Neural interface systems with on-device computing: machine learning and neuromorphic architectures

Information Transmission through Biotic-Abiotic Interfaces to Restore or Enhance Human Function

Advancements in reliable information transfer across biotic-abiotic interfaces have enabled the restoration of lost human function. For example, communication between neuronal cells and electrical devices restores the ability to walk to a tetraplegic patient and vision to patients blinded by retinal disease. These impactful medical achievements are aided by tailored biotic-abiotic interfaces that maximize information transfer fidelity by considering the physical properties of the underlying biological and synthetic components. This Review develops a modular framework to define and describe the engineering of biotic and abiotic components as well as the design of interfaces to facilitate biotic-abiotic information transfer using light or electricity. Delineating the properties of the biotic, interface, and abiotic components that enable communication can serve as a guide for future research in this highly interdisciplinary field. Application of synthetic biology to engineer light-sensitive proteins has facilitated the control of neural signaling and the restoration of rudimentary vision after retinal blindness. Electrophysiological methodologies that use brain-computer interfaces and stimulating implants to bypass spinal column injuries have led to the rehabilitation of limb movement and walking ability. Cellular interfacing methodologies and on-chip learning capability have been made possible by organic transistors that mimic the information processing capacity of neurons. The collaboration of molecular biologists, material scientists, and electrical engineers in the emerging field of biotic-abiotic interfacing will lead to the development of prosthetics capable of responding to thought and experiencing touch sensation via direct integration into the human nervous system. Further interdisciplinary research will improve electrical and optical interfacing technologies for the restoration of vision, offering greater visual acuity and potentially color vision in the near future.

Neural Decoding and Feature Selection Techniques for Closed-Loop Control of Defensive Behavior

Objective

Many psychiatric disorders involve excessive avoidant or defensive behavior, such as avoidance in anxiety and trauma disorders or defensive rituals in obsessive-compulsive disorders. Developing algorithms to predict these behaviors from local field potentials (LFPs) could serve as foundational technology for closed-loop control of such disorders. A significant challenge is identifying the LFP features that encode these defensive behaviors.

Approach

We analyzed LFP signals from the infralimbic cortex and basolateral amygdala of rats undergoing tone-shock conditioning and extinction, standard for investigating defensive behaviors. We utilized a comprehensive set of neuro-markers across spectral, temporal, and connectivity domains, employing SHapley Additive exPlanations for feature importance evaluation within Light Gradient-Boosting Machine models. Our goal was to decode three commonly studied avoidance/defensive behaviors: freezing, bar-press suppression, and motion (accelerometry), examining the impact of different features on decoding performance.

Main results

Band power and band power ratio between channels emerged as optimal features across sessions. High-gamma (80-150 Hz) power, power ratios, and inter-regional correlations were more informative than other bands that are more classically linked to defensive behaviors. Focusing on highly informative features enhanced performance. Across 4 recording sessions with 16 subjects, we achieved an average coefficient of determination of 0.5357 and 0.3476, and Pearson correlation coefficients of 0.7579 and 0.6092 for accelerometry jerk and bar press rate, respectively. Utilizing only the most informative features revealed differential encoding between accelerometry and bar press rate, with the former primarily through local spectral power and the latter via inter-regional connectivity. Our methodology demonstrated remarkably low time complexity, requiring <110 ms for training and <1 ms for inference.

Significance

Our results demonstrate the feasibility of accurately decoding defensive behaviors with minimal latency, using LFP features from neural circuits strongly linked to these behaviors. This methodology holds promise for real-time decoding to identify physiological targets in closed-loop psychiatric neuromodulation.

A modular organic neuromorphic spiking circuit for retina-inspired sensory coding and neurotransmitter-mediated neural pathways

Signal communication mechanisms within the human body rely on the transmission and modulation of action potentials. Replicating the interdependent functions of receptors, neurons and synapses with organic artificial neurons and biohybrid synapses is an essential first step towards merging neuromorphic circuits and biological systems, crucial for computing at the biological interface. However, most organic neuromorphic systems are based on simple circuits which exhibit limited adaptability to both external and internal biological cues, and are restricted to emulate only specific the functions of an individual neuron/synapse. Here, we present a modular neuromorphic system which combines organic spiking neurons and biohybrid synapses to replicate a neural pathway. The spiking neuron mimics the sensory coding function of afferent neurons from light stimuli, while the neuromodulatory activity of interneurons is emulated by neurotransmitters-mediated biohybrid synapses. Combining these functions, we create a modular connection between multiple neurons to establish a pre-processing retinal pathway primitive.

Bioelectronic Medicine: a multidisciplinary roadmap from biophysics to precision therapies

Bioelectronic Medicine stands as an emerging field that rapidly evolves and offers distinctive clinical benefits, alongside unique challenges. It consists of the modulation of the nervous system by precise delivery of electrical current for the treatment of clinical conditions, such as post-stroke movement recovery or drug-resistant disorders. The unquestionable clinical impact of Bioelectronic Medicine is underscored by the successful translation to humans in the last decades, and the long list of preclinical studies. Given the emergency of accelerating the progress in new neuromodulation treatments (i.e., drug-resistant hypertension, autoimmune and degenerative diseases), collaboration between multiple fields is imperative. This work intends to foster multidisciplinary work and bring together different fields to provide the fundamental basis underlying Bioelectronic Medicine. In this review we will go from the biophysics of the cell membrane, which we consider the inner core of neuromodulation, to patient care. We will discuss the recently discovered mechanism of neurotransmission switching and how it will impact neuromodulation design, and we will provide an update on neuronal and glial basis in health and disease. The advances in biomedical technology have facilitated the collection of large amounts of data, thereby introducing new challenges in data analysis. We will discuss the current approaches and challenges in high throughput data analysis, encompassing big data, networks, artificial intelligence, and internet of things. Emphasis will be placed on understanding the electrochemical properties of neural interfaces, along with the integration of biocompatible and reliable materials and compliance with biomedical regulations for translational applications. Preclinical validation is foundational to the translational process, and we will discuss the critical aspects of such animal studies. Finally, we will focus on the patient point-of-care and challenges in neuromodulation as the ultimate goal of bioelectronic medicine. This review is a call to scientists from different fields to work together with a common endeavor: accelerate the decoding and modulation of the nervous system in a new era of therapeutic possibilities.

Resource-Efficient Neural Network Architectures for Classifying Nerve Cuff Recordings on Implantable Devices

BACKGROUND

Closed-loop functional electrical stimulation can use recorded nerve signals to create implantable systems that make decisions regarding nerve stimulation in real-time. Previous work demonstrated convolutional neural network (CNN) discrimination of activity from different neural pathways recorded by a high-density multi-contact nerve cuff electrode, achieving state-of-the-art performance but requiring too much data storage and power for a practical implementation on surgically implanted hardware.

OBJECTIVE

To reduce resource utilization for an implantable implementation, with minimal performance loss for CNNs that can discriminate between neural pathways in multi-contact cuff electrode recordings.

METHODS

Neural networks (NNs) were evaluated using rat sciatic nerve recordings previously collected using 56-channel cuff electrodes to capture spatiotemporal neural activity patterns. NNs were trained to classify individual, natural compound action potentials (nCAPs) elicited by sensory stimuli. Three architectures were explored: the previously reported ESCAPE-NET, a fully convolutional network, and a recurrent neural network. Variations of each architecture were evaluated based on F1-score, number of weights, and floating-point operations (FLOPs).

RESULTS

NNs were identified that, when compared to ESCAPE-NET, require 1,132-1,787x fewer weights, 389-995x less memory, and 6-11,073x fewer FLOPs, while maintaining macro F1-scores of 0.70-0.71 compared to a baseline of 0.75. Memory requirements range from 22.69 KB to 58.11 KB, falling within on-chip memory sizes from published deep learning accelerators fabricated in ASIC technology.

CONCLUSION

Reduced versions of ESCAPE-NET require significantly fewer resources without significant accuracy loss, thus can be more easily incorporated into a surgically implantable device that performs closed-loop responsive neural stimulation.

From basic sciences and engineering to epileptology: A translational approach

Collaborative efforts between basic scientists, engineers, and clinicians are enabling translational epileptology. In this article, we summarize the recent advances presented at the International Conference for Technology and Analysis of Seizures (ICTALS 2022): (1) novel developments of structural magnetic resonance imaging; (2) latest electroencephalography signal-processing applications; (3) big data for the development of clinical tools; (4) the emerging field of hyperdimensional computing; (5) the new generation of artificial intelligence (AI)-enabled neuroprostheses; and (6) the use of collaborative platforms to facilitate epilepsy research translation. We highlight the promise of AI reported in recent investigations and the need for multicenter data-sharing initiatives.

A Comprehensive Review of Emerging Trends and Innovative Therapies in Epilepsy Management

Epilepsy is a complex neurological disorder affecting millions worldwide, with a substantial number of patients facing drug-resistant epilepsy. This comprehensive review explores innovative therapies for epilepsy management, focusing on their principles, clinical evidence, and potential applications. Traditional antiseizure medications (ASMs) form the cornerstone of epilepsy treatment, but their limitations necessitate alternative approaches. The review delves into cutting-edge therapies such as responsive neurostimulation (RNS), vagus nerve stimulation (VNS), and deep brain stimulation (DBS), highlighting their mechanisms of action and promising clinical outcomes. Additionally, the potential of gene therapies and optogenetics in epilepsy research is discussed, revealing groundbreaking findings that shed light on seizure mechanisms. Insights into cannabidiol (CBD) and the ketogenic diet as adjunctive therapies further broaden the spectrum of epilepsy management. Challenges in achieving seizure control with traditional therapies, including treatment resistance and individual variability, are addressed. The importance of staying updated with emerging trends in epilepsy management is emphasized, along with the hope for improved therapeutic options. Future research directions, such as combining therapies, AI applications, and non-invasive optogenetics, hold promise for personalized and effective epilepsy treatment. As the field advances, collaboration among researchers of natural and synthetic biochemistry, clinicians from different streams and various forms of medicine, and patients will drive progress toward better seizure control and a higher quality of life for individuals living with epilepsy.

In Liquido Computation with Electrochemical Transistors and Mixed Conductors for Intelligent Bioelectronics

Next-generation implantable computational devices require long-term-stable electronic components capable of operating in, and interacting with, electrolytic surroundings without being damaged. Organic electrochemical transistors (OECTs) emerged as fitting candidates. However, while single devices feature impressive figures of merit, integrated circuits (ICs) immersed in common electrolytes are hard to realize using electrochemical transistors, and there is no clear path forward for optimal top-down circuit design and high-density integration. The simple observation that two OECTs immersed in the same electrolytic medium will inevitably interact hampers their implementation in complex circuitry. The electrolyte's ionic conductivity connects all the devices in the liquid, producing unwanted and often unforeseeable dynamics. Minimizing or harnessing this crosstalk has been the focus of very recent studies. Herein, the main challenges, trends, and opportunities for realizing OECT-based circuitry in a liquid environment that could circumnavigate the hard limits of engineering and human physiology, are discussed. The most successful approaches in autonomous bioelectronics and information processing are analyzed. Elaborating on the strategies to circumvent and harness device crosstalk proves that platforms capable of complex computation and even machine learning (ML) can be realized in liquido using mixed ionic-electronic conductors (OMIECs).

Modulating Brain Activity with Invasive Brain-Computer Interface: A Narrative Review

Brain-computer interface (BCI) can be used as a real-time bidirectional information gateway between the brain and machines. In particular, rapid progress in invasive BCI, propelled by recent developments in electrode materials, miniature and power-efficient electronics, and neural signal decoding technologies has attracted wide attention. In this review, we first introduce the concepts of neuronal signal decoding and encoding that are fundamental for information exchanges in BCI. Then, we review the history and recent advances in invasive BCI, particularly through studies using neural signals for controlling external devices on one hand, and modulating brain activity on the other hand. Specifically, regarding modulating brain activity, we focus on two types of techniques, applying electrical stimulation to cortical and deep brain tissues, respectively. Finally, we discuss the related ethical issues concerning the clinical application of this emerging technology.

NeuralTree: A 256-Channel 0.227-μJ/Class Versatile Neural Activity Classification and Closed-Loop Neuromodulation SoC

Closed-loop neural interfaces with on-chip machine learning can detect and suppress disease symptoms in neurological disorders or restore lost functions in paralyzed patients. While high-density neural recording can provide rich neural activity information for accurate disease-state detection, existing systems have low channel counts and poor scalability, which could limit their therapeutic efficacy. This work presents a highly scalable and versatile closed-loop neural interface SoC that can overcome these limitations. A 256-channel time-division multiplexed (TDM) front-end with a two-step fast-settling mixed-signal DC servo loop (DSL) is proposed to record high-spatial-resolution neural activity and perform channel-selective brain-state inference. A tree-structured neural network (NeuralTree) classification processor extracts a rich set of neural biomarkers in a patient- and disease-specific manner. Trained with an energy-aware learning algorithm, the NeuralTree classifier detects the symptoms of underlying disorders (e.g., epilepsy and movement disorders) at an optimal energy-accuracy trade-off. A 16-channel high-voltage (HV) compliant neurostimulator closes the therapeutic loop by delivering charge-balanced biphasic current pulses to the brain. The proposed SoC was fabricated in 65nm CMOS and achieved a 0.227μJ/class energy efficiency in a compact area of 0.014mm2/channel. The SoC was extensively verified on human electroencephalography (EEG) and intracranial EEG (iEEG) epilepsy datasets, obtaining 95.6%/94% sensitivity and 96.8%/96.9% specificity, respectively. In-vivo neural recordings using soft μECoG arrays and multi-domain biomarker extraction were further performed on a rat model of epilepsy. In addition, for the first time in literature, on-chip classification of rest-state tremor in Parkinson's disease (PD) from human local field potentials (LFPs) was demonstrated.

Robust Spike-Based Continual Meta-Learning Improved by Restricted Minimum Error Entropy Criterion

The spiking neural network (SNN) is regarded as a promising candidate to deal with the great challenges presented by current machine learning techniques, including the high energy consumption induced by deep neural networks. However, there is still a great gap between SNNs and the online meta-learning performance of artificial neural networks. Importantly, existing spike-based online meta-learning models do not target the robust learning based on spatio-temporal dynamics and superior machine learning theory. In this invited article, we propose a novel spike-based framework with minimum error entropy, called MeMEE, using the entropy theory to establish the gradient-based online meta-learning scheme in a recurrent SNN architecture. We examine the performance based on various types of tasks, including autonomous navigation and the working memory test. The experimental results show that the proposed MeMEE model can effectively improve the accuracy and the robustness of the spike-based meta-learning performance. More importantly, the proposed MeMEE model emphasizes the application of the modern information theoretic learning approach on the state-of-the-art spike-based learning algorithms. Therefore, in this invited paper, we provide new perspectives for further integration of advanced information theory in machine learning to improve the learning performance of SNNs, which could be of great merit to applied developments with spike-based neuromorphic systems.