GlaS@MICCAI’2015: Gland Segmentation is a dataset for instance segmentation, semantic segmentation, and object detection tasks. It is used in the medical industry, and in the medical research.

The dataset consists of 165 images with 1530 labeled objects belonging to 1 single class (gland).

Images in the GlaS@MICCAI’2015: Gland Segmentation dataset have pixel-level instance segmentation annotations. Due to the nature of the instance segmentation task, it can be automatically transformed into a semantic segmentation (only one mask for every class) or object detection (bounding boxes for every object) tasks. All images are labeled (i.e. with annotations). There are 3 splits in the dataset: train (85 images), test_a (60 images), and test_b (20 images). Also, the dataset contains patient_id, grade_sirinukunwattana and malignant/benign tags. The dataset was released in 2015 by the University of Warwick, Eindhoven University of Technology, The Chinese University of Hong Kong, University of Central Lancashire, University of Freiburg, ExB Research and Development, Biomedical Imaging Laboratory (LIB), Medical University of Graz, University of Zurich and ETH Zurich, Graz University of Technology, Ludwig Boltzmann Institute for Clinical Forensic Imaging, and University Hospitals Coventry and Warwickshire.

Data Usage

The dataset used in this competition is provided for research purposes only. Commercial uses are not allowed.

If you intend to publish research work that uses this dataset, you must cite our review paper to be published after the competition

K. Sirinukunwattana, J. P. W. Pluim, H. Chen, X Qi, P. Heng, Y. Guo, L. Wang, B. J. Matuszewski, E. Bruni, U. Sanchez, A. Böhm, O. Ronneberger, B. Ben Cheikh, D. Racoceanu, P. Kainz, M. Pfeiffer, M. Urschler, D. R. J. Snead, N. M. Rajpoot
"Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest"
http://arxiv.org/abs/1603.00275 [Preprint]

The details of the journal version will be available soon.

AND the following paper, wherein the same dataset was first used:

K. Sirinukunwattana, D.R.J. Snead, N.M. Rajpoot,
"A Stochastic Polygons Model for Glandular Structures in Colon Histology Images," in IEEE Transactions on Medical Imaging, 2015
doi: 10.1109/TMI.2015.2433900

Source

If you make use of the GlaS@MICCAI’2015: Gland Segmentation data, please cite the following reference:

@misc{sirinukunwattana2016gland,
  title={Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest}, 
  author={Korsuk Sirinukunwattana and Josien P. W. Pluim and Hao Chen and Xiaojuan Qi and Pheng-Ann Heng and Yun Bo Guo and Li Yang Wang and Bogdan J. Matuszewski and Elia Bruni and Urko Sanchez and Anton Böhm and Olaf Ronneberger and Bassem Ben Cheikh and Daniel Racoceanu and Philipp Kainz and Michael Pfeiffer and Martin Urschler and David R. J. Snead and Nasir M. Rajpoot},
  year={2016},
  eprint={1603.00275},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

Source

Dataset GlaS@MICCAI’2015: Gland Segmentation can be downloaded in Supervisely format:

As an alternative, it can be downloaded with dataset-tools package:

pip install --upgrade dataset-tools

… using following python code:

import dataset_tools as dtools

dtools.download(dataset='GlaS@MICCAI'2015: Gland Segmentation', dst_dir='~/dataset-ninja/')

Make sure not to overlook the python code example available on the Supervisely Developer Portal. It will give you a clear idea of how to effortlessly work with the downloaded dataset.

The data in original format can be downloaded here.