Aarhus University Seal / Aarhus Universitets segl

A CMOS-based neuromorphic device for seizure detection from LFP signals

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Standard

A CMOS-based neuromorphic device for seizure detection from LFP signals. / Ronchini, Margherita; Zamani, Milad; Huynh, Hai Au; Rezaeiyan, Yasser; Panuccio, Gabriella; Farkhani, Hooman; Moradi, Farshad.

In: Journal of Physics D: Applied Physics, Vol. 55, No. 1, 014001, 01.2022.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Harvard

APA

CBE

MLA

Vancouver

Author

Bibtex

@article{da6c8e2ea2e84cbaa9b73265fde76e24,
title = "A CMOS-based neuromorphic device for seizure detection from LFP signals",
abstract = "Recent research provides examples of neuromorphic systems applied to process biological signals or to interface biological tissues. Usually, in such contexts, the neuromorphic system is used for automatic anomaly detection. The automation of the long-term monitoring of biological signals holds promise for lightening the burden placed on clinicians. At the same time, the adoption of such devices potentially allows processing to be performed locally, without the need to transfer data to an external processor. In turn, on-site signal analysis makes closed-loop intervention feasible, to correct the source of the anomalies. So far, the common approach has been to deploy the network of spiking neurons either on multi-core neuromorphic platforms or on programmable units (FPGA). However, if the aim is to develop wearable or even chronically implantable devices, it is imperative to move in the direction of embedded solutions, tailored and optimized for the specific application. To this end, the present study proposes a neuromorphic device implemented in CMOS technology for the detection of epileptic seizures (ictal events) from local field potential (LFP) signals. The LFP data have been acquired by a multi-electrode array (MEA) in a slice of mouse hippocampus-cortex (CTX). The system includes an analog-to-event converter (AEC) encoding the recorded signals into trains of spikes, and a small spiking neural network (SNN) of 2x1 neurons with online biological-plausible learning. The AEC yields two spike-trains: UP spikes that account for the positive slope signal and DOWN spikes that correspond to the negative slope signal. The synapses among the input and output layers are plastic and follow the spike-timing-dependent plasticity (STDP) rule. Early results show that the SNN module is able to detect ictal events with a delay of 64.98 ± 30.92 ms, consuming < 50 pW. The layout of the entire system occupies 528 µm × 278 µm.",
keywords = "LFP signals, SNN, neuromorphic, seizure-detection",
author = "Margherita Ronchini and Milad Zamani and Huynh, {Hai Au} and Yasser Rezaeiyan and Gabriella Panuccio and Hooman Farkhani and Farshad Moradi",
year = "2022",
month = jan,
doi = "10.1088/1361-6463/ac28bb",
language = "English",
volume = "55",
journal = "Journal of Physics D: Applied Physics",
issn = "0022-3727",
publisher = "Institute of Physics Publishing Ltd.",
number = "1",

}

RIS

TY - JOUR

T1 - A CMOS-based neuromorphic device for seizure detection from LFP signals

AU - Ronchini, Margherita

AU - Zamani, Milad

AU - Huynh, Hai Au

AU - Rezaeiyan, Yasser

AU - Panuccio, Gabriella

AU - Farkhani, Hooman

AU - Moradi, Farshad

PY - 2022/1

Y1 - 2022/1

N2 - Recent research provides examples of neuromorphic systems applied to process biological signals or to interface biological tissues. Usually, in such contexts, the neuromorphic system is used for automatic anomaly detection. The automation of the long-term monitoring of biological signals holds promise for lightening the burden placed on clinicians. At the same time, the adoption of such devices potentially allows processing to be performed locally, without the need to transfer data to an external processor. In turn, on-site signal analysis makes closed-loop intervention feasible, to correct the source of the anomalies. So far, the common approach has been to deploy the network of spiking neurons either on multi-core neuromorphic platforms or on programmable units (FPGA). However, if the aim is to develop wearable or even chronically implantable devices, it is imperative to move in the direction of embedded solutions, tailored and optimized for the specific application. To this end, the present study proposes a neuromorphic device implemented in CMOS technology for the detection of epileptic seizures (ictal events) from local field potential (LFP) signals. The LFP data have been acquired by a multi-electrode array (MEA) in a slice of mouse hippocampus-cortex (CTX). The system includes an analog-to-event converter (AEC) encoding the recorded signals into trains of spikes, and a small spiking neural network (SNN) of 2x1 neurons with online biological-plausible learning. The AEC yields two spike-trains: UP spikes that account for the positive slope signal and DOWN spikes that correspond to the negative slope signal. The synapses among the input and output layers are plastic and follow the spike-timing-dependent plasticity (STDP) rule. Early results show that the SNN module is able to detect ictal events with a delay of 64.98 ± 30.92 ms, consuming < 50 pW. The layout of the entire system occupies 528 µm × 278 µm.

AB - Recent research provides examples of neuromorphic systems applied to process biological signals or to interface biological tissues. Usually, in such contexts, the neuromorphic system is used for automatic anomaly detection. The automation of the long-term monitoring of biological signals holds promise for lightening the burden placed on clinicians. At the same time, the adoption of such devices potentially allows processing to be performed locally, without the need to transfer data to an external processor. In turn, on-site signal analysis makes closed-loop intervention feasible, to correct the source of the anomalies. So far, the common approach has been to deploy the network of spiking neurons either on multi-core neuromorphic platforms or on programmable units (FPGA). However, if the aim is to develop wearable or even chronically implantable devices, it is imperative to move in the direction of embedded solutions, tailored and optimized for the specific application. To this end, the present study proposes a neuromorphic device implemented in CMOS technology for the detection of epileptic seizures (ictal events) from local field potential (LFP) signals. The LFP data have been acquired by a multi-electrode array (MEA) in a slice of mouse hippocampus-cortex (CTX). The system includes an analog-to-event converter (AEC) encoding the recorded signals into trains of spikes, and a small spiking neural network (SNN) of 2x1 neurons with online biological-plausible learning. The AEC yields two spike-trains: UP spikes that account for the positive slope signal and DOWN spikes that correspond to the negative slope signal. The synapses among the input and output layers are plastic and follow the spike-timing-dependent plasticity (STDP) rule. Early results show that the SNN module is able to detect ictal events with a delay of 64.98 ± 30.92 ms, consuming < 50 pW. The layout of the entire system occupies 528 µm × 278 µm.

KW - LFP signals

KW - SNN

KW - neuromorphic

KW - seizure-detection

UR - http://www.scopus.com/inward/record.url?scp=85117706427&partnerID=8YFLogxK

U2 - 10.1088/1361-6463/ac28bb

DO - 10.1088/1361-6463/ac28bb

M3 - Journal article

VL - 55

JO - Journal of Physics D: Applied Physics

JF - Journal of Physics D: Applied Physics

SN - 0022-3727

IS - 1

M1 - 014001

ER -