PSF Estimation and deconvolution: models, microscopy images, and datasets

<p>This is the accompanying dataset for the publication Adrian Shajkofci, Michael Liebling, &ldquo;Spatially-Variant CNN-Based Point Spread Function Estimation for Blind Deconvolution and Depth Estimation in Optical Microscopy,&rdquo; IEEE Transactions on Image Processing, vol. 29, pp. 5848-5861, 2020.</p> <p>Publications based on this data must cite the above paper.<br> <br> BibTeX Citation:<br> @ARTICLE{shajkofci.liebling:20,<br> &nbsp; author={A. Shajkofci and M. Liebling},<br> &nbsp; journal={IEEE Trans. Image Proces.},&nbsp;<br> &nbsp; title={Spatially-Variant {CNN}-Based Point Spread Function Estimation for Blind Deconvolution and Depth Estimation in Optical Microscopy},<br> &nbsp; year={2020},<br> &nbsp; volume={29},<br> &nbsp; number={},<br> &nbsp; pages={5848-5861},<br> &nbsp; doi={10.1109/TIP.2020.2986880}}<br> &nbsp;</p> <p>In the archive, you will find&nbsp;:</p> <ul> <li>- Trained models for PSF estimation and deconvolution</li> <li>- Synthetic training dataset of cells and beads</li> <li>- Stacks of multi-channel fluorescence microscopy images of HeLa cells, rat brain cells, beads and plant cells to test the PSF estimation tool, deconvolution algorithm or auto-focus algorithm.</li> <li>- Stacks of tilted grid (3, 6 and 9 degrees) using astigmatic lenses for depth estimation.<br> &nbsp;</li> </ul> <p>The code for running the models is available here:<br> <a href="https://github.com/idiap/psfestimation">https://github.com/idiap/psfestimation</a></p> <p><br> <strong>Reference paper</strong></p> <p>A. Shajkofci and M. Liebling, &quot;Spatially-Variant CNN-Based Point Spread Function Estimation for Blind Deconvolution and Depth Estimation in Optical Microscopy,&quot; in IEEE Transactions on Image Processing, vol. 29, pp. 5848-5861, 2020, doi: 10.1109/TIP.2020.2986880.</p> <p>&nbsp;</p> <p><strong>Ethical compliance</strong></p> <p>The post-mortem stained and fixed tissue slices whose images are included in this data set were reused from experiments approved by the EPFL ethics committee.</p> <p>&nbsp;</p> <p><strong>Funding</strong></p> <p>This work was supported by the Swiss National Science Foundation under Grants 206021_164022 &ldquo;Platform for Reproducible Acquisition, Processing, and Sharing of Dynamic, Multi-Modal Data&rdquo; and 200020_179217 &ldquo;COMPBIO: Computational biomicroscopy: advanced image processing methods to quantify live biological systems&rdquo;</p>