A new hybrid method combining genetic algorithm and support vector machine classifier: Application to CAD system for mammogram images

Breast cancer continues to be one of the most common cancers, and survival rates critically depend on its detection in the initial stages. Several studies have demonstrated the benefits and potential of using CAD (Computer-Assisted Diagnosis) systems to help specialists in their clinical interpretation of mammograms. CAD is based essentially on 2 main steps: Extraction of pertinent features and classification. In fact, several types of features are used in this work characterizing the extracted masses which are: texture features based on co-occurrence matrix and shape features based on Hu moments and central moments. All these features represent feature vector used in training and testing the used classifier. To reduce dimensionality and optimize classification process a new approach based on genetic algorithm is proposed. It incorporates Svm classifier results as part of multi objective function for fitness function. Once the best subset of features is chosen, classification is made by SVM classifier using Gaussian kernel function. Experimental results demonstrate the effectiveness of the proposed algorithm.

[1]  Jinlian Wang,et al.  2-D MT inversion using genetic algorithm , 2005 .

[2]  Hae-Kwang Kim,et al.  Region-based shape descriptor invariant to rotation, scale and translation , 2000, Signal Process. Image Commun..

[3]  V. Vapnik.  Estimation of Dependences Based on Empirical Data , 2006 .

[4]  Mohammad Darzi,et al.  Feature Selection for Breast Cancer Diagnosis: A Case-Based Wrapper Approach , 2011 .

[5]  Nadir Farah,et al.  Kernel based classifiers fusion with features diversity for breast masses classification , 2013, 2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA).

[6]  中松 和巳.  New advances in intelligent decision technologies : results of the first KES international symposium IDT 2009 , 2009 .

[7]  M. Rízzí.  Review : Health Care CAD Systems for Breast Microcalcification Cluster Detection , 2012 .

[8]  Mohamed Tayeb Laskri,et al.  Random vector quantisation modelling in automatic speaker verification , 2013, Int. J. Biom..

[9]  Daphne Koller,et al.  Toward Optimal Feature Selection , 1996, ICML.

[10]  Shlomo Zilberstein,et al.  Using Anytime Algorithms in Intelligent Systems , 1996, AI Mag..

[11]  Jean Yee Hwa Yang,et al.  Two-Step Cross-Entropy Feature Selection for Microarrays—Power Through Complementarity , 2011, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[12]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[13]  M K Markey,et al.  Application of the mutual information criterion for feature selection in computer-aided diagnosis. , 2001, Medical physics.

[14]  Nami Mun.  University of Michigan Alumni Reading , 2010 .

[15]  Sung-Bae Cho,et al.  Efficient huge-scale feature selection with speciated genetic algorithm , 2005 .

[16]  E.J. Delp,et al.  A Comparison of Feature Selection Methods for the Detection of Breast Cancers in Mammograms: Adaptive Sequential Floating Search vs. Genetic Algorithm , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[17]  S Forrest,et al.  Genetic algorithms , 1996, CSUR.

[18]  Lakhmi C. Jain,et al.  Recent Advances in Intelligent Decision Technologies , 2007, KES.

[19]  Ping Zhang,et al.  A neural-genetic algorithm for feature selection and breast abnormality classification in digital mammography , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[20]  Thomas M. Deserno,et al.  Breast Lesions Classification applied to a reference database , 2008 .

[21]  Alireza Osareh,et al.  A Computer Aided Diagnosis System for Breast Cancer , 2011 .

[22]  Xiaoming Xu,et al.  A hybrid genetic algorithm for feature selection wrapper based on mutual information , 2007, Pattern Recognit. Lett..