English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Calcium imaging has become a powerful and popular technique to monitor theactivity of large populations of neurons in vivo. However, for ethicalconsiderations and despite recent technical developments, recordings are stillconstrained to a limited number of trials and animals. This limits the amountof data available from individual experiments and hinders the development ofanalysis techniques and models for more realistic sizes of neuronalpopulations. The ability to artificially synthesize realistic neuronal calciumsignals could greatly alleviate this problem by scaling up the number oftrials. Here, we propose a Generative Adversarial Network (GAN) model togenerate realistic calcium signals as seen in neuronal somata with calciumimaging. To this end, we propose CalciumGAN, a model based on the WaveGANarchitecture and train it on calcium fluorescent signals with the Wassersteindistance. We test the model on artificial data with known ground-truth and showthat the distribution of the generated signals closely resembles the underlyingdata distribution. Then, we train the model on real calcium traces recordedfrom the primary visual cortex of behaving mice and confirm that thedeconvolved spike trains match the statistics of the recorded data. Together,these results demonstrate that our model can successfully generate realisticcalcium traces, thereby providing the means to augment existing datasets ofneuronal activity for enhanced data exploration and modelling.

Synthesising Realistic Calcium Traces of Neuronal Populations Using GAN