Removing independent noise in systems neuroscience data using DeepInterpolation

Progress in nearly every scientific discipline is hindered by the presence of independent noise in spatiotemporally structured datasets. Three widespread technologies for measuring neural activity—calcium imaging, extracellular electrophysiology, and fMRI—all operate in domains in which shot noise and/or thermal noise deteriorate the quality of measured physiological signals. Current denoising approaches sacrifice spatial and/or temporal resolution to increase the Signal-to-Noise Ratio of weak neuronal events, leading to missed opportunities for scientific discovery. Here, we introduce DeepInterpolation, a general-purpose denoising algorithm that trains a spatio-temporal nonlinear interpolation model using only noisy samples from the original raw data. Applying DeepInterpolation to in vivo two-photon Ca2+ imaging yields up to 6 times more segmented neuronal segments with a 15 fold increase in single pixel SNR, uncovering network dynamics at the single-trial level. In extracellular electrophysiology recordings, DeepInterpolation recovered 25% more high-quality spiking units compared to a standard data analysis pipeline. On fMRI datasets, DeepInterpolation increased the SNR of individual voxels 1.6-fold. All these improvements were attained without sacrificing spatial or temporal resolution. DeepInterpolation could well have a similar impact in other domains for which independent noise is present in experimental data.

[1]  Loic A. Royer,et al.  Content-aware image restoration: pushing the limits of fluorescence microscopy , 2018, Nature Methods.

[2]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Jaakko Lehtinen,et al.  Noise2Noise: Learning Image Restoration without Clean Data , 2018, ICML.

[4]  Natalia Mesa,et al.  The Effect of Inclusion Criteria on the Functional Properties Reported in Mouse Visual Cortex , 2020, eNeuro.

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

[6]  Daniel N Hill,et al.  Quality Metrics to Accompany Spike Sorting of Extracellular Signals , 2011, The Journal of Neuroscience.

[7]  Hongkui Zeng,et al.  Kilohertz two-photon brain imaging in awake mice , 2019, Nature Methods.

[8]  Ying Ma,et al.  Penalized matrix decomposition for denoising, compression, and improved demixing of functional imaging data , 2018, bioRxiv.

[9]  Nathan C. Klapoetke,et al.  Transgenic Mice for Intersectional Targeting of Neural Sensors and Effectors with High Specificity and Performance , 2015, Neuron.

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

[11]  M. Cohen,et al.  Measuring and interpreting neuronal correlations , 2011, Nature Neuroscience.

[12]  Michael Z. Lin,et al.  A Suite of Transgenic Driver and Reporter Mouse Lines with Enhanced Brain-Cell-Type Targeting and Functionality , 2018, Cell.

[13]  César Caballero-Gaudes,et al.  Methods for cleaning the BOLD fMRI signal , 2016, NeuroImage.

[14]  Sergey L. Gratiy,et al.  Fully integrated silicon probes for high-density recording of neural activity , 2017, Nature.

[15]  Michael Z. Lin,et al.  Kilohertz two-photon fluorescence microscopy imaging of neural activity in vivo , 2019, Nature Methods.

[16]  Satrajit S. Ghosh,et al.  FMRIPrep: a robust preprocessing pipeline for functional MRI , 2018, bioRxiv.

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

[18]  Susana Q. Lima,et al.  PINP: A New Method of Tagging Neuronal Populations for Identification during In Vivo Electrophysiological Recording , 2009, PloS one.

[19]  Matteo Carandini,et al.  Kilosort: realtime spike-sorting for extracellular electrophysiology with hundreds of channels , 2016, bioRxiv.

[20]  Hyunjin Park,et al.  FuNP (Fusion of Neuroimaging Preprocessing) Pipelines: A Fully Automated Preprocessing Software for Functional Magnetic Resonance Imaging , 2019, Front. Neuroinform..

[21]  Florian Jug,et al.  Noise2Void - Learning Denoising From Single Noisy Images , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[23]  Luca Turella,et al.  Variability in the analysis of a single neuroimaging dataset by many teams , 2019, Nature.

[24]  Loïc Royer,et al.  Noise2Self: Blind Denoising by Self-Supervision , 2019, ICML.

[25]  Jeremy F. Magland,et al.  SpikeForest: reproducible web-facing ground-truth validation of automated neural spike sorters , 2020, bioRxiv.

[26]  Loic A. Royer,et al.  Content-Aware Image Restoration: Pushing the Limits of Fluorescence Microscopy , 2018, bioRxiv.

[27]  Fuhui Long,et al.  A survey of spiking activity reveals a functional hierarchy of mouse corticothalamic visual areas , 2019, bioRxiv.

[28]  Mark J. Schnitzer,et al.  Automated Analysis of Cellular Signals from Large-Scale Calcium Imaging Data , 2009, Neuron.

[29]  Eric Shea-Brown,et al.  A large-scale standardized physiological survey reveals functional organization of the mouse visual cortex , 2019, Nature Neuroscience.

[30]  Loic A. Royer,et al.  Applications, Promises, and Pitfalls of Deep Learning for Fluorescence Image Reconstruction , 2018 .

[31]  Abhay Patil,et al.  Learning Image Restoration without Clean Data , 2019 .

[32]  Tomoyasu Horikawa,et al.  Generic decoding of seen and imagined objects using hierarchical visual features , 2015, Nature Communications.

[33]  Hongkui Zeng,et al.  Fundamental bounds on the fidelity of sensory cortical coding , 2020, Nature.

[34]  Christof Koch,et al.  A large-scale, standardized physiological survey reveals higher order coding throughout the mouse visual cortex , 2018, bioRxiv.

[35]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Shay Ohayon,et al.  Open Ephys: an open-source, plugin-based platform for multichannel electrophysiology , 2017, Journal of neural engineering.