Multiple Nuclei HeLa cell ground truth images with four labels (nuclear envelope, nucleus, rest of the cell, and background) for deep learning architecture training.

This is a data set that contains labelled HeLa cell images, indicating the four different classes - nuclear envelope, nucleus, rest of the cell, and background. Similar ground truth have been published for this data set, but in this case, multiple nuclei have been labelled, whilst previous ones only focused on the central cell (https://doi.org/10.5281/zenodo.3874949)

Details of the imaging, preparation and segmentation have been published in:

Cefa Karabağ, Martin L. Jones, Christopher J. Peddie, Anne E. Weston, Lucy M. Collinson, Constantino Carlos Reyes-Aldasoro. Segmentation and Modelling of the Nuclear Envelope of HeLa Cells Imaged with Serial Block Face Scanning Electron Microscopy. J. Imaging 2019, 5(9), 75; https://doi.org/10.3390/jimaging5090075

Cefa Karabağ, Martin L. Jones, Christopher J. Peddie, Anne E. Weston, Lucy M. Collinson, Constantino Carlos Reyes-Aldasoro. Semantic segmentation of HeLa cells: An objective comparison between one traditional algorithm and four deep-learning architectures, PLOS ONE, 2020;  https://doi.org/10.1371/journal.pone.0230605

Cefa Karabağ, Martin L. Jones, Constantino Carlos Reyes-Aldasoro, Segmentation of the Plasma Membrane of HeLa Cells, J. Imaging 2021, 7(6), 93; https://doi.org/10.3390/jimaging7060093

The data sets are freely available through EMPIAR: http://dx.doi.org/10.6019/EMPIAR-10094 EMPIAR.