A guide to CNN-based dense segmentation of neuronal EM images

Large-scale reconstitution of neuronal circuits from volumetric electron microscopy images is a remarkable research goal in neuroanatomy. However, the large-scale reconstruction is a result of automatic segmentation using convolutional neural networks (CNNs), which is still challenging for general researchers to perform. This review focuses on two representative CNNs for dense neuronal segmentation: flood-filling networks (FFNs) and local shape descriptors (LSDs)-predicting U-Net (LSD network). It outlines their basic mechanisms, requirements, and output segmentation using the author's example segmentation. The FFN excels in segmenting long axons, and the LSD network is adept at segmenting myelinated axons. The choice between FFN and LSD depends on the target, as neither is universally superior. A common limitation of FFN and LSD is the easy detachment of thin spines from parent dendrites, which is fundamentally unavoidable. The author also introduces CNNs that were proposed to mitigate this issue. As CNN-based automated segmentation can take months, researchers need to be aware of the selection of an appropriate CNN, required computer resources and fundamental limitations. This review serves as a guide for such dense neuronal segmentation.