This page shares the results of corneal endothelial image segmentation using the U-Net-based convolutional neural network.
The original dataset of corneal endothelial images used in this study was described and made available by Yann Gavet and Jean-Charles Pinoli in their work:
Gavet Y., Pinoli J.-C.: Comparison and Supervised Learning of Segmentation Methods Dedicated to Specular Microscope Images of Corneal Endothelium, International Journal of Biomedical Imaging, vol. 2014, Article ID 704791, 13 pages, 2014. doi:10.1155/2014/704791
The method used for corneal endothelial image segmentation whose results are available on this page was described in details in:
Fabijańska A.: Segmentation of Corneal Endothelium Images Using a U-Net-based Convolutional Neural Network, Artificial Intelligence in Medicine, 2018, vol. 88, pp. 1-13
The source code of this method is available in the following GitHub repository: https://github.com/afabijanska/CornealEndothelium/
It is requested that any published material reporting results using data from this dataset acknowledges it by quoting the following publication:
Fabijańska A.: Segmentation of Corneal Endothelium Images Using a U-Net-based Convolutional Neural Network, Artificial Intelligence in Medicine, 2018, vol. 88, pp. 1-13
Link, BibTEX
Optional, but also interesting:
Fabijańska A.: Corneal endothelium image segmentation using feedforward neural network, 2017 Federated Conference on Computer Science and Information Systems (FedCSIS), Prague, 2017, pp. 629-637
Link, BibTEX
Fabijańska A.: Automatic segmentation of corneal endothelial cells from microscopy images, Biomedical Signal Processing and Control, 2019, vol. 47C, pp. 145-158
Link, BibTEX
