Open Access Open Access  Restricted Access Subscription or Fee Access

A Hybrid Feature Extraction Scheme Based on DWT and Uniform LBP for Digital Mammograms Classification

(*) Corresponding author

Authors' affiliations



Breast cancer can be treated most effectively when detected in its early stage. To support radiologists to detect breast abnormalities earlier and more rapidly, creation of a system to analyze automatically mammograms is important. Several techniques can be used to accomplish this task. This paper presents a new approach for digital mammograms classification based on hybrid feature extraction. After decomposing mammogram images in wavelet basis for global feature extraction, block-based uniform local binary pattern is used to extract local features from the resulting sub-bands. Principal component analysis is employed for dimensionality reduction The Support vector machine is then used to construct a supervised classifier. Comparisons with another artificial intelligence algorithm i.e. KNearest Neighbor were also made using two distance calculation methods, namely Euclidian and City-block. Experimental results on Digital Database for Screening Mammography (DDSM) show that the proposed method can classify normal from abnormal mammograms more effectively and has proved also to be better in comparison to other traditional recognition methods.
Copyright © 2015 Praise Worthy Prize - All rights reserved.


Mammograms Classification; Hybrid Feature Extraction; Discrete Wavelet Transform; Uniform Local Binary Pattern; Support Vector Machine

Full Text:



World Health Organization,Cancer,Fact Sheet No.297.

H. D. Cheng, J. Shan, W. Ju, Y. Guo, et L. Zhang, « Automated breast cancer detection and classification using ultrasound images: A survey », Pattern Recognit., vol. 43, no 1, p. 299 - 317, 2010.

« A comparison of two methods for the segmentation of masses in the digital mammograms », Comput. Med. Imaging Graph., vol. 34, no 3, p. 185 - 191, 2010.

G. ML, K. N, A. SG, « Computer aided diagnosis in medical imaging », IEEE Trans Med Imaging, vol. 20, no 12, p. 1205–8, 2001.

K. Ganesan, U. R. Acharya, C. K. Chua, L. C. Min, K. T. Abraham, et K. Ng, « Computer-Aided Breast Cancer Detection Using Mammograms: A Review », Biomed. Eng. IEEE Rev. In, vol. 6, p. 77-98, 2013.

E. A. Rashed, I. A. Ismail, et S. I. Zaki, « Multiresolution mammogram analysis in multilevel decomposition », Pattern Recognit. Lett., vol. 28, no 2, p. 286 - 292, 2007.

I. Buciu et A. Gacsadi, « Directional features for automatic tumor classification of mammogram images », Biomed. Signal Process. Control, vol. 6, no 4, p. 370 - 378, 2011.

R. Bellotti, F. De Carlo, S. Tangaro, G. Gargano, G. Maggipinto, M. Castellano, R. Massafra, D. Cascio, F. Fauci, R. Magro, et others, « A completely automated CAD system for mass detection in a large mammographic database », Med. Phys., vol. 33, no 8, p. 3066–3075, 2006.

J. Liu, X. Liu, J. Chen, et J. Tang, « Improved local binary patterns for classification of masses using mammography », in Systems, Man, and Cybernetics (SMC), 2011 IEEE International Conference on, p. 2692-2695, 2011.

M. Meselhy Eltoukhy, I. Faye, B. Belhaouari Samir, « A statistical based feature extraction method for breast cancer diagnosis in digital mammogram using multiresolution representation », Comput. Biol. Med., vol. 42, no 1, p. 123–128, 2012.

R. Mousa, Q. Munib, et A. Moussa, « Breast cancer diagnosis system based on wavelet analysis and fuzzy-neural », Expert Syst. Appl., vol. 28, no 4, p. 713 - 723, 2005.

S. Berraho, S. El Margae, M. Ait Kerroum,Y. Fakhri, « Statistical block-based DWT features for digital mammograms classification », SITA'14 - The 9th International Conference on Intelligent Systems: Theories and Applications , p. 1-7, 2014.

Y. Zhang, N. Tomuro, J. Furst, D. Raicu, « Building an ensemble system for diagnosing masses in mammograms », Int. J. Comput. Assist. Radiol. Surg., vol. 7, no 2, p. 323-329, 2012.

C. B. R. Ferreira et D. L. Borges, « Analysis of mammogram classification using a wavelet transform decomposition », Pattern Recognit. Lett., vol. 24, no 7, p. 973 - 982, 2003.

T. Ojala, M. Pietikäinen, D. Harwood, « A comparative study of texture measures with classification based on featured distributions », Pattern Recognit., vol. 29, no 1, p. 51–59, 1996.

M. Vetterli et C. Herley, « Wavelets and filter banks: theory and design », Signal Process. IEEE Trans. On, vol. 40, no 9, p. 2207-2232, sept. 1992.

S. Mallat, A wavelet tour of signal processing. Academic press, 1999.

E. Sakka, A. Prentza, I. Lamprinos, D. Koutsouris, « Microcalcification detection using multiresolution analysis based on wavelet transform », in IEEE International Special Topic Conference on Information Technology in Biomedicine, Ioannina, Epirus, Greece, 2006.

T. Ojala, M. Pietikainen, T. Maenpaa, « Multiresolution gray-scale and rotation invariant texture classification with local binary patterns », Pattern Anal. Mach. Intell. IEEE Trans. On, vol. 24, no 7, p. 971-987, juill. 2002.

J. Fehr et H. Burkhardt, « 3D rotation invariant local binary patterns », in Pattern Recognition, 2008. ICPR 2008. 19th International Conference on, p. 1-4, 2008.

V. Vapnik, Statistical learning theory. 1988.

C. Cortes , V. Vapnik, « Support-vector networks », Mach. Learn., vol. 20, no 3, p. 273–297, 1995.

N. Cristianini , J. Shawe-Taylor, An introduction to support vector machines and other kernel-based learning methods. Cambridge university press, 2000.

J. Kim, B.-S. Kim, S. Savarese, « Comparing image classification methods: K-nearest-neighbor and support-vector-machines », in Proceedings of the 6th WSEAS international conference on Computer Engineering and Applications, and Proceedings of the 2012 American conference on Applied Mathematics, p. 133–138, 2012.

K. Bowyer, D. Kopans, W. Kegelmeyer, R. Moore, M. Sallam, K. Chang, K. Woods, « The digital database for screening mammography », in Third International Workshop on Digital Mammography, vol. 58, 1996.

BI-RADS, « Breast imaging reporting and data system (BI-RADS) breast imaging atlas (4th ed.) », American College of Radiology, 2003.

S. Ergin, O. Kilinc, « A new feature extraction framework based on wavelets for breast cancer diagnosis », Comput. Biol. Med., vol. 51, no 0, p. 171 - 182, 2014.

A. Khare, U. S. Tiwary, « Soft-thresholding for denoising of medical images—A multiresolution approach », Int. J. Wavelets Multiresolution Inf. Process., vol. 3, no 04, p. 477–496, 2005.

Principal Component Analysis Series: Springer Series on Statistics. 2nd Ed., Springer, NY, 2002.

C.-W. Hsu, C.-C. Chang, C.-J. Lin, others, A practical guide to support vector classification. 2003.

M. Agarwal, A. Kumar, V. Gupta, « Text Extraction of Colour Images using Mathematical Morphology & HAAR Transform », IOSR J. Comput. Eng. IOSR-JCE E-ISSN, p. 2278–0661, 2013.

M. M. Eltoukhy , I. Faye, « An Optimized Feature Selection Method For Breast Cancer Diagnosis in Digital Mammogram using Multiresolution Representation », Appl Math, vol. 8, no 6, p. 2921–2928, 2014.

D. Wang, L. Shi, P. A. Heng, « Automatic detection of breast cancers in mammograms using structured support vector machines », Neurocomputing, vol. 72, no 13-15, p. 3296 - 3302, 2009.

M. Masotti, « A ranklet-based image representation for mass classification in digital mammograms », Med. Phys., vol. 33, no 10, p. 3951–3961, 2006.


Please send any question about this web site to
Copyright © 2005-2024 Praise Worthy Prize