search

ysbecca / py-wsi

Python package for dealing with whole slide images (.svs) for machine learning, particularly for fast prototyping. Includes patch sampling and storing using OpenSlide. Patches may be stored in LMDB, HDF5 files, or to disk. It is highly recommended to fork and download this repository so that personal customisations can be made for your work.
https://ysbecca.github.io/programming/2018/05/22/py-wsi.html
GNU General Public License v3.0
161 stars 93 forks source link

Slides are not annotated #37

Open tayyaba69 opened 4 years ago

tayyaba69 commented 4 years ago

In dataset I have XML file which is only for the reference and is not the ground truth. Binary pixel masks is provided as TIF files are the ground truth. That is why there is a difference in label map. Can you suggest any solution to this problem? Thankyou

ysbecca commented 3 years ago

@tayyaba69 Apologies for the extremely delayed response to this. You could either generate the XML file for your pixel masks and use py-wsi out of the box, but it would perhaps be easier to just alter the py-wsi code to read in the pixel masks. Actually, py-wsi reads in the XMLs and generates downsampled (smaller size for faster processing) binary masks, to label image patches.