/Deep-Z

Three-dimensional propagation and time-reversal of fluorescence images

Deep-Z: Three-dimensional propagation and time-reversal of fluorescence images

Neural network learns fluorescence wave propagation and time-reversal to propagate a 2D fluorescence image onto user-defined 3D surfaces, enabling 3D imaging of fluorescent samples using a single 2D image, without mechanical scanning, additional hardware, or a trade-off of resolution or speed. For details, refer to our publication "Three-dimensional propagation and time-reversal of fluorescence images" [1]. (Video below: 3D reconstruction of a C. elegans using Deep-Z inference) Video

Test a inference model

Download the model and plug-in from google drive http://bit.ly/deep-z (download the whole folder, ~ 2 GB). Then follow the guide "User Guide_v1.3". The provided version is for use with FIJI/imageJ on CPU only. A ready-to-use FIJI app is also provided in the download

Train your own model

The current version does not support code to train your own model.

Condition of use:

  1. This plugin is intended for research and non-commercial use only. You will be free to use this software for research purposes, but you cannot transmit and distribute it without our permission.
  2. We provide no warranties of any kind on this software and shall in no event be liable for damages of any kind in connection with the use and exploitation of this software. Your results may vary and can improve with our future release of this plug-in, but we do not guarantee the success of testing results.
  3. Please cite our publication [1] if the plugin is useful to your work. You are supposed to include a citation of [1] when you present or publish results that based on this plugin.

References:

[1] Wu, Yichen, Yair Rivenson, Hongda Wang, Yilin Luo, Eyal Ben-David, and Aydogan Ozcan. “Three-Dimensional Propagation and Time-Reversal of Fluorescence Images.” ArXiv:1901.11252 [Physics], January 31, 2019. http://arxiv.org/abs/1901.11252.

Release Note:

v1.1: 01/30/3019, stable plugin release.

v1.2: 02/23/2019, stable plugin release. Added image intensity evaluation to compensate for illumination variances for user images.

v1.3: 02/26/2019, stable plugin release. Used triangle threshold to separate sample and background to compensate for sample sparsity variances for user images.