Figure 4:

Manual and automated segmentations of breast cancer. (A) Inputs to the model consisting of the first postcontrast image (T1c), postcontrast minus precontrast image (T1) (DCE-in), and washout (DCE-out), with an independent reference for radiologist 4 (R4) made from the intersection of radiologists 1–3 (R1–R3 [Ref4]) and the network output (M Probs) indicating probability that a voxel is cancer (green = low; red = high). (B) Example segmentation from all four radiologists (R1–R4) for a given section, and the model segmentation created by thresholding probabilities (M). Dice scores for R4 and M were computed using Ref4 as the target. (C) Zooming in on the areas outlined in yellow in B, showing the boundaries of segmentations for the machine as well as human-generated segmentations as drawn on the screen by R1–R4.