DeepCINAC: A Deep-Learning-Based Python Toolbox for Inferring Calcium Imaging Neuronal Activity Based on Movie Visualization

Two-photon calcium imaging is now widely used to infer neuronal dynamics from changes in fluorescence of an indicator. However, state of the art computational tools are not optimized for the reliable detection of fluorescence transients from highly synchronous neurons located in densely packed regions such as the CA1 pyramidal layer of the hippocampus during early postnatal stages of development. Indeed, the latest analytical tools often lack proper benchmark measurements. To meet this challenge, we first developed a graphical user interface allowing for a precise manual detection of all calcium transients from imaged neurons based on the visualization of the calcium imaging movie. Then, we analyzed the movies using a convolutional neural network with an attention process and a bidirectional long-short term memory network. This method is able to reach human performance and offers a better F1 score (harmonic mean of sensitivity and precision) than CaImAn to infer neural activity in the developing CA1 without any user intervention. It also enables automatically identifying activity originating from GABAergic neurons. Overall, DeepCINAC offers a simple, fast and flexible open-source toolbox for processing a wide variety of calcium imaging datasets while providing the tools to evaluate its performance. Significance statement Inferring neuronal activity from calcium imaging data remains a challenge due to the difficulty in obtaining a ground truth using patch clamp recordings and the problem of finding optimal tuning parameters of inference algorithms. DeepCINAC offers a flexible, fast and easy-to-use toolbox to infer neuronal activity from any kind of calcium imaging dataset through visual inspection.

[1]  Kenneth D. Harris,et al.  Community-based benchmarking improves spike rate inference from two-photon calcium imaging data , 2018, PLoS Comput. Biol..

[2]  Stefan R. Pulver,et al.  Ultra-sensitive fluorescent proteins for imaging neuronal activity , 2013, Nature.

[3]  Jeffrey L. Gauthier,et al.  A Dedicated Population for Reward Coding in the Hippocampus , 2018, Neuron.

[4]  S. Smirnakis,et al.  Viral transduction of the neonatal brain delivers controllable genetic mosaicism for visualising and manipulating neuronal circuits in vivo , 2013, The European journal of neuroscience.

[5]  Aristides B. Arrenberg,et al.  Spatial gradients and multidimensional dynamics in a neural integrator circuit , 2011, Nature Neuroscience.

[6]  Y. Ben-Ari,et al.  Giant synaptic potentials in immature rat CA3 hippocampal neurones. , 1989, The Journal of physiology.

[7]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[8]  Aurélien Géron,et al.  Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems , 2017 .

[9]  Michel A. Picardo,et al.  Dynamic Changes in Interneuron Morphophysiological Properties Mark the Maturation of Hippocampal Network Activity , 2012, The Journal of Neuroscience.

[10]  R. Cossart,et al.  Assemblies of Perisomatic GABAergic Neurons in the Developing Barrel Cortex , 2019, Neuron.

[11]  Marc Levoy,et al.  Neuronal Dynamics Regulating Brain and Behavioral State Transitions , 2019, Cell.

[12]  L. Maffei,et al.  Spontaneous impulse activity of rat retinal ganglion cells in prenatal life. , 1988, Science.

[13]  Adam S. Charles,et al.  Detecting and correcting false transients in calcium imaging , 2018, Nature Methods.

[14]  Tjerk P. Straatsma,et al.  NWChem: A comprehensive and scalable open-source solution for large scale molecular simulations , 2010, Comput. Phys. Commun..

[15]  Selmaan N. Chettih,et al.  Dynamic Reorganization of Neuronal Activity Patterns in Parietal Cortex , 2017, Cell.

[16]  M. Whittington,et al.  Long-Range–Projecting GABAergic Neurons Modulate Inhibition in Hippocampus and Entorhinal Cortex , 2012, Science.

[17]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

[18]  Oliver Rübel,et al.  NWB:N 2.0: An Accessible Data Standard for Neurophysiology , 2019, bioRxiv.

[19]  Christof Koch,et al.  Neurodata Without Borders: Creating a Common Data Format for Neurophysiology , 2015, Neuron.

[20]  Michael J. O'Donovan,et al.  Motor activity in the isolated spinal cord of the chick embryo: synaptic drive and firing pattern of single motoneurons , 1989, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[21]  Mark D. Humphries,et al.  On the use of calcium deconvolution algorithms in practical contexts , 2019, bioRxiv.

[22]  David Pfau,et al.  Simultaneous Denoising, Deconvolution, and Demixing of Calcium Imaging Data , 2016, Neuron.

[23]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[24]  Pengcheng Zhou,et al.  CaImAn an open source tool for scalable calcium imaging data analysis , 2019, eLife.

[25]  Rosa Cossart,et al.  Internally Recurring Hippocampal Sequences as a Population Template of Spatiotemporal Information , 2015, Neuron.

[26]  Eric Jones,et al.  SciPy: Open Source Scientific Tools for Python , 2001 .

[27]  Yehezkel Ben-Ari,et al.  Retinal Waves Trigger Spindle Bursts in the Neonatal Rat Visual Cortex , 2006, The Journal of Neuroscience.

[28]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[29]  Quoc V. Le,et al.  Searching for Activation Functions , 2018, arXiv.

[30]  R. Provine.  Ontogeny of bioelectric activity in the spinal cord of the chick embryo and its behavioral implications. , 1972, Brain research.

[31]  Adam S. Charles,et al.  Neural anatomy and optical microscopy (NAOMi) simulation for evaluating calcium imaging methods , 2019, Journal of Neuroscience Methods.

[32]  Stacy D. Grunke,et al.  Intracerebroventricular viral injection of the neonatal mouse brain for persistent and widespread neuronal transduction. , 2014, Journal of Visualized Experiments.

[33]  Lin Tian,et al.  Functional imaging of hippocampal place cells at cellular resolution during virtual navigation , 2010, Nature Neuroscience.

[34]  Michael A. Long,et al.  Stable Sequential Activity Underlying the Maintenance of a Precisely Executed Skilled Behavior , 2018, Neuron.

[35]  Nicholas A. Steinmetz,et al.  Spontaneous behaviors drive multidimensional, brainwide activity , 2019, Science.

[36]  Xuelong Li,et al.  Describing Video With Attention-Based Bidirectional LSTM , 2019, IEEE Transactions on Cybernetics.

[37]  Mario Dipoppa,et al.  Suite2p: beyond 10,000 neurons with standard two-photon microscopy , 2016, bioRxiv.

[38]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .