Estimation of breast percent density in raw and processed full field digital mammography images via adaptive fuzzy c‐means clustering and support vector machine segmentation

Abstract

Purpose:The amount of fibroglandular tissue content in the breast as estimated mammographically, commonly referred to as breast percent density (PD%), is one of the most significant risk factors for developing breast cancer. Approaches to quantify breast density commonly focus on either semiautomated methods or visual assessment, both of which are highly subjective. Furthermore, most studies published to date investigating computer-aided assessment of breast PD% have been performed using digitized screen-film mammograms, while digital mammography is increasingly replacing screenfilm mammography in breast cancer screening protocols. Digital mammography imaging generates two types of images for analysis, raw (i.e., "FOR PROCESSING") and vendor postprocessed (i.e., "FOR PRESENTATION"), of which postprocessed images are commonly used in clinical practice. Development of an algorithm which effectively estimates breast PD% in both raw and postprocessed digital mammography images would be beneficial in terms of direct clinical application and retrospective analysis. Methods: This work proposes a new algorithm for fully automated quantification of breast PD% based on adaptive multiclass fuzzy c-means (FCM) clustering and support vector machine (SVM) classification, optimized for the imaging characteristics of both raw and processed digital mammography images as well as for individual patient and image characteristics. Our algorithm first delineates the breast region within the mammogram via an automated thresholding scheme to identify background air followed by a straight line Hough transform to extract the pectoral muscle region. The algorithm then applies adaptive FCM clustering based on an optimal number of clusters derived from image properties of the specific mammogram to subdivide the breast into regions of similar graylevel intensity. Finally, a SVM classifier is trained to identify which clusters within the breast tissue are likely fibroglandular, which are then aggregated into a final dense tissue segmentation that is used to compute breast PD%. Our method is validated on a group of 81 women for whom bilateral, mediolateral oblique, raw and processed screening digital mammograms were available, and agreement is assessed with both continuous and categorical density estimates made by a trained breast-imaging radiologist. Results: Strong association between algorithm-estimated and radiologist-provided breast PD% was detected for both raw (r = 0.82, p < 0.001) and processed (r = 0.85, p < 0.001) digital mammograms on a per-breast basis. Stronger agreement was found when overall breast density was assessed on a per-woman basis for both raw (r = 0.85, p < 0.001) and processed (0.89, p < 0.001) mammograms. Strong agreement between categorical density estimates was also seen (weighted Cohen's κ ≥ 0.79). Repeated measures analysis of variance demonstrated no statistically significant differences between the PD% estimates (p > 0.1) due to either presentation of the image (raw vs processed) or method of PD% assessment (ra...

Parenchymal texture analysis in digital mammography: A fully automated pipeline for breast cancer risk assessment

“…33,34 First, the pipeline performs preprocessing steps to segment the breast region followed by z-score normalization of the gray-level intensity values within the segmented breast. Subsequently, breast PD% is estimated using a previously validated automated technique 18 and a set of lattice-based parenchymal texture features is extracted. A logistic regression classifier is then trained using cross validation, by selecting features that most significantly contribute to case-control classification (Fig.…”

“…recently developed method, validated for digital mammography. 18 Specifically, an adaptive multiclass fuzzy c-means clustering algorithm is applied to partition the breast area into a set of subregions with similar image intensity properties. Then, a linear support vector machine classifier labels each of these detected subregions as either being composed primarily of dense tissue or fat.…”

“…The breast region is first segmented using a previously validated algorithm 18 prior to any subsequent texture analysis. Briefly, the air-breast boundary is delineated using automated thresholding.…”

“…Briefly, the air-breast boundary is delineated using automated thresholding. 18 Then, for medio-lateral oblique (MLO) images, the region of the pectoral muscle is removed by identifying its boundary using a straight line Hough transform. Zscore normalization 18 is further applied within the segmented breast region, to standardize gray-level intensity range for all images across subjects.…”

“…15 It can be evaluated via visual categorical assessment, 14 such as by using the Boyd or ACR-BIRADS scale, or by using computer-aided methods to estimate a continuous measure of breast PD%. [16][17][18][19][20] Given that the distribution of dense tissue within the breast is not uniform, there is increasing interest in also measuring the heterogeneity of the parenchymal pattern ( Fig. 1) in more granular ways than the global assessment of breast PD%.…”