The Analysis of Digital Mammograms Using HOG and GLCM Features

An algorithm for early detection of breast cancer is proposed in this paper. Breast cancer is one disease if detected early, can be cured effectively. Failure of early detection is causing many deaths among woman worldwide. Early detection requires proper screening. Digital mammograms are useful for this purpose as they are non-invasive. But data available from the mammograms is often difficult to interpret and analyse. Many algorithms are available in the literature for analysis of digital mammograms. In this work, an algorithm using the concatenation of simple Histogram of Oriented Gradients (HOG) and Grey Level Co-Occurrence Matrix (GLCM) features are used for classification. The database used is a benchmark database MIAS. All the abnormal images of the database are chosen for the experimentation. The images in the database are of poor contrast and are having some noisy pixels. ROIs are extracted from the images. All the ROI (Region of Interest) images are pre-processed with median filtering and Contrast Limited Adaptive Histogram Equalization (CLAHE). Several classifiers are used to assess the performance of the proposed algorithm i.e., KNN, CT, SVM (RBF kernel), ANN, LDA, and Naive Bayes classifier. Performance metrics used in this work are sensitivity, specificity, precision and accuracy. Results are compared with the existing algorithms available in the literature and superiority of the proposed method is presented as the proposed method obtained an accuracy of 99.11%.

[1]  Keith E. Muller,et al.  Contrast-limited adaptive histogram equalization: speed and effectiveness , 1990, [1990] Proceedings of the First Conference on Visualization in Biomedical Computing.

[2]  Brijesh Verma,et al.  Classification of benign and malignant patterns in digital mammograms for the diagnosis of breast cancer , 2010, Expert Syst. Appl..

[3]  P. Petersen,et al.  Bendlets: A second-order shearlet transform with bent elements , 2016, Applied and Computational Harmonic Analysis.

[4]  Biswajit Pathak,et al.  TEXTURE ANALYSIS BASED ON THEGRAY-LEVEL CO-OCCURRENCEMATRIX CONSIDERING POSSIBLEORIENTATIONS , 2013 .

[5]  M. Tech,et al.  GLCM ARCHITECTURE FOR IMAGE EXTRACTION , 2014 .

[6]  Samir Brahim Belhaouari,et al.  A comparison of wavelet and curvelet for breast cancer diagnosis in digital mammogram , 2010, Comput. Biol. Medicine.

[7]  Shahriar B. Shokouhi,et al.  Classification of benign and malignant masses based on Zernike moments , 2011, Comput. Biol. Medicine.

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

[9]  Yide Ma,et al.  An Efficient Approach for Automated Mass Segmentation and Classification in Mammograms , 2015, Journal of Digital Imaging.

[10]  N. Pradeep,et al.  Segmentation and Feature Extraction of Tumors from Digital Mammograms , 2012 .

[11]  Rabi Narayan Panda,et al.  Efficient CAD system based on GLCM & derived feature for diagnosing Breast Cancer , 2015 .

[12]  Ibrahima Faye,et al.  A method to reduce curvelet coefficients for mammogram classification , 2014, 2014 IEEE REGION 10 SYMPOSIUM.

[13]  David Gur,et al.  Improving breast mass detection using histogram of oriented gradients , 2014, Medical Imaging.

[14]  R Nithya,et al.  Classification of Normal and Abnormal Patterns in Digital Mammograms for Diagnosis of Breast Cancer , 2011 .

[15]  Zhe Wang,et al.  Classification of Region of Interest in Mammograms Using Dual Contourlet Transform and Improved KNN , 2017, J. Sensors.

[16]  Hamid Soltanian-Zadeh,et al.  Fast opposite weight learning rules with application in breast cancer diagnosis , 2013, Comput. Biol. Medicine.

[17]  B. Mohan,et al.  Automatic breast cancer analysis using Bandelet transform , 2015, 2015 National Conference on Recent Advances in Electronics & Computer Engineering (RAECE).