Closed-Loop Neural Prostheses With On-Chip Intelligence: A Review and a Low-Latency Machine Learning Model for Brain State Detection

Zhu, Bingzhao; Shin, Uisub; Shoaran, Mahsa

doi:10.1109/tbcas.2021.3112756

Cited by 39 publications

(13 citation statements)

References 118 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI-based methods have been utilized for spike sorting, detection of neurological symptoms (e.g., epileptic seizures [11]), and motor intention decoding in a number of neural interface SoCs. Here, we focus on AI methods used for spike sorting and/or motor decoding in prosthetic BMIs.…”

Section: B State-of-the-art Bmi Socsmentioning

confidence: 99%

See 1 more Smart Citation

Challenges and Opportunities of Edge AI for Next-Generation Implantable BMIs

Shaeri¹,

Afzal²,

Shoaran³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Neuroscience and neurotechnology are currently being revolutionized by artificial intelligence (AI) and machine learning. AI is widely used to study and interpret neural signals (analytical applications), assist people with disabilities (prosthetic applications), and treat underlying neurological symptoms (therapeutic applications). In this brief, we will review the emerging opportunities of on-chip AI for the next-generation implantable brain machine interfaces (BMIs), with a focus on state-of-theart prosthetic BMIs. Major technological challenges for the effectiveness of AI models will be discussed. Finally, we will present algorithmic and IC design solutions to enable a new generation of AI-enhanced and high-channel-count BMIs.

show abstract

Section: B State-of-the-art Bmi Socsmentioning

confidence: 99%

“…A discrimination window is composed of two decision boundaries for each data dimension, simply implemented by a few digital comparators. Similarly, decision tree (DT)-based models classify the data with a set of successive comparisons and achieve excellent energy efficiencies [11], Fig. 2(c).…”

Section: B State-of-the-art Bmi Socsmentioning

confidence: 99%

Challenges and Opportunities of Edge AI for Next-Generation Implantable BMIs

Shaeri¹,

Afzal²,

Shoaran³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…At best, distributed BCI applications have been studied in prior work that consists of multiple sensor implants that offload processing to external devices with higher power budgets [31,32]. But, this is not a panacea because of the long network latency, privacy, and mobility limitations [33].…”

Section: Introductionmentioning

confidence: 99%

“…The second category also monitor the brain continuously but rely on agents external to Hull to respond. This includes, for example, the detection of an individual's intended movement, and relaying of this data to prostheses or assistive devices [3,[33][34][35]. These applications enable paralyzed individuals to actuate machines and restore (partial) sensory function.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Site Accelerator-Rich Processing Fabric for Scalable Brain-Computer Interfacing

Sriram¹,

Pothukuchi²,

Michał³

et al. 2023

Preprint

View full text Add to dashboard Cite

Hull 1 is an accelerator-rich distributed implantable brain-computer interface (BCI) that reads biological neurons at data rates that are 2-3 orders of magnitude higher than the prior art, while supporting many neuroscientific applications. Prior approaches have restricted brain interfacing to tens of megabits per second in order to meet two constraints necessary for effective operation and safe long-term implantation-power dissipation under tens of milliwatts and response latencies in the tens of milliseconds. Hull also adheres to these constraints, but is able to interface with the brain at much higher data rates, thereby enabling, for the first time, BCI-driven research on and clinical treatment of brain-wide behaviors and diseases that require reading and stimulating many brain locations. Central to Hull's power efficiency is its realization as a distributed system of BCI nodes with accelerator-rich compute. Hull balances modular system layering with aggressive cross-layer hardware-software co-design to integrate compute, networking, and storage. The result is a lesson in designing networked distributed systems with hardware accelerators from the ground up.

show abstract

“…Closed-loop brain stimulation has emerged as a promising therapeutic solution to treating such disorders [2]- [6], and a number of FDA-approved and research-based devices are currently available, including NeuroPace's responsive neurostimulation [7] and Medtronic's Percept deep-brain stimulation (DBS) [8] systems. However, these devices have a low channel count (4)(5)(6) and rely on simplistic symptom detection algorithms (e.g., feature thresholding), which could result in suboptimal detection accuracy and limited therapeutic efficacy.…”

mentioning

confidence: 99%

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

Shin¹,

Ding²,

Zhu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

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 count 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 highvoltage (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 0.014mm 2 /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 from human local field potentials (LFPs) was demonstrated.

show abstract

Closed-Loop Neural Prostheses With On-Chip Intelligence: A Review and a Low-Latency Machine Learning Model for Brain State Detection

Cited by 39 publications

References 118 publications

Challenges and Opportunities of Edge AI for Next-Generation Implantable BMIs

Challenges and Opportunities of Edge AI for Next-Generation Implantable BMIs

A Multi-Site Accelerator-Rich Processing Fabric for Scalable Brain-Computer Interfacing

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

Contact Info

Product

Resources

About