Quantitative assessment of breast density from digitized mammograms into Tabar's patterns

We describe a semi-automated technique for the quantitative assessment of breast density from digitized mammograms in comparison with patterns suggested by Tabar. It was developed using the MATLAB-based graphical user interface applications. It is based on an interactive thresholding method, after a short automated method that shows the fibroglandular tissue area, breast area and breast density each time new thresholds are placed on the image. The breast density is taken as a percentage of the fibroglandular tissue to the breast tissue areas. It was tested in four different ways, namely by examining: (i) correlation of the quantitative assessment results with subjective classification, (ii) classification performance using the quantitative assessment technique, (iii) interobserver agreement and (iv) intraobserver agreement. The results of the quantitative assessment correlated well (r2 = 0.92) with the subjective Tabar patterns classified by the radiologist (correctly classified 83% of digitized mammograms). The average kappa coefficient for the agreement between the readers was 0.63. This indicated moderate agreement between the three observers in classifying breast density using the quantitative assessment technique. The kappa coefficient of 0.75 for intraobserver agreement reflected good agreement between two sets of readings. The technique may be useful as a supplement to the radiologist's assessment in classifying mammograms into Tabar's pattern associated with breast cancer risk.

[1]  L. Looi,et al.  Mammographic breast glandularity in Malaysian women: data derived from radiography. , 2004, AJR. American journal of roentgenology.

[2]  N. Boyd,et al.  Mammographic densities and breast cancer risk. , 1998, Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology.

[3]  P. Taylor,et al.  Measuring image texture to separate "difficult" from "easy" mammograms. , 1994, The British journal of radiology.

[4]  M Souto,et al.  Computer-assisted diagnosis: the classification of mammographic breast parenchymal patterns. , 1995, Physics in medicine and biology.

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

[6]  L. Tabár,et al.  The Tabár classification of mammographic parenchymal patterns. , 1997, European journal of radiology.

[7]  M. Pike,et al.  Changes in mammographic densities induced by a hormonal contraceptive designed to reduce breast cancer risk. , 1994, Journal of the National Cancer Institute.

[8]  David Gur,et al.  Computerized assessment of tissue composition on digitized mammograms. , 2002, Academic radiology.

[9]  J. Vetter,et al.  Entrance skin exposure and mean glandular dose: effect of scatter and field gradient at mammography. , 1997, Radiology.

[10]  N. Boyd,et al.  Automated analysis of mammographic densities. , 1996, Physics in medicine and biology.

[11]  H Rusinek,et al.  Fatty and fibroglandular tissue volumes in the breasts of women 20-83 years old: comparison of X-ray mammography and computer-assisted MR imaging. , 1997, AJR. American journal of roentgenology.

[12]  M A Astrahan,et al.  The detection of changes in mammographic densities. , 1998, Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology.

[13]  N. Obuchowski,et al.  Automatic segmentation of mammographic density. , 2001, Academic radiology.

[14]  Jayaram K. Udupa,et al.  Optimum Image Thresholding via Class Uncertainty and Region Homogeneity , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Lubomir M. Hadjiiski,et al.  Computerized image analysis: estimation of breast density on mammograms. , 2001, Medical physics.

[16]  J. Brady,et al.  Estimation of compressed breast thickness during mammography. , 1998, The British journal of radiology.

[17]  J. Grove,et al.  Wolfe's mammographic classification and breast cancer risk: the effect of misclassification on apparent risk ratios. , 1985, The British journal of radiology.

[18]  A. Miller,et al.  Quantitative classification of mammographic densities and breast cancer risk: results from the Canadian National Breast Screening Study. , 1995, Journal of the National Cancer Institute.

[19]  K. Faulkner,et al.  An Investigation into Variations in the Estimation of Mean Glandular Dose in Mammography , 1995 .

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

[21]  Dev P. Chakraborty,et al.  Breast tissue density quantification via digitized mammograms , 2001, IEEE Transactions on Medical Imaging.

[22]  N. Boyd,et al.  Relationship between mammographic and histological risk factors for breast cancer. , 1992, Journal of the National Cancer Institute.

[23]  B. Chapman,et al.  Automated assessment of the composition of breast tissue revealed on tissue-thickness-corrected mammography. , 2003, AJR. American journal of roentgenology.

[24]  P. Toniolo,et al.  Reproducibility of Wolfe's classification of mammographic parenchymal patterns. , 1992, Preventive medicine.

[25]  Caroline Diorio,et al.  Wolfe's parenchymal pattern and percentage of the breast with mammographic densities: redundant or complementary classifications? , 2003, Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology.

[26]  E. Fishell,et al.  Mammographic patterns and breast cancer risk: methodologic standards and contradictory results. , 1984, Journal of the National Cancer Institute.

[27]  J. Wolfe.  Breast patterns as an index of risk for developing breast cancer. , 1976, AJR. American journal of roentgenology.

[28]  A. Oza,et al.  Mammographic parenchymal patterns: a marker of breast cancer risk. , 1993, Epidemiologic reviews.

[29]  S. Duffy,et al.  Mammographic parenchymal patterns and risk of breast cancer at and after a prevalence screen in Singaporean women. , 2000, International journal of epidemiology.

[30]  W J Davros,et al.  Quantitative analysis of breast parenchymal density: correlation with women's age. , 1999, Academic radiology.

[31]  I. Gram,et al.  Percentage density, Wolfe's and Tabár's mammographic patterns: agreement and association with risk factors for breast cancer , 2005, Breast Cancer Research.

[32]  L. Clarke,et al.  Image segmentation in digital mammography: comparison of local thresholding and region growing algorithms. , 1992, Computerized Medical Imaging and Graphics.

[33]  N. Boyd,et al.  Analysis of mammographic density and breast cancer risk from digitized mammograms. , 1998, Radiographics : a review publication of the Radiological Society of North America, Inc.

[34]  J. Russo,et al.  Cancer risk related to mammary gland structure and development , 2001, Microscopy research and technique.