# Fast deep learning correspondence for neuron tracking and identification in C.elegans using synthetic training

arXiv: https://arxiv.org/abs/2101.08211 · HTML: https://mlsanity.com/paper/2101.08211/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 45 references that are in the map.
- First posted on arXiv 20 Jan 2021.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Deep learning tools for the measurement of animal behavior in neuroscience](https://mlsanity.com/paper/1909.13868/) (2019)
- [Automatically tracking neurons in a moving and deforming brain](https://mlsanity.com/paper/1610.04579/) (2016)
- [Brain-wide 3D imaging of neuronal activity in Caenorhabditis elegans with sculpted light](https://mlsanity.com/paper/1406.1603/) (2014)
- [Simultaneous optogenetic manipulation and calcium imaging in freely moving C. elegans](https://mlsanity.com/paper/1311.6406/) (2013)

## Built on by (most cited first, 3 of 3)

- [Rapid detection and recognition of whole brain activity in a freely behaving Caenorhabditis elegans](https://mlsanity.com/paper/2109.10474/) (2021)
- [A Neural Network Based Automated IFT-20 Sensory Neuron Classifier for Caenorhabditis elegans](https://mlsanity.com/paper/2210.14961/) (2022)
- [SINETRA: a Versatile Framework for Evaluating Single Neuron Tracking in Behaving Animals](https://mlsanity.com/paper/2411.09462/) (2024)

## Abstract (arXiv)

We present an automated method to track and identify neurons in C. elegans, called "fast Deep Learning Correspondence" or fDLC, based on the transformer network architecture. The model is trained once on empirically derived synthetic data and then predicts neural correspondence across held-out real animals via transfer learning. The same pre-trained model both tracks neurons across time and identifies corresponding neurons across individuals. Performance is evaluated against hand-annotated datasets, including NeuroPAL [1]. Using only position information, the method achieves 80.0% accuracy at tracking neurons within an individual and 65.8% accuracy at identifying neurons across individuals. Accuracy is even higher on a published dataset [2]. Accuracy reaches 76.5% when using color information from NeuroPAL. Unlike previous methods, fDLC does not require straightening or transforming the animal into a canonical coordinate system. The method is fast and predicts correspondence in 10 ms making it suitable for future real-time applications.