Surface Projection (Drosophila wing, e-cadherin)
This work (method and data) is part of Content-aware image restoration: pushing the limits of fluorescence microscopy by Martin Weigert et al. in Nature Methods.
An extended CARE Network offers the possibility to reconstruct low SNR images and simultaneously projects only relevant intensities embedded in imaged volumes. It can be seen that our results are a considerable improved compared to the output of other state-of-the-art projection algorithms (here we compare to results obtained by Premosa).
The trained model is published for demonstration purposes. You can try it via Fiji and KNIME.
To run the demo in Fiji, follow these instructions.
To run the demo in KNIME, follow these instructions.
Results on the composite task of joint surface projection and denoising (on a developing D. melanogaster wing).
An intuitive way to assess the prediction uncertainty CARE networks predict in addition to predicting the restored images.