A Dual Decoder U-Net-Based Model for Nuclei Instance Segmentation in Hematoxylin and Eosin-Stained Histological Images

This repository contains the architecture of our developed dual decoder model and other used models for nuclei instance segmentation in the following study:

Paper link: https://www.frontiersin.org/articles/10.3389/fmed.2022.978146/full (open access)

BibTex entry:

@article{dualdecoder2022,
title = "A Dual Decoder U-Net-Based Model for Nuclei Instance Segmentation in Hematoxylin and Eosin-Stained Histological Images",
journal = "Frontiers in Medicine",
volume = "",
pages = "",
year = "2022",
doi = "",
author = "Amirreza Mahbod and Gerald Schaefer and Georg Dorffner and Sepideh Hatamikia and Rupert Ecker and Isabella Ellinger"
}

Proposed dual decoder model scheme for nuclei instance segmentation:

Links to the used datasets in the study:

CryoNuSeg: https://www.kaggle.com/datasets/ipateam/segmentation-of-nuclei-in-cryosectioned-he-images
NuInsSeg: https://www.kaggle.com/datasets/ipateam/segmentation-of-nuclei-in-cryosectioned-he-images
MoNuSAC: https://monusac-2020.grand-challenge.org/

Acknowledgements

This work was supported by the Austrian Research Promotion Agency (FFG), No. 872636.