Note that these images are saved as Numpy arrays, in order to be ready to use with our codebase. Please contact us if you would like original TIFF images.
These datasets are available for general use by academic or non-profit, or government-sponsored researchers. This license does not grant the right to use this dataset or any derivation of it for commercial activities. For more information, please contact us.
The code and its documentation are available on GitHub. It is available for general use by academic or non-profit, or government-sponsored researchers. This license does not grant the right to use this code or any derivation of it for commercial activities. For more information, please contact us. The codebase is divided into three main repositories:
All these repositories come with Dockerfiles defining working environments.
Pre-trained models can be found in the /trained_models subfolder of each repository. Note that by design, Kernel TS do not need pre-trained model.
Please email us to get access to the web demo.
Corresponding authors in italic. Please use info [(at)] optim-nanoscopy.net for any question or inquiry about the paper or the datasets.
Paul De Koninck
Deep learning team:
Marie-Ève Paquet for making the CaMKII-SNAPf plasmid, Giuseppe Vicidomini and Giorgio Tortarolo for support with FRC analysis, Renaud Bernatchez for the implementation of a rating application, Simon Labrecque for the widefield imaging dataset, Francine Nault, Laurence Emond and Charleen Salesse for the neuronal cell culture. This work was supported by Natural Sciences and Engineering Research Council of Canada, the Canadian Institute of Health Research (PJT-153107), the Fonds de Recherche Nature et Technologie du Québec, and Mitacs.