Skip to content

This repository contains my implementations of the algorithms which we used for evaluation of the MoNuSeg challenge at MICCAI 2018.

Notifications You must be signed in to change notification settings

ruchikaverma-iitg/MoNuSeg

Repository files navigation

Please cite the following papers if you use this repository-

Kumar, N., Verma R. et al., "A Multi-organ Nucleus Segmentation Challenge," in IEEE Transactions on Medical Imaging 2019

Kumar, N., Verma, R., Sharma, S., Bhargava, S., Vahadane, A., & Sethi, A. (2017). A dataset and a technique for generalized nuclear segmentation for computational pathology. IEEE transactions on medical imaging, 36(7), 1550-1560

File name Description
Aggregated_Jaccard_Index_v1_0 Compute average AJI across all nuclei for each image
compute_AJI Compute average AJI (across all nuclei) per image for each participant
Ensemble_mask Combine instance masks of top 5 techniques to get ensemble mask using majority voting
correct_nd_missing_nuc_count Count correctly classified nuclei and missing nuclei in each predicted mask of top 5 techniques
he_to_binary_mask_final Use H&E stained image along with associated xml file to generate binary and colored mask
Nuclei-Segmentation An implementation of Mask R-CNN algorithm for nuclei segmentation

An implementation of Mask R-CNN algorithm using Matterport library for nuclei segmentation from whole slide images of tissue sections can be found from the links given below:

Testing code

Trained weights

About

This repository contains my implementations of the algorithms which we used for evaluation of the MoNuSeg challenge at MICCAI 2018.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages