Two fully automated data-driven 3D whole-breast segmentation strategies in MRI for MR-based breast density using image registration and U-Net with a focus on reproducibility

Visual Computing for Industry, Biomedicine, and Art

Table 1 Summary characteristics of the data used in different subsets

	Dictionary set	Deep learning set	Test-retest set
Purpose	To develop the template dictionary for the registration breast segmentation	To develop the deep learning network for the breast segmentation	To evaluate the test-retest reproducibility of MagDensity derived using available segmentation methods
Scanner	B, P	B, P, S	B, P
Data set	Sulindac	Sulindac and metformin	Sulindac