An automated classification scheme for mammograms based on amount and distribution of fibroglandular breast tissue density

Mammographic parenchymal patterns in asymptomatic women

Background:

Breast density has been found to be an independent risk factor for breast cancer. Mammographic breast parenchymal pattern or percent density is mainly a reflection of the proportion of glandular tissue to fatty tissue, and studies have shown that it works synergistically with other risk factors such as nulliparity in predicting breast cancer risk. This study analyses the various mammographic breast patterns and correlates this with some demographic variables and final Breast Imaging Reporting and Data System outcomes of asymptomatic women in our center.

Materials and Methods:

This is a prospective descriptive study of mammographic breast pattern in 459 females who presented at the breast imaging suite of our institution. Mammography was performed after completion of an assisted administered questionnaire for demographic information. A GE Senographe DMR machine using two standard views (craniocaudal and mediolateral oblique) and additional views were used when necessary.

Results:

A total of 459 women ranging in age from 34 to 80 years were included in the study, of which 46.6% were in the age range of 41 to 50 years. The scattered fibroglandular pattern was the most common pattern found (44%), and the homogeneous dense pattern was the least common (0.4%). A significant association with age and menopause status was found, while no association was found with age at the time of the woman's first delivery and family history of breast cancer.

Conclusion:

This study demonstrates that there is a significant association between breast cancer and age and menopause status. However, no correlation was found with the age of women at their first delivery and family history of breast cancer.

Computer aided detection of breast density and mass, and visualization of other breast anatomical regions on mammograms using graph cuts

Breast cancer mostly arises from the glandular (dense) region of the breast. Consequently, breast density has been found to be a strong indicator for breast cancer risk. Therefore, there is a need to develop a system which can segment or classify dense breast areas. In a dense breast, the sensitivity of mammography for the early detection of breast cancer is reduced. It is difficult to detect a mass in a breast that is dense. Therefore, a computerized method to separate the existence of a mass from the glandular tissues becomes an important task. Moreover, if the segmentation results provide more precise demarcation enabling the visualization of the breast anatomical regions, it could also assist in the detection of architectural distortion or asymmetry. This study attempts to segment the dense areas of the breast and the existence of a mass and to visualize other breast regions (skin-air interface, uncompressed fat, compressed fat, and glandular) in a system. The graph cuts (GC) segmentation technique is proposed. Multiselection of seed labels has been chosen to provide the hard constraint for segmentation of the different parts. The results are promising. A strong correlation (r = 0.93) was observed between the segmented dense breast areas detected and radiological ground truth.