Detecting Synapse Location and Connectivity by Signed Proximity Estimation and Pruning with Deep Nets

Abstract

Synaptic connectivity detection is a critical task for neural reconstruction from Electron Microscopy (EM) data. Most of the existing algorithms for synapse detection do not identify the cleft location and direction of connectivity simultaneously. The few methods that computes direction along with contact location have only been demonstrated to work on either dyadic (most common in vertebrate brain) or polyadic (found in fruit fly brain) synapses, but not on both types. In this paper, we present an algorithm to automatically predict the location as well as the direction of both dyadic and polyadic synapses. The proposed algorithm first generates candidate synaptic connections from voxelwise predictions of signed proximity generated by a 3D U-net. A second 3D CNN then prunes the set of candidates to produce the final detection of cleft and connectivity orientation. Experimental results demonstrate that the proposed method outperforms the existing methods for determining synapses in both rodent and fruit fly brain 1 .

Automated Synapse Detection Method for Cerebellar Connectomics

“…The method has a few limitations, too. First, the reconstruction is a prerequisite ( Staffler et al, 2017 ; Parag et al, 2018 ; Buhmann et al, 2021 ). Other methods are needed if a researcher wants to reconstruct only a few neurons first, find their synapses, and then backward trace the synaptic partners of the first neurons from the synapses.…”

A large-scale volumetric correlated light and electron microscopy study localizes Alzheimer’s disease-related molecules in the hippocampus

“…Although manual annotation to analyze synapses is straightforward, it is not ideal for analysis of their density as a function of proximity to a plaque, given their large number. We thus used machine-learning-based automated synapse detection (Buhmann et al, 2021;Çiçek et al, 2016;Lin et al, 2021;Parag et al, 2019;Santurkar et al, 2017;Staffler et al, 2017;Su et al, 2023), which has been performed on large-scale connectomics datasets (Scheffer et al, 2020;Shapson-Coe et al, 2021;Turner et al, 2022) and proved to be time-efficient, unbiased and accurate.…”

Convolutional nets for reconstructing neural circuits from brain images acquired by serial section electron microscopy

“…A number of approaches are used to find the partner neurons at a synaptic cleft [64,66,58,67,70]. For example, Dorkenwald et al [58] extract features relating the predicted cleft segments to candidate partners by overlap with these partners, as well as their contact site, and feed these features to a random forest classifier for a final "synaptic" or "non-synaptic" classification for inferring connectivity.…”

“…For example, Dorkenwald et al [58] extract features relating the predicted cleft segments to candidate partners by overlap with these partners, as well as their contact site, and feed these features to a random forest classifier for a final "synaptic" or "non-synaptic" classification for inferring connectivity. Parag et al [70] pass a candidate cleft, local image context, and a candidate pair of partner segments to a convolutional net to make a similar "synaptic" or "non-synaptic" judgment. Turner et al [71] use a similar model, yet they instead use the cleft as an attentional input to predict the voxels of relevant presynaptic and postsynaptic partners.…”