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
Sample digital mammograms of BIRADS categories I–IV digital mammograms in order of increasing percent density. (I) <25%; (II) 26%–50%; (III) 51%–75%; (IV) >75%.
Flowchart of the proposed algorithm.
Comparison of gray-level intensity distributions of the breast region in “For Processing” (i.e., “Raw,” images a and b), histogram equalized raw (i.e., images c and d) and “For Presentation” (i.e., “Processed”; images e and f) digital mammograms of a BIRADS III category woman.
Illustration of adaptive air threshold detection on a digital mammogram with nonzero air pixels. (Left) Histogram showing the location of the first major rise in gray-level values, E, (long-dashed line) and the computed air threshold, th, (short-dashed). (Right) Identified breast-air interface contour (white line).
Effect of gray-level histogram smoothing. (Left) Original mammogram with breast area outlined in white, (Center) Z-score normalized gray-level intensity histogram constructed at a 0.01 bin-width, (Right) Histogram postsmoothing with a Gaussian kernel of width = 50, alpha = 5.
Segmentation algorithm for a k = 6 mammogram. (a) Original mammogram; (b) normalized, smoothed breast-pixel intensity histogram with FCM cluster centroids (vertical lines); (c) pixel cluster-membership represented by shading; (d) final dense tissue segmentation combining clusters 5–6.
Scatter plots of per-breast (top row) and per-woman (bottom row) algorithm-estimated (x axis) and radiologist-provided (y axis) PD% for raw (left column) and processed (right column) DM image sets. Regression (solid) and unity (dashed) lines are provided for reference.
Distributions of per-breast (left) and per-woman (right) assessed PD% as a function of image presentation and assessment-method. Two-way ANOVA indicated no significant groupwise differences (p > 0.1).
Per-breast (top) and per-woman (bottom) box-plots of algorithm-estimated PD% in raw (left) and processed (right) DM images vs radiologist-provided categorical ACR BIRADS density scores. BIRADS categories were assigned using the standard thresholds on continuous PD%: (I) < 25%; (II) 25%–50%; (III) 51%–75%; (IV) >75%.
Cross-validation performance as a function of histogram-construction parameters (i.e., bin width, b, Gaussian kernel width, w, and kernel variance, α) for raw (top) and processed (bottom) digital mammograms.
Distribution of assigned BIRADs density categories for raw and processed DM images.
Features with a 90%+ selection rate in the (a) raw and (b) processed mammogram datasets.
Repeated Measures ANOVA Tables for per-breast (Top) and per-woman (Bottom) estimation of breast PD%. No systematic difference due to presentation type (raw vs processed) or method of estimation (radiologist vs algorithm) was found, even if interaction was considered (p > 0.1).
Categorical agreement assessed using quadratic-weighted Cohen's κ between radiologist and algorithm computed BIRAD density. Strong agreement (κ ≥0.79; p < 0.001) is seen between the two categorical estimates when assessed either per woman or per breast for both raw and processed images. The κ values and 95% confidence intervals are reported.
Article metrics loading...
Full text loading...