Skip to main content

CRCHistoPhenotypes - Labeled Cell Nuclei Data

Description of the Dataset

This dataset involves 100 H&E stained histology images of colorectal adenocarcinomas. A total of 29,756 nuclei were marked at/around the center for detection purposes. Out of these, there were 22,444 nuclei that also have an associated class label, i.e. epithelial, inflammatory, fibroblast, and miscellaneous. Full details of the dataset can be found in the following paper:

  • K. Sirinukunwattana, S.E.A. Raza, Y.W Tsang, I.A. Cree, D.R.J. Snead, N.M. Rajpoot, ‘Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images,’ IEEE Transactions on Medical Imaging, 2016 (in press) [PDF]

Each image is contained in a separate folder, and the ground truth data for nucleus detection and classification are provided as nuclear coordinates in ‘.mat’ (MATLAB).


Usage Terms and Conditions

This dataset is released for research purpose only. By using this dataset in your research, you agree to cite the following paper in any research output generated from using this dataset:

  • K. Sirinukunwattana, S.E.A. Raza, Y.W Tsang, I.A. Cree, D.R.J. Snead, N.M. Rajpoot, ‘Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images,’ IEEE Transactions on Medical Imaging, 2016 (in press) [PDF]

Contact

If you have any comments or questions about this dataset, please feel free to drop an email at K.Sirinukunwattana@warwick.ac.uk or N.M.Rajpoot@warwick.ac.uk


Download

CRCHistoPhenotypes(v0.2)