A New Method Based-Gentle Adaboost and Wavelet Transform for Breast Cancer Classification

In this paper we have realized a comparative study of mammograms classification accuracy based on a new Gentle Adaboost algorithm for different wavelet transforms and different features. Our proposition deals with the combination of a new Gentle Adaboost based algorithm with three wavelets transforms. In this new algorithm, the main classifier is realized by weighted weak classifiers. These weak classifiers are constructed from the sub-bands of discrete wavelet transform, stationary wavelet transform and double density wavelet transform. Used features are extracted from transformed mammograms. We have investigated the effect of these wavelet transforms combined with the extracted features on the classification accuracy. Receiver Operating Curves (ROC) tool is employed to evaluate the performance of the propositions. Mammograms of MIAS Database are used as samples to classify. True positive rate is plotted versus false positive rate for different types of features and for Gentle Adaboost iterations. Results showed that the best area under curve (AUC), is reached for Zernike moments combined with double density wavelet transform and it is equal to 1 for both t = 10 and t = 50.

[1]  Gunnar Rätsch,et al.  An Introduction to Boosting and Leveraging , 2002, Machine Learning Summer School.

[2]  Yoav Freund,et al.  Boosting a weak learning algorithm by majority , 1995, COLT '90.

[3]  L. M. Murphy,et al.  Linear feature detection and enhancement in noisy images via the Radon transform , 1986, Pattern Recognit. Lett..

[4]  Mark Culp,et al.  ada: An R Package for Stochastic Boosting , 2006 .

[5]  Anil K. Jain,et al.  Audio- and Video-Based Biometric Person Authentication: 5th International Conference, AVBPA 2005, Hilton Rye Town, NY, USA, July 20-22, 2005, Proceedings (Lecture Notes in Computer Science) , 2005 .

[6]  Loris Nanni,et al.  Wavelet selection for disease classification by DNA microarray data , 2011, Expert Syst. Appl..

[7]  Suzanne Lesecq,et al.  Fault Isolation Based on Wavelets Transform , 2007 .

[8]  C. N. Savithri,et al.  EFFECTIVE MULTI-RESOLUTION TRANSFORM IDENTIFICATION FOR CHARACTERIZATION AND CLASSIFICATION OF TEXTURE GROUPS , 2011 .

[9]  Stanley R. Deans,et al.  Hough Transform from the Radon Transform , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Shuzhi Sam Ge,et al.  Face recognition by applying wavelet subband representation and kernel associative memory , 2004, IEEE Transactions on Neural Networks.

[11]  Stefan M. Rüger,et al.  Evaluation of Texture Features for Content-Based Image Retrieval , 2004, CIVR.

[12]  Hideyuki Tamura,et al.  Textural Features Corresponding to Visual Perception , 1978, IEEE Transactions on Systems, Man, and Cybernetics.

[13]  Robert E. Schapire,et al.  The Boosting Approach to Machine Learning An Overview , 2003 .

[14]  R. Schapire.  The Strength of Weak Learnability , 1990, Machine Learning.

[15]  Ian W. Ricketts,et al.  The Mammographic Image Analysis Society digital mammogram database , 1994 .

[16]  Josef Kittler,et al.  Audio- and Video-Based Biometric Person Authentication, 5th International Conference, AVBPA 2005, Hilton Rye Town, NY, USA, July 20-22, 2005, Proceedings , 2005, AVBPA.

[17]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[18]  Yoram Singer,et al.  Improved Boosting Algorithms Using Confidence-rated Predictions , 1998, COLT' 98.

[19]  B. Silverman,et al.  The Stationary Wavelet Transform and some Statistical Applications , 1995 .

[20]  Yoav Freund,et al.  An Adaptive Version of the Boost by Majority Algorithm , 1999, COLT '99.

[21]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.