Table 2.

List of automated segmentation modules available for identifying tissue types, including an explanation of the parameters in each case.

Segmentation module	User-controlled parameters
Iterative hole filling	• Desired hole radius
	• Majority threshold—number of pixels $>50\%$ required to fill a pixel; this has to do with the curvature of target holes
	• Number of iterations
K-means classification and Markov random field	• Number of classes to identify as different regions (tissue types)
	• Error tolerance for clustering grayscale values into different classes
	• Degree of smoothness on the classified regions
	• Number of iterations
MR bias field correction	• Downsample factor—downsamples the image to improve computational time of bias correction
	• Number of iterations—three values controlling the computational time of a three-part process in bias correction
	• Spline distance—controls grid resolution, which will affect computational time
MR breast skin extraction	• Threshold below which tissue is considered to be skin/air
	• Radius of the morphological opening kernel for extracting the largest component of the image (the breast)
	• Number of iterations
	• Majority threshold—number of pixels $>50\%$ required to fill a pixel; this has to do with the curvature of the breast
	• Dilation radius—thickness of the skin
Thresholding	• Lower and upper thresholds—values between which grayscale values are classified as a region
Region dilation and erosion	• Dilation or erosion radius—amount by which to dilate or erode the region