Expansion - Microtubules
Updated: Dec 6, 2022
This model enhances the spatial resolution of volumetric fluorescence microscopy images to simulate expansion microscopy (ExM) data. The model is well suited for enhancing spatial resolution of live cell imaging - which is incompatible with ExM. This model is trained using the 3D-RCAN architecture, developed in-house (read about it on BioRxiv [1]).
Post-expansion 3D volumetric images of fluorescently-labeled microtubules are captured on an instant structured illumination microscopy (iSIM) system with a 60x 1.2 NA water immersion objective. DAPI stain is used for estimating the expansion factor, which is 4x for the dataset. The post-expansion data is blurred with a modified PSF matched to the expansion factor with noise added to simulate pre-expansion data as input. The model is trained using image pairs of simulated input and post-expansion data.
Download
By downloading, installing, copying, accessing, or using the software, you agree to the terms of this end user license agreement.
Model file (.aiviadl)
Test image (.aivia.tif)
Requirements
Make sure you have Python versions 3.5 to 3.7 installed with TensorFlow-GPU version 1.13.0 and above.