Alternatively, the sample may be imaged with a scanning electron microscope, then the surface abraded using a focused ion beam, or trimmed using an in-microscope microtome.
Popular approaches are U-Net architectures to predict voxel-wise affinities paired with a watershed segmentation[7] and flood-filling networks.
[8] These approaches produce an over-segmentation which can be manually or automatically agglomerated to correctly represent a neuron.
Even for automatically agglomerated segmentations, large manual proofreading efforts are employed for highest accuracy.
[13] This mimics the infrastructure of genetics, where interactive query tools such as BLAST are normally used to look at genes of interest, which for most research comprise only a small portion of the genome.