Synaptic Partner Assignment Using Attentional Voxel Association Networks
This work addresses the challenge of mapping neural connections in connectomics, which is incremental as it builds on existing methods for synapse location by focusing on partner identification.
The paper tackles the problem of identifying synaptic partners in connectomics by directly generating masks of presynaptic and postsynaptic partners from a given cleft mask using a convolutional network with attentional gating. The approach performs well on a mouse somatosensory cortex dataset and is evaluated in a combined system for predicting clefts and connections.
Connectomics aims to recover a complete set of synaptic connections within a dataset imaged by volume electron microscopy. Many systems have been proposed for locating synapses, and recent research has included a way to identify the synaptic partners that communicate at a synaptic cleft. We re-frame the problem of identifying synaptic partners as directly generating the mask of the synaptic partners from a given cleft. We train a convolutional network to perform this task. The network takes the local image context and a binary mask representing a single cleft as input. It is trained to produce two binary output masks: one which labels the voxels of the presynaptic partner within the input image, and another similar labeling for the postsynaptic partner. The cleft mask acts as an attentional gating signal for the network. We find that an implementation of this approach performs well on a dataset of mouse somatosensory cortex, and evaluate it as part of a combined system to predict both clefts and connections.