# Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks

arXiv: https://arxiv.org/abs/1811.11356 · HTML: https://mlsanity.com/paper/1811.11356/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 2 of 2)

- [Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex](https://mlsanity.com/paper/2306.03779/) (2023)
- [Improving Data-Efficient Fossil Segmentation via Model Editing](https://mlsanity.com/paper/2210.03879/) (2022)

## Abstract (arXiv)

Recent successes in deep learning have started to impact neuroscience. Of particular significance are claims that current segmentation algorithms achieve "super-human" accuracy in an area known as connectomics. However, as we will show, these algorithms do not effectively generalize beyond the particular source and brain tissues used for training -- severely limiting their usability by the broader neuroscience community. To fill this gap, we describe a novel connectomics challenge for source- and tissue-agnostic reconstruction of neurons (STAR), which favors broad generalization over fitting specific datasets. We first demonstrate that current state-of-the-art approaches to neuron segmentation perform poorly on the challenge. We further describe a novel convolutional recurrent neural network module that combines short-range horizontal connections within a processing stage and long-range top-down connections between stages. The resulting architecture establishes the state of the art on the STAR challenge and represents a significant step towards widely usable and fully-automated connectomics analysis.