Detection of masses based on asymmetric regions of digital bilateral mammograms using spatial description with variogram and cross-variogram functions

A mammogram is an examination of the breast intended to prevent and diagnose breast cancer. In this work we propose a methodology for detecting masses by determining certain asymmetric regions between pairs of mammograms of the left and the right breast. The asymmetric regions are detected by means of structural variations between corresponding regions, defined by a spatial descriptor called cross-variogram function. After determining the asymmetric regions of a pair of images, the variogram function is applied to each asymmetric region separately, for classification as either mass or non-mass. The first stage of the methodology consists in preprocessing the images to make them adequate for registration. The following step performs the bilateral registration of pairs of left and right breasts. Pairs of corresponding regions are listed and their variations are measured by means of the cross-variogram spatial descriptor. Next, a model is created to train a Support Vector Machine (SVM) using the values of the cross-variogram function of each pair of windows as features. The pairs of breasts containing lesions are classified as asymmetric regions; the remaining ones are classified as symmetric regions. From the asymmetric regions, features are extracted from the variogram function to be used as tissue texture descriptors. The regions containing masses are classified as mass regions, and the other ones as non-mass regions. Stepwise linear discriminant analysis is used to select the most statistically significant features. Tests are performed with new cases for the final classification as either mass or non-mass by the trained SVM. The best results presented in the final classification were 96.38% of accuracy, 100% of sensitivity and 95.34% of specificity. The worst case presented 70.21% of accuracy, 100% of sensitivity and 67.56% of specificity. The average values for all tests were 90.26% of accuracy, 100% of sensitivity and 85.37% of specificity.

[1]  A.K. Barros,et al.  Independent Component Analysis in Breast Tissues Mammograms Images Classification Using LDA and SVM , 2007, 2007 6th International Special Topic Conference on Information Technology Applications in Biomedicine.

[2]  Michael Edward Hohn,et al.  An Introduction to Applied Geostatistics: by Edward H. Isaaks and R. Mohan Srivastava, 1989, Oxford University Press, New York, 561 p., ISBN 0-19-505012-6, ISBN 0-19-505013-4 (paperback), $55.00 cloth, $35.00 paper (US) , 1991 .

[3]  Marcelo Zanchetta do Nascimento,et al.  Automatic Detection of Breast Masses Using Two-View Mammography , 2009 .

[4]  Kevin W. Bowyer,et al.  Registration and difference analysis of corresponding mammogram images , 1999, Medical Image Anal..

[5]  Cheng-Chang Lu,et al.  Non-rigid mammogram registration using demons algorithm: Preliminary results , 2007, SIP.

[6]  Anthony Widjaja,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2003, IEEE Transactions on Neural Networks.

[7]  Jean-Philippe Thirion,et al.  Fast Non-Rigid Matching of 3D Medical Images , 1995 .

[8]  Ian W. Ricketts,et al.  Detecting abnormalities on mammograms by bilateral comparison , 1996 .

[9]  Anselmo Cardoso de Paiva,et al.  Detection of Breast Masses in Mammogram Images Using Growing Neural Gas Algorithm and Ripley’s K Function , 2009, J. Signal Process. Syst..

[10]  R. Bilonick.  An Introduction to Applied Geostatistics , 1989 .

[11]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[12]  N. Obuchowski.  Receiver operating characteristic curves and their use in radiology. , 2003, Radiology.

[13]  Nikos Dimitropoulos,et al.  A fully automated scheme for mammographic segmentation and classification based on breast density and asymmetry , 2011, Comput. Methods Programs Biomed..

[14]  Anselmo Cardoso de Paiva,et al.  Detection of masses in mammographic images using geometry, Simpson's Diversity Index and SVM , 2010 .

[15]  Yufeng Zheng,et al.  Breast Cancer Detection with Gabor Features from Digital Mammograms , 2010, Algorithms.

[16]  J. Manning,et al.  The relationship between breast asymmetry, breast size and the occurrence of breast cancer. , 1997, The British journal of radiology.

[17]  Shengzhou Xu,et al.  Bilateral Asymmetry Detection in Mammograms Using Non-rigid Registraion and Pseudo-color Coding , 2010, 2010 International Conference on Electrical and Control Engineering.

[18]  P. Parsons,et al.  FLUCTUATING ASYMMETRY: AN EPIGENETIC MEASURE OF STRESS , 1990, Biological reviews of the Cambridge Philosophical Society.

[19]  Xuelong Li,et al.  On Combining Morphological Component Analysis and Concentric Morphology Model for Mammographic Mass Detection , 2010, IEEE Transactions on Information Technology in Biomedicine.

[20]  T K Lau,et al.  Automated detection of breast tumors using the asymmetry approach. , 1991, Computers and biomedical research, an international journal.

[21]  Nico Karssemeijer,et al.  Temporal Change Analysis for Characterization of Mass Lesions in Mammography , 2007, IEEE Transactions on Medical Imaging.

[22]  Bin Zheng,et al.  Computerized detection of breast tissue asymmetry depicted on bilateral mammograms: a preliminary study of breast risk stratification. , 2010, Academic radiology.

[23]  Maryellen L. Giger,et al.  Computerized detection of masses in digital mammograms: Investigation of feature-analysis techniques , 1994, Journal of Digital Imaging.

[24]  Richard H. Moore,et al.  Current Status of the Digital Database for Screening Mammography , 1998, Digital Mammography / IWDM.

[25]  Anselmo Cardoso de Paiva,et al.  Detection of masses in mammogram images using CNN, geostatistic functions and SVM , 2011, Comput. Biol. Medicine.

[26]  Anastasios N. Venetsanopoulos,et al.  Mean shift based algorithm for mammographic breast mass detection , 2010, 2010 IEEE International Conference on Image Processing.

[27]  Hironori Yamauchi,et al.  Detecting mass and its region in mammograms using mean shift segmentation and Iris Filter , 2010, 2010 10th International Symposium on Communications and Information Technologies.

[28]  Eun-Kyung Kim,et al.  Asymmetric mammographic findings based on the fourth edition of BI-RADS: types, evaluation, and management. , 2009, Radiographics : a review publication of the Radiological Society of North America, Inc.

[29]  Lubomir M. Hadjiiski,et al.  Bilateral analysis based false positive reduction for computer-aided mass detection. , 2007, Medical physics.

[30]  A. Ardeshir Goshtasby.  2-D and 3-D Image Registration for Medical Remote Sensing , 2008 .

[31]  Peter A. Lachenbruch,et al.  Some unsolved practical problems in discriminant analysis , 1975 .

[32]  A. Ardeshir Goshtasby,et al.  2-D and 3-D Image Registration: for Medical, Remote Sensing, and Industrial Applications , 2005 .

[33]  Alexander J. Smola,et al.  Learning with Kernels: support vector machines, regularization, optimization, and beyond , 2001, Adaptive computation and machine learning series.

[34]  Fredrik Georgsson,et al.  Differential Analysis Of Bilateral Mammograms , 2003, Int. J. Pattern Recognit. Artif. Intell..

[35]  Anastasios N. Venetsanopoulos,et al.  Breast mass detection using bilateral filter and mean shift based clustering , 2010, 2010 International Conference on Signal Processing and Multimedia Applications (SIGMAP).

[36]  J. Manning,et al.  Breast asymmetry and predisposition to breast cancer , 2006, Breast Cancer Research.