Skip to main content
Fig. 1 | Visual Computing for Industry, Biomedicine, and Art

Fig. 1

From: 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

Fig. 1

A. Workflow of the image processing steps for the registration breast segmentation method; B. The step-by-step results of the image processing. (a) Edge-enhanced fat-water-sum image after Canny edge detection method, (b) outcome of the Otsu thresholding, (c) mask after morphological operations, (d) body region extracted by applying the mask, and (e1) and (e2) single-sided breasts generated from D by cutting the breasts in the middle and flipping the left side to the right

Back to article page