Automated Detection and Segmentation of Synaptic Contacts in Nearly Isotropic Serial Electron Microscopy Images

Anna Kreshuk,Ullrich Koethe,Christoph Sommer,Marco Cantoni,Christoph N Straehle,Graham Knott,Fred A Hamprecht,Steven Barnes

doi:10.1371/journal.pone.0024899

Abstract

We describe a protocol for fully automated detection and segmentation of asymmetric, presumed excitatory, synapses in serial electron microscopy images of the adult mammalian cerebral cortex, taken with the focused ion beam, scanning electron microscope (FIB/SEM). The procedure is based on interactive machine learning and only requires a few labeled synapses for training. The statistical learning is performed on geometrical features of 3D neighborhoods of each voxel and can fully exploit the high z-resolution of the data. On a quantitative validation dataset of 111 synapses in 409 images of 1948×1342 pixels with manual annotations by three independent experts the error rate of the algorithm was found to be comparable to that of the experts (0.92 recall at 0.89 precision). Our software offers a convenient interface for labeling the training data and the possibility to visualize and proofread the results in 3D. The source code, the test dataset and the ground truth annotation are freely available on the website http://www.ilastik.org/synapse-detection.

Highlights

The chemical synapse is the predominant means by which information is transferred and stored in the central nervous system
With serial section transmission electron microscopy, synaptic density can be estimated by manually counting synapses within a large volume, or by stereological extrapolation from paired 2D images [1,2,3,4]
The recent introduction of focused ion beam/scanning electron microscopy (FIB/SEM)[6] with isotropic resolution approaching 5 nm has opened the door to a direct detection and segmentation of all synapses in large volumes of tissue, without the need to resort to extrapolation from paired slices

Summary

Introduction

The chemical synapse is the predominant means by which information is transferred and stored in the central nervous system. With serial section transmission electron microscopy (ssTEM), synaptic density can be estimated by manually counting synapses within a large volume, or by stereological extrapolation from paired 2D images [1,2,3,4]. The recent introduction of focused ion beam/scanning electron microscopy (FIB/SEM)[6] with isotropic resolution approaching 5 nm has opened the door to a direct detection and segmentation of all synapses in large volumes of tissue, without the need to resort to extrapolation from paired slices. A protocol for manual synapse detection in FIB/SEM data has recently been proposed in [7]. Even for the best quality EM images, manual detection of synapses remains a difficult, error-prone and time-consuming task, which calls for automated protocols to overcome the tedium of manual analysis

Methods

Results

Conclusion