Skip to content

yuerua/HE_Tissue_Segmentation

 
 

Repository files navigation

UNMaSk: Unmasking the immune microecology of ductal carcinoma in situ with deep learning.

Overview schematic of UNMaSk pipeline for DCIS segmentation.

Schematic of IM-Net architecture for DCIS segmentation and schematic of DRDIN cell detection network.

Training Data

Images used for training https://github.com/pathdata/HE_Tissue_Segmentation/tree/master/CIS/TrainData

Ground truth images https://github.com/pathdata/HE_Tissue_Segmentation/tree/master/CIS/TrainData/mask

Overlay of groundtruth on the training image https://github.com/pathdata/HE_Tissue_Segmentation/tree/master/CIS/TrainData/overlay

Illustrative images used in training IM-NET

Citation

Reference

All training data of carcinoma in situ regions that were annotated as a part of the project is made available in this github repository. Training data tiles were anonymised from raw HE image tiles. Request for data access for the Duke samples can be submitted to E.S.H and Y.Y

Training

Data preparation and implementation codes are maintained in this repository and will be periodically updated. Please contact the corresponding authours for future collaboration and any queries regarding the implementation.

About

tissue segmentation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 69.5%
  • MATLAB 24.3%
  • C 5.3%
  • Other 0.9%