Automatic Detection of Synaptic Partners in a Whole-BrainDrosophilaEM Dataset

Abstract

The study of neural circuits requires the reconstruction of neurons and the identification of synaptic connections between them. To scale the reconstruction to the size of whole-brain datasets, semi-automatic methods are needed to solve those tasks. Here, we present an automatic method for synaptic partner identification in insect brains, which uses convolutional neural networks to identify post-synaptic sites and their pre-synaptic partners. The networks can be trained from human generated point annotations alone and require only simple post-processing to obtain final predictions. We used our method to extract 244 million putative synaptic partners in the fifty-teravoxel full adult fly brain (FAFB) electron microscopy (EM) dataset and evaluated its accuracy on 146,643 synapses from 702 neurons with a total cable length of 312 mm in four different brain regions. The predicted synaptic connections can be used together with a neuron segmentation to infer a connectivity graph with high accuracy: between 92% and 96% of edges linking connected neurons are correctly classified as weakly connected (less than five synapses) and strongly connected (at least five synapses). Our synaptic partner predictions for the FAFB dataset are publicly available, together with a query library allowing automatic retrieval of up-and downstream neurons.

A Connectome and Analysis of the AdultDrosophilaCentral Brain

“…The Janelia Facilities group was essential in proving a stable environment for image collection. We thank Julia Buhmann and Jan Funke for help in implementing the synapse prediction algorithm described in ( Buhmann et al, 2019 ). Many colleagues at Janelia as well as Marta Costa, Greg Jefferis and others in Cambridge tested the performance of Neuprint performance prior to its release.…”

“…Given the size of the hemibrain image volume, a major challenge from a machine learning perspective is the range of varying image statistics across the volume. In particular, model performance can quickly degrade in regions of the data set with statistics that are not well-captured by the training set( Buhmann et al, 2019 ). To address this challenge, we took an iterative approach to synapse prediction, interleaving model re-training with manual proofreading, all based on previously reported methods( Huang et al, 2018 ).…”

A Connectome of the AdultDrosophilaCentral Brain

“…A major challenge from a machine learning perspective is the range of varying image statistics across the volume. In particular, model performance can quickly degrade in regions of the data set whose statistics are not well-captured by the training set [28]. To address this challenge, we took an iterative approach to synapse prediction, interleaving model re-training with manual proofreading, all based on the methods of [29].…”

“…As an independent check on synapse quality, we also trained a separate classifier proposed in [28], using an enhanced version of the 'synful' software package. Both synapse predictors also give a confidence value for each synapse, a measure of how firmly the classifier believes the found feature is a true synapse.…”

“…The Janelia Facilities group was essential in proving a stable environment for image collection. We thank Julia Buhmann and Jan Funke for help in implementing the synapse prediction algorithm described in [28]. Many colleagues at Janelia as well as Marta Costa, Greg Jefferis and others in Cambridge tested Neuprint performance prior to release.…”