Nuclei-Segmentation

This repository contains an implementation of Mask R-CNN algorithm using Matterport library for nuclei segmentation from whole slide images of tissue sections.

Description: Nuclei segmentation using Mask R-CNN based on the ResNet 50 backbone.

This model was trained using data from our IEEE TMI paper and MoNuSeg challenge.

Please cite the following papers if you use this code or data for your work-

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

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

Feel free to use the testing script with available model weights to check the performance of trained model using the following links-

Testing code

Trained weights