In this proposed method, the segmentation of brain Magnetic Resonance Images (MRI) has been carried out using Pulse Coupled Neural network (PCNN) and classification by Back Propogation Neural Network (BPNN) techniques. The proposed method includes five stages pre-processing, clustering, feature extraction, feature selection and classification. For extracting the features Non Sub-sampled Contourlet Transform (NSCT) method has been used. For feature selection optimized Fire-fly intelligence has been preferred. Finally, the selected features are given to BPNN to identify the input data either as normal or abnormal. The performance of the classifier was evaluated in terms of True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN) and the accuracy was found to be good.

PCNN, NSCT, Feature extraction, feature selection. Fire-fly, MR Brain Image

[1] D.Selvaraj, R., Dhanasekaran, A Review on Tissue Segmentation and Feature Extraction of MRI Brain Images, International journal of computer science & Engineering Technology,Vol. 4,pp. 1313-1332, 2013
[2] Iztok Fister, Iztok Fister Jr., Xin-She Yang, Janez Brest, A Comprehensive review of Firefly Algorithms, Swarm and Evolutionary Computation, Vol.13, pp. 34–46, 2013.
[3] Susana M., Vieira, Luís, F., Mendonça, Gonçalo J., Farinha, João M.C., and Sousa, Modified Binary PSO for Feature Selection using SVM Applied to Mortality Prediction of Septic Patients, Applied Soft Computing, Vol. 13, No. 8, pp. 3494–3504, 2013
[4] Ashish Kumar Bhandari, Vineet Kumar Singh, Anil Kumar, Girish Kumar ingh, Cuckoo Search Algorithm and Wind Driven Optimization based Study of Satellite Image Segmentation for Multilevel Thresholding using Kapur’s Entropy, Expert Systems with Applications, Vol. 41, No. 7, pp.3538–3560, 2014.
[5] Amita Kumari and Rajesh Mehra, Hybridized Classification of Brain MRI using PSO & SVM, International Journal of Engineering and Advanced Technology (IJEAT), Vol. 3, No. 4, pp. 319-323, 2014.
[6] Abdenour, Mekhmoukhand Karim Mokrani, Improved Fuzzy C-Means Based Particle Swarm Optimization (PSO) Initialization and Outlier Rejection with Level Set Methods for MR Brain Image Segmentation,Computer Methods and Programs in Biomedicine,Vol. 122, No. 2, pp. 266-281, 2015.
[7] Nguyen Cong Long, Phayung Meesad, and Herwig Unger, A highly Accurate Firefly based Algorithm for Heart disease Prediction, Expert Systems with Applications, Vol. 42, No.21, pp.8221–8231, 2015.
[8] Kuntimad, G and Ranganath, H.S, Perfect Image Segmentation using Pulse Coupled Neural Networks, IEEE Transactions on neural networks, Vol. 10, No.3, pp. 591-598, 1999.
[9] Liu Xiaofang, ChengDansong, Tang Xianglong, Liu Jiafeng (2008), Image Segmentation based on Pulse Coupled Neural Network, IEEE Conference on information sciences,pp. 744-748.
[10] Jhon L. Johnson and Mary Lou Padgett, PCNN Models and Applications , IEEE Transactions on neural networks, Vol. 10,No. 3, pp. 480-498, 1999.
[11] B.Thamaraichelvi, G.Yamuna, Application of various segmentation techniques for brain mri –a comparative study, International Journal of Advances in Engineering & Technology, Vol. 7, Issue 5, pp. 1434-1442, 2014.
[12] He Xiaolan and Wu Yili, Texture Feature Extraction Method Combining Non- sub sampled Contour Transformation with Gray Level Co-Occurrence Matrix, Journal of multimedia, Vol. 8, No. 6, pp. 675-684, 2013.
[13] Xin-She Yang, Firefly Algorithms, Nature-Inspired Optimization Algorithms, Chapter 8, pp. 111-127, 2014.
[14] Vanita Jain, Aarushi Jain, Achin Jain, Arun Kumar Dubey, Comparative Study between FA, ACO, and PSO Algorithms for Optimizing Quadratic Assignment Problem, Research Paper | Isroset-Journal (IJSRCSE), Vol.6 , Issue.2 , pp.76-81, Apr-2018. doi: https://doi.org/10.26438/ijsrcse/v6i2.7681,
[15] G.R.Shahmohammadi, Kh.Mohammadi, Key Management in Hierarchical Sensor Networks Using Improved Evolutionary Algorithm, Research Paper | Journal (IJSRNSC), Vol.4 , Issue.2 , pp.5-14, Apr-2016.