An electronic neuromorphic system for real-time detection of High Frequency Oscillations (HFOs) in intracranial EEG

In this work, we present a neuromorphic system that combines for the first time a neural recording headstage with a signal-to-spike conversion circuit and a multi-core spiking neural network (SNN) architecture on the same die for recording, processing, and detecting High Frequency Oscillations (HFO), which are biomarkers for the epileptogenic zone. The device was fabricated using a standard 0.18$\mu$m CMOS technology node and has a total area of 99mm$^{2}$. We demonstrate its application to HFO detection in the iEEG recorded from 9 patients with temporal lobe epilepsy who subsequently underwent epilepsy surgery. The total average power consumption of the chip during the detection task was 614.3$\mu$W. We show how the neuromorphic system can reliably detect HFOs: the system predicts postsurgical seizure outcome with state-of-the-art accuracy, specificity and sensitivity (78%, 100%, and 33% respectively). This is the first feasibility study towards identifying relevant features in intracranial human data in real-time, on-chip, using event-based processors and spiking neural networks. By providing "neuromorphic intelligence" to neural recording circuits the approach proposed will pave the way for the development of systems that can detect HFO areas directly in the operation room and improve the seizure outcome of epilepsy surgery.

[1]  Reid R. Harrison,et al.  The Design of Integrated Circuits to Observe Brain Activity , 2008, Proceedings of the IEEE.

[2]  Jean Gotman,et al.  High‐frequency oscillations: The state of clinical research , 2017, Epilepsia.

[3]  Manuel Delgado-Restituto,et al.  A Sub- $\mu$ W Reconfigurable Front-End for Invasive Neural Recording That Exploits the Spectral Characteristics of the Wideband Neural Signal , 2020, IEEE Transactions on Circuits and Systems I: Regular Papers.

[4]  Eduardo D. Sontag,et al.  Neural Systems as Nonlinear Filters , 2000, Neural Computation.

[5]  Philippa J. Karoly,et al.  Seizure forecasting and cyclic control of seizures , 2020, Epilepsia.

[6]  Misha Anne Mahowald,et al.  VLSI analogs of neuronal visual processing: a synthesis of form and function , 1992 .

[7]  M. Zijlmans,et al.  Changing concepts in presurgical assessment for epilepsy surgery , 2019, Nature Reviews Neurology.

[8]  Andreas Hierlemann,et al.  Switch-Matrix-Based High-Density Microelectrode Array in CMOS Technology , 2010, IEEE Journal of Solid-State Circuits.

[9]  D. Mogul,et al.  Using Automated Detection and Classification of Interictal HFOs to Improve the Identification of Epileptogenic Zones in Preparation for Epilepsy Surgery , 2019, bioRxiv.

[10]  Franco Maloberti,et al.  Implantable Monitoring System for Epilepsy , 2020 .

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

[12]  Tobi Delbrück,et al.  Bias Current Generators with Wide Dynamic Range , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[13]  Giacomo Indiveri,et al.  A Scalable Multicore Architecture With Heterogeneous Memory Structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs) , 2017, IEEE Transactions on Biomedical Circuits and Systems.

[14]  Bernabe Linares-Barranco,et al.  Hardware Implementation of Deep Network Accelerators Towards Healthcare and Biomedical Applications , 2020, IEEE Transactions on Biomedical Circuits and Systems.

[15]  R. Polikar,et al.  Ensemble based systems in decision making , 2006, IEEE Circuits and Systems Magazine.

[16]  R.R. Harrison,et al.  A Low-Power Integrated Circuit for a Wireless 100-Electrode Neural Recording System , 2006, IEEE Journal of Solid-State Circuits.

[17]  Minkyu Je,et al.  A Sub-µW/Ch Analog Front-End for Δ-Neural Recording With Spike-Driven Data Compression , 2019, IEEE Trans. Biomed. Circuits Syst..

[18]  Giacomo Indiveri,et al.  A neuromorphic systems approach to in-memory computing with non-ideal memristive devices: From mitigation to exploitation , 2018, Faraday discussions.

[19]  Aurel A. Lazar,et al.  The power of connectivity: Identity preserving transformations on visual streams in the spike domain , 2013, Neural Networks.

[20]  Gian Nicola Angotzi,et al.  SiNAPS: An implantable active pixel sensor CMOS-probe for simultaneous large-scale neural recordings. , 2019, Biosensors & bioelectronics.

[21]  Jean Gotman,et al.  The morphology of high frequency oscillations (HFO) does not improve delineating the epileptogenic zone , 2016, Clinical Neurophysiology.

[22]  Chiara Bartolozzi,et al.  Neuromorphic Electronic Circuits for Building Autonomous Cognitive Systems , 2014, Proceedings of the IEEE.

[23]  Tobi Delbruck,et al.  A Dynamic Vision Sensor With 1% Temporal Contrast Sensitivity and In-Pixel Asynchronous Delta Modulator for Event Encoding , 2015, IEEE Journal of Solid-State Circuits.

[24]  Matthias Dümpelmann,et al.  How to record high‐frequency oscillations in epilepsy: A practical guideline , 2017, Epilepsia.

[25]  Kai-Wen Yao,et al.  A bandwidth-tunable bioamplifier with voltage-controlled symmetric pseudo-resistors , 2015, Microelectron. J..

[26]  Tommaso Fedele,et al.  Prediction of seizure outcome improved by fast ripples detected in low-noise intraoperative corticogram , 2017, Clinical Neurophysiology.

[27]  Big data needs a hardware revolution , 2018, Nature.

[28]  Chiara Bartolozzi,et al.  Synaptic Dynamics in Analog VLSI , 2007, Neural Computation.

[29]  Rahul Sarpeshkar,et al.  An Energy-Efficient Micropower Neural Recording Amplifier , 2007, IEEE Transactions on Biomedical Circuits and Systems.

[30]  Giacomo Indiveri,et al.  Frontiers in Neuromorphic Engineering , 2011, Front. Neurosci..

[31]  Kwabena Boahen,et al.  Point-to-point connectivity between neuromorphic chips using address events , 2000 .

[32]  Giacomo Indiveri,et al.  Real-Time Ultra-Low Power ECG Anomaly Detection Using an Event-Driven Neuromorphic Processor , 2019, IEEE Transactions on Biomedical Circuits and Systems.

[33]  J. Sarnthein,et al.  High-density ECoG improves the detection of high frequency oscillations that predict seizure outcome , 2019, Clinical Neurophysiology.

[34]  Rodney J. Douglas,et al.  A pulse-coded communications infrastructure for neuromorphic systems , 1999 .

[35]  Romain Brette,et al.  Neuroinformatics Original Research Article Brian: a Simulator for Spiking Neural Networks in Python , 2022 .

[36]  Giacomo Indiveri,et al.  ECG-based Heartbeat Classification in Neuromorphic Hardware , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[37]  Thomas Grunwald,et al.  Resection of high frequency oscillations predicts seizure outcome in the individual patient , 2017, Scientific Reports.

[38]  Reid R. Harrison,et al.  A low-power, low-noise CMOS amplifier for neural recording applications , 2002, 2002 IEEE International Symposium on Circuits and Systems. Proceedings (Cat. No.02CH37353).

[39]  P. Krsek,et al.  The clinical utility of intraoperative electrocorticography in pediatric epilepsy surgical strategy and planning. , 2020, Journal of Neurosurgery: Pediatrics.

[40]  Giacomo Indiveri,et al.  A Neuromorphic Event-Based Neural Recording System for Smart Brain-Machine-Interfaces , 2015, IEEE Transactions on Biomedical Circuits and Systems.

[41]  Carver A. Mead,et al.  Neuromorphic electronic systems , 1990, Proc. IEEE.

[42]  P. Gosselaar,et al.  The value of intra-operative electrographic biomarkers for tailoring during epilepsy surgery: from group-level to patient-level analysis , 2020, Scientific Reports.

[43]  Vijay Viswam,et al.  A 1024-Channel CMOS Microelectrode Array With 26,400 Electrodes for Recording and Stimulation of Electrogenic Cells In Vitro , 2014, IEEE Journal of Solid-State Circuits.

[44]  Jan Craninckx,et al.  A Compact Quad-Shank CMOS Neural Probe With 5,120 Addressable Recording Sites and 384 Fully Differential Parallel Channels , 2019, IEEE Transactions on Biomedical Circuits and Systems.

[45]  J. Gotman,et al.  Intracranial EEG in the 21st Century , 2020, Epilepsy currents.

[46]  Tommaso Fedele,et al.  Automatic detection of high frequency oscillations during epilepsy surgery predicts seizure outcome , 2016, Clinical Neurophysiology.

[47]  Kwabena Boahen,et al.  Communicating neuronal ensembles between neuromorphic chips , 1998 .

[48]  Nikola Kasabov,et al.  Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition. , 2013, Neural networks : the official journal of the International Neural Network Society.

[49]  Sándor Beniczky,et al.  Machine learning and wearable devices of the future , 2020, Epilepsia.

[50]  Giacomo Indiveri,et al.  A Neuromorphic Device for Detecting High-Frequency Oscillations in Human iEEG , 2019, 2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS).

[51]  P. E. Fleischer,et al.  Design formulas for biquad active filters using three operational amplifiers , 1973 .

[52]  Giacomo Indiveri,et al.  A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses , 2015, Front. Neurosci..

[53]  P. V. van Rijen,et al.  Tailoring epilepsy surgery with fast ripples in the intraoperative electrocorticogram , 2017, Annals of neurology.

[54]  Giacomo Indiveri,et al.  Discrimination of EMG Signals Using a Neuromorphic Implementation of a Spiking Neural Network , 2019, IEEE Transactions on Biomedical Circuits and Systems.