1 Citation
Vessels predicted by the convolutional neural network 3DHEUnet, based on the U-net architecture with a regression loss (mean-squared error). Left: Network inputs (green: autofluorescence, blue: DAPI) with ground truth vessel location (red: isolectin fluorescence with manual correction). Right: Autofluorescence and DAPI signals (green, blue) with network prediction for vessel location (red). Vessels depicted in the right-sided image were predicted without any input from the isolectin fluorescent channel. White boxes indicate a few examples of accurately predicted vessels. Video is a fly-through of 2D slices acquired at different depth in a 3D volume.