baidu-research/NCRF

Can you explain how the code calculates the FROC score?

Closed this issue · 2 comments

alibalapour commented

I want to plot and calculate FROC for 3 WSIs (Test_001, Test_065, and Test_079 from Camelyon16), but the result is nan. I can't understand how do you calculate FROC.
We have a CSV file that shows coordinates and probabilities of tumors generated by the model and ground truth mask. Is this ground truth mask have a particular property?
What are the values of the ground truth mask? 0 or 1?
What is ITC_labels in Evaluation_FROC.py?
How do you generate a ground truth mask of WSI from annotations? Is there a particular way or the same as the way provided by ASAP?

tree1rain commented

Open tumor slide image with ASAP.
Load the annotation file in .xml format.
Save.

  • 👍1
tree1rain commented

ASAP Save -> *.tif -> assign labels to annotation groups -> (tumor: 1), (Exclusion: 0), (_0: 1), (_1: 1), (_2: 0)
filled_image = nd.morphology.binary_fill_holes(binary)
this line of code will fill in the hole, so there is no difference between (Exclusion: 0) and (Exclusion: 1)
Evaluation_FROC.py -> computeEvaluationMask -> distance = nd.distance_transform_edt(255 - pixelarray[:,:,0]*255)

  • 👍1