MoNuSeg grand-challenge organized at MICCAI 2018

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|

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