Synaptic Cleft Segmentation in Non-Isotropic Volume Electron Microscopy of the Complete Drosophila Brain

TL;DR

This paper introduces a novel 3D-U-Net model for synaptic cleft segmentation in non-isotropic volume electron microscopy data, achieving significant improvements and enabling large-scale brain analysis.

Contribution

The authors designed a new 3D-U-Net architecture optimized for non-isotropic data and developed open source software for large-scale synaptic cleft prediction.

Findings

Significant improvement over state-of-the-art methods.

Successful application to a 50 teravoxel Drosophila brain dataset.

Model generalizes well to unseen brain regions.

Abstract

Neural circuit reconstruction at single synapse resolution is increasingly recognized as crucially important to decipher the function of biological nervous systems. Volume electron microscopy in serial transmission or scanning mode has been demonstrated to provide the necessary resolution to segment or trace all neurites and to annotate all synaptic connections. Automatic annotation of synaptic connections has been done successfully in near isotropic electron microscopy of vertebrate model organisms. Results on non-isotropic data in insect models, however, are not yet on par with human annotation. We designed a new 3D-U-Net architecture to optimally represent isotropic fields of view in non-isotropic data. We used regression on a signed distance transform of manually annotated synaptic clefts of the CREMI challenge dataset to train this model and observed significant improvement over the state of the art. We developed open source software for optimized parallel prediction on very large volumetric datasets and applied our model to predict synaptic clefts in a 50 tera-voxels dataset of the complete Drosophila brain. Our model generalizes well to areas far away from where training data was available.