Signal-to-signal neural networks for improved spike estimation from calcium imaging data

Harnessing the potential of human induced pluripotent stem cells, functional assays and machine learning for neurodevelopmental disorders

Neurodevelopmental disorders (NDDs) affect 4.7% of the global population and are associated with delays in brain development and a spectrum of impairments that can lead to lifelong disability and even mortality. Identification of biomarkers for accurate diagnosis and medications for effective treatment are lacking, in part due to the historical use of preclinical model systems that do not translate well to the clinic for neurological disorders, such as rodents and heterologous cell lines. Human-induced pluripotent stem cells (hiPSCs) are a promising in vitro system for modeling NDDs, providing opportunities to understand mechanisms driving NDDs in human neurons. Functional assays, including patch clamping, multielectrode array, and imaging-based assays, are popular tools employed with hiPSC disease models for disease investigation. Recent progress in machine learning (ML) algorithms also presents unprecedented opportunities to advance the NDD research process. In this review, we compare two-dimensional and three-dimensional hiPSC formats for disease modeling, discuss the applications of functional assays, and offer insights on incorporating ML into hiPSC-based NDD research and drug screening.

Ultrafast optical imaging techniques for exploring rapid neuronal dynamics

Optical neuroimaging has significantly advanced our understanding of brain function, particularly through techniques such as two-photon microscopy, which captures three-dimensional brain structures with sub-cellular resolution. However, traditional methods struggle to record fast, complex neuronal interactions in real time, which are crucial for understanding brain networks and developing treatments for neurological diseases such as Alzheimer's, Parkinson's, and chronic pain. Recent advancements in ultrafast imaging technologies, including kilohertz two-photon microscopy, light field microscopy, and event-based imaging, are pushing the boundaries of temporal resolution in neuroimaging. These techniques enable the capture of rapid neural events with unprecedented speed and detail. This review examines the principles, applications, and limitations of these technologies, highlighting their potential to revolutionize neuroimaging and improve the diagnose and treatment of neurological disorders. Despite challenges such as photodamage risks and spatial resolution trade-offs, integrating these approaches promises to enhance our understanding of brain function and drive future breakthroughs in neuroscience and medicine. Continued interdisciplinary collaboration is essential to fully leverage these innovations for advancements in both basic and clinical neuroscience.

Crossmixed convolutional neural network for digital speech recognition

Digital speech recognition is a challenging problem that requires the ability to learn complex signal characteristics such as frequency, pitch, intensity, timbre, and melody, which traditional methods often face issues in recognizing. This article introduces three solutions based on convolutional neural networks (CNN) to solve the problem: 1D-CNN is designed to learn directly from digital data; 2DS-CNN and 2DM-CNN have a more complex architecture, transferring raw waveform into transformed images using Fourier transform to learn essential features. Experimental results on four large data sets, containing 30,000 samples for each, show that the three proposed models achieve superior performance compared to well-known models such as GoogLeNet and AlexNet, with the best accuracy of 95.87%, 99.65%, and 99.76%, respectively. With 5-10% higher performance than other models, the proposed solution has demonstrated the ability to effectively learn features, improve recognition accuracy and speed, and open up the potential for broad applications in virtual assistants, medical recording, and voice commands.

Effective and efficient neural networks for spike inference from in vivo calcium imaging

Calcium imaging provides advantages in monitoring large populations of neuronal activities simultaneously. However, it lacks the signal quality provided by neural spike recording in traditional electrophysiology. To address this issue, we developed a supervised data-driven approach to extract spike information from calcium signals. We propose the ENS2 (effective and efficient neural networks for spike inference from calcium signals) system for spike-rate and spike-event predictions using ΔF/F0 calcium inputs based on a U-Net deep neural network. When testing on a large, ground-truth public database, it consistently outperformed state-of-the-art algorithms in both spike-rate and spike-event predictions with reduced computational load. We further demonstrated that ENS2 can be applied to analyses of orientation selectivity in primary visual cortex neurons. We conclude that it would be a versatile inference system that may benefit diverse neuroscience studies.

A deep learning framework for inference of single-trial neural population dynamics from calcium imaging with subframe temporal resolution

In many areas of the brain, neural populations act as a coordinated network whose state is tied to behavior on a millisecond timescale. Two-photon (2p) calcium imaging is a powerful tool to probe such network-scale phenomena. However, estimating the network state and dynamics from 2p measurements has proven challenging because of noise, inherent nonlinearities and limitations on temporal resolution. Here we describe Recurrent Autoencoder for Discovering Imaged Calcium Latents (RADICaL), a deep learning method to overcome these limitations at the population level. RADICaL extends methods that exploit dynamics in spiking activity for application to deconvolved calcium signals, whose statistics and temporal dynamics are quite distinct from electrophysiologically recorded spikes. It incorporates a new network training strategy that capitalizes on the timing of 2p sampling to recover network dynamics with high temporal precision. In synthetic tests, RADICaL infers the network state more accurately than previous methods, particularly for high-frequency components. In 2p recordings from sensorimotor areas in mice performing a forelimb reach task, RADICaL infers network state with close correspondence to single-trial variations in behavior and maintains high-quality inference even when neuronal populations are substantially reduced.

A database and deep learning toolbox for noise-optimized, generalized spike inference from calcium imaging

Inference of action potentials ('spikes') from neuronal calcium signals is complicated by the scarcity of simultaneous measurements of action potentials and calcium signals ('ground truth'). In this study, we compiled a large, diverse ground truth database from publicly available and newly performed recordings in zebrafish and mice covering a broad range of calcium indicators, cell types and signal-to-noise ratios, comprising a total of more than 35 recording hours from 298 neurons. We developed an algorithm for spike inference (termed CASCADE) that is based on supervised deep networks, takes advantage of the ground truth database, infers absolute spike rates and outperforms existing model-based algorithms. To optimize performance for unseen imaging data, CASCADE retrains itself by resampling ground truth data to match the respective sampling rate and noise level; therefore, no parameters need to be adjusted by the user. In addition, we developed systematic performance assessments for unseen data, openly released a resource toolbox and provide a user-friendly cloud-based implementation.

A simple parametric representation of the Hodgkin-Huxley model

The Hodgkin-Huxley model, decades after its first presentation, is still a reference model in neuroscience as it has successfully reproduced the electrophysiological activity of many organisms. The primary signal in the model represents the membrane potential of a neuron. A simple representation of this signal is presented in this paper. The new proposal is an adapted Frequency Modulated Möbius multicomponent model defined as a signal plus error model in which the signal is decomposed as a sum of waves. The main strengths of the method are the simple parametric formulation, the interpretability and flexibility of the parameters that describe and discriminate the waveforms, the estimators' identifiability and accuracy, and the robustness against noise. The approach is validated with a broad simulation experiment of Hodgkin-Huxley signals and real data from squid giant axons. Interesting differences between simulated and real data emerge from the comparison of the parameter configurations. Furthermore, the potential of the FMM parameters to predict Hodgkin-Huxley model parameters is shown using different Machine Learning methods. Finally, promising contributions of the approach in Spike Sorting and cell-type classification are detailed.