Semi automatically generated nuclei instance segmentation and classification dataset with exhaustive nuclei labels across 19 different tissue types. The dataset consists of 481 visual fields, of which 312 are randomly sampled from more than 20K whole slide images at different magnifications, from multiple data sources. In total the dataset contains 205,343 labeled nuclei, each with an instance segmentation mask. Models trained on pannuke can aid in whole slide image tissue type segmentation, and generalise to new tissues. PanNuke demonstrates one of the first succesfully semi-automatically generated datasets.

Data Format

Samples from exhaustively annotated PanNuke dataset, that contains image patches from 19 tissue types for nuclei instance segmentation and classification (Red: Neoplastic; Green: Inflammatory; Dark Blue: Connective; Yellow: Dead; Orange: Epithelial)

Nuclei Type Statistics

A comparative plot of class distributions per tissue. Numbers in parenthesis represent the total number of nuclei within that category or tissue type.

Citation

@inproceedings{gamper2019pannuke,
  title={PanNuke: an open pan-cancer histology dataset for nuclei instance segmentation and
classification},
  author={Gamper, Jevgenij and Koohbanani, Navid Alemi and Benet, Ksenija
and Khuram, Ali and Rajpoot, Nasir},
  booktitle={European Congress on Digital Pathology},
  pages={11--19},
  year={2019},
  organization={Springer}
}

@article{gamper2020pannuke,
  title={PanNuke Dataset Extension, Insights and baselines},
  author={Gamper, Jevgenij and Koohbanani, Navid Alemi
and Graham, Simon and Jahanifar, Mostafa and Khurram, Syed Ali and Azam, Ayesha and Hewitt,
Katherine and Rajpoot, Nasir},
  journal={arXiv preprint arXiv:2003.10778},
  year={2020}
}