Aarts , Simulated Annealing and Boltzmann Machines ( John Wiley and Sons , Chichester , 1990 ) . Google Scholar
J. Tohkaet al., IEEE Trans. Med. Imag. 26, 696 (2007), DOI: 10.1109/TMI.2007.895453. Crossref, Google Scholar
T. Kozek, T. Rosca and L. O. Chua, IEEE Trans. Circuit Syst. 40, 392 (1993). Crossref, Google Scholar
B. Chandler, C. Rekeczky and Y. Nishio, IEICE Trans. Fund. 82, 321 (1999). Google Scholar
http:\\www.howstuffworks.com\mri.htm . Google Scholar
B. Cigale and D. Zazula, Application of simulated annealing to biosignal classification and segmentation, IEEE Symp. Computer-based Medical Systems (2002) pp. 165–170. Google Scholar
R. A. Rutenbar, IEEE Trans. Circuit. Dev. 19 (1989), DOI: 10.1109/101.17235. Google Scholar
K. Sekihara, H. Haneishi and N. Ohyama, Digital Image Synthesis Optimization 1351, 410 (1990). Crossref, Google Scholar