Automatic breast density segmentation based on pixel classification

Mammographic breast density has been found to be a strong risk factor for breast cancer. In most studies it is assessed with a user assisted threshold method, which is time consuming and subjective. In this study we develop a breast density segmentation method that is fully automatic. The method is based on pixel classification in which different approaches known in literature to segment breast density are integrated and extended. In addition the method incorporates knowledge of a trained observer, by using segmentations obtained by the user assisted threshold method as training data. The method is trained and tested using 1300 digitised film mammographic images acquired with a variety of systems. Results show a high correspondence between the automated method and the user assisted threshold method. The Spearman's rank correlation coefficient between our method and the user assisted method was R = 0.914 for percent density, which is substantially higher than the best correlation found in literature (R=0.70). The AUC obtained when discriminating between fatty and dense pixels was 0.985. A combination of segmentation strategies outperformed the application of a single segmentation technique. The method was shown to be robust for differences in mammography systems, image acquisition techniques and image quality.

[1]  N Karssemeijer,et al.  Automated classification of parenchymal patterns in mammograms. , 1998, Physics in medicine and biology.

[2]  Imma Boada,et al.  Breast Density Segmentation: A Comparison of Clustering and Region Based Techniques , 2008, Digital Mammography / IWDM.

[3]  Nico Karssemeijer,et al.  Volumetric breast density estimation from full-field digital mammograms , 2006, IEEE Trans. Medical Imaging.

[4]  Michael Brady,et al.  Mammographic Image Analysis , 1999, Computational Imaging and Vision.

[5]  Xavier Lladó,et al.  A Statistical Approach for Breast Density Segmentation , 2010, Journal of Digital Imaging.

[6]  Josef Kittler,et al.  Floating search methods in feature selection , 1994, Pattern Recognit. Lett..

[7]  Dan Rico,et al.  A volumetric method for estimation of breast density on digitized screen-film mammograms. , 2003, Medical physics.

[8]  Nico Karssemeijer,et al.  Thickness correction of mammographic images by anisotropic filtering and interpolation of dense tissue , 2005, SPIE Medical Imaging.

[9]  Paul Sajda,et al.  Role of feature selection in building pattern recognizers for computer-aided diagnosis , 1998, Medical Imaging.

[10]  Maryellen L. Giger,et al.  Power Spectral Analysis of Mammographic Parenchymal Patterns for Breast Cancer Risk Assessment , 2008, Journal of Digital Imaging.

[11]  T. Sellers,et al.  Mammographic density, breast cancer risk and risk prediction , 2007, Breast Cancer Research.

[12]  Theofanis Sapatinas,et al.  Discriminant Analysis and Statistical Pattern Recognition , 2005 .

[13]  Norman F. Boyd,et al.  Screen-Film Mammographic Density and Breast Cancer Risk: A Comparison of the Volumetric Standard Mammogram Form and the Interactive Threshold Measurement Methods , 2010, Cancer Epidemiology, Biomarkers & Prevention.

[14]  R. J. Ferrari,et al.  Segmentation of the fibro-glandular disc in mammogrms using Gaussian mixture modelling , 2004, Medical and Biological Engineering and Computing.

[15]  Michael Brady,et al.  Breast Density Segmentation Using Texture , 2006, Digital Mammography / IWDM.

[16]  N. Boyd,et al.  Breast tissue composition and susceptibility to breast cancer. , 2010, Journal of the National Cancer Institute.

[17]  Maryellen L. Giger,et al.  Computerized texture analysis of mammographic parenchymal patterns of digitized mammograms , 2004, CARS.

[18]  Michael J. Carston,et al.  An Automated Approach for Estimation of Breast Density , 2008, Cancer Epidemiology Biomarkers & Prevention.

[19]  Bradley M. Hemminger,et al.  Mixture Modeling for Digital Mammogram Display and Analysis , 1998, Digital Mammography / IWDM.

[20]  Arnau Olivera,et al.  Classifying mammograms using texture information , 2007 .

[21]  N. Boyd,et al.  The quantitative analysis of mammographic densities. , 1994, Physics in medicine and biology.

[22]  Nico Karssemeijer,et al.  The effect of feature selection methods on computer-aided detection of masses in mammograms , 2010, Physics in medicine and biology.

[23]  J J Heine,et al.  A statistical methodology for mammographic density detection. , 2000, Medical physics.

[24]  Michael Brady,et al.  Texture Based Mammogram Classification and Segmentation , 2006, Digital Mammography / IWDM.

[25]  V. McCormack,et al.  Breast Density and Parenchymal Patterns as Markers of Breast Cancer Risk: A Meta-analysis , 2006, Cancer Epidemiology Biomarkers & Prevention.

[26]  Maryellen L. Giger,et al.  Computerized Texture Analysis of Mammographic Parenchymal Patterns of Digitized Mammograms1 , 2005 .