Focused Proofreading: Efficiently Extracting Connectomes from Segmented EM Images

09/03/2014
by   Stephen M. Plaza, et al.
0

Identifying complex neural circuitry from electron microscopic (EM) images may help unlock the mysteries of the brain. However, identifying this circuitry requires time-consuming, manual tracing (proofreading) due to the size and intricacy of these image datasets, thus limiting state-of-the-art analysis to very small brain regions. Potential avenues to improve scalability include automatic image segmentation and crowd sourcing, but current efforts have had limited success. In this paper, we propose a new strategy, focused proofreading, that works with automatic segmentation and aims to limit proofreading to the regions of a dataset that are most impactful to the resulting circuit. We then introduce a novel workflow, which exploits biological information such as synapses, and apply it to a large dataset in the fly optic lobe. With our techniques, we achieve significant tracing speedups of 3-5x without sacrificing the quality of the resulting circuit. Furthermore, our methodology makes the task of proofreading much more accessible and hence potentially enhances the effectiveness of crowd sourcing.

READ FULL TEXT

page 7

page 9

page 11

page 15

research
04/01/2016

Large-Scale Electron Microscopy Image Segmentation in Spark

The emerging field of connectomics aims to unlock the mysteries of the b...
research
08/31/2018

Understanding Neural Pathways in Zebrafish through Deep Learning and High Resolution Electron Microscope Data

The tracing of neural pathways through large volumes of image data is an...
research
04/11/2016

Fully-Automatic Synapse Prediction and Validation on a Large Data Set

Extracting a connectome from an electron microscopy (EM) data set requir...
research
05/27/2023

Trustworthy Deep Learning for Medical Image Segmentation

Despite the recent success of deep learning methods at achieving new sta...
research
02/08/2023

The XPRESS Challenge: Xray Projectomic Reconstruction – Extracting Segmentation with Skeletons

The wiring and connectivity of neurons form a structural basis for the f...
research
09/05/2014

Annotating Synapses in Large EM Datasets

Reconstructing neuronal circuits at the level of synapses is a central p...
research
06/12/2020

An Evolutional Algorithm for Automatic 2D Layer Segmentation in Laser-aided Additive Manufacturing

Toolpath planning is an important task in laser aided additive manufactu...

Please sign up or login with your details

Forgot password? Click here to reset