How to get the picture in Figure 5 Red lines denote the ground truth.

wentaozhu / adversarial-deep-structural-networks

ISBI2018: Adversarial Deep Structural Networks for Mammographic Mass Segmentation https://arxiv.org/abs/1612.05970

Apache License 2.0

51 stars 25 forks source link

Closed c1a1o1 closed 6 years ago

c1a1o1 commented 6 years ago

How to get the picture in Figure 5 Red lines denote the ground truth.?

wentaozhu commented 6 years ago

First get the predicted probability as fchollet/keras#41 . Then use matlab "bwperim", you can get the perimeter of objects in binary image.

c1a1o1 commented 6 years ago

thanks for your help!