^{1}

^{2}

^{3}

^{1}

^{2}

^{3}

^{2}

^{3}

^{4}

^{4}

^{2}

^{3}

^{1}

^{5}

^{*}

^{1}

^{2}

^{3}

^{4}

^{5}

Edited by: Ulrich G. Hofmann, Universitätsklinikum Freiburg, Germany

Reviewed by: Luca Berdondini, Fondazione Istituto Italiano di Tecnologia, Italy; Sara L. Gonzalez Andino, Geneva University Hospitals (HUG), Switzerland

This article was submitted to Neural Technology, a section of the journal Frontiers in Neuroscience

This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

Developing new standardized tools to characterize brain recording devices is critical to evaluate neural probes and for translation to clinical use. The signal-to-noise ratio (SNR) measurement is the gold standard for quantifying the performance of brain recording devices. Given the drawbacks with the SNR measure, our first objective was to devise a new method to calculate the SNR of neural signals to distinguish signal from noise. Our second objective was to apply this new SNR method to evaluate electrodes of three different materials (platinum black, Pt; carbon nanotubes, CNTs; and gold, Au) co-localized in tritrodes to record from the same cortical area using specifically designed multielectrode arrays. Hence, we devised an approach to calculate SNR at different frequencies based on the features of cortical slow oscillations (SO). Since SO consist in the alternation of silent periods (Down states) and active periods (Up states) of neuronal activity, we used these as noise and signal, respectively. The spectral SNR was computed as the power spectral density (PSD) of Up states (signal) divided by the PSD of Down states (noise). We found that Pt and CNTs electrodes have better recording performance than Au electrodes for the explored frequency range (5–1500 Hz). Together with two proposed SNR estimators for the lower and upper frequency limits, these results substantiate our SNR calculation at different frequency bands. Our results provide a new validated SNR measure that provides rich information of the performance of recording devices at different brain activity frequency bands (<1500 Hz).

Interfacing the brain using electrodes to record from and stimulate it is a standard approach for investigating brain function. Multielectrode arrays (MEAs) in particular are widely used devices, both in basic research and in the clinic, that can record electrophysiological signals simultaneously from different neuronal populations. MEAs have been used in basic research to study brain function in

Besides electrode limitations, it is important to consider that recording systems have to ensure an amplification stage as close as possible to the recording site by means of a high common mode rejection (the ability to reject common noise in the active and reference electrode) in order to reduce external noise and ensure stable recordings. This can be achieved by a large input impedance in the amplifier (normally in the order of TΩ at 1 kHz) (

Current approaches for assessing SNR in brain recordings rely mostly on the amplitude of the signal. For instance, some reported methodologies are based on the recording of evoked (

In brain recordings, the frequency bands of interest include the LFP (<500 Hz), MUA (200–1500 Hz) (

The aims of this study were: (1) to develop and validate a new approach to quantify the SNR of brain recording devices; and (2) to compare the throughput of co-localized electrodes of different materials, namely Au, CNTs and Pt. For these purposes, we used an adaptation of the SNR calculation based on the features of the slow oscillations, which we recorded using MEAs with electrodes of the three aforementioned materials distributed in tritrodes and stereotrodes. The integration of three materials in close vicinity within the same MEA allowed the direct comparison between them, thereby avoiding the problem of comparing electrodes from different probes and/or electronic systems, and avoiding recording different neural activity patterns coming from distant neuronal populations.

Signal-to-noise ratio is defined as the ratio of the power spectral density (PSD) of a signal (meaningful information) with respect to the power of the background noise. In the analysis of brain recordings, this measure is commonly applied in spike sorting to select the best recording location, and also to characterize the reliability of neural information transmission (

Where

where

To easily quantify the performance of each material, thereby avoiding the vast amounts of information obtained through the spectral analysis, we proposed and validated a set of SNR estimators. The advantage of using these SNR estimators is that they reduce and summarize the large amount of information provided by the spectral SNR, since the spectral SNR gives a value of SNR at each different frequency. These estimators are derived from the spectral SNR curve (Eq. 2), or directly from the LFP signal.

The area under the spectral SNR curve within the frequency range from 5 to 1500 Hz, where 5 Hz is the minimum frequency allowed by the PSD and 1500 Hz is the upper limit of the MUA band. It is calculated as follows:

where _{0} the lowest frequency of the band and

The AUC can also be calculated for defined frequency bands. In our case, we chose three frequency bands of interest: low (5–30 Hz), middle (30–200 Hz), and high (200–1500 Hz). The low band ranges from the limit of resolution of the PSD (5 Hz) to the upper limit of the β band (30 Hz). The middle band ranges from the lower limit of the γ band (30 Hz) to the lower limit of the MUA band (200 Hz). Finally, the high band corresponds to a part of the MUA band (>200 Hz).

Frequency at which the spectral SNR equals zero. At this point, the power of the signal is exactly the same as the power of the noise.

This is the most widely reported approach to compute the SNR in LFP recordings in animals under anesthesia (

Flexible microprobes integrating 16 Au microelectrodes were fabricated using SU-8 negative photoresist as flexible substrate as previously described (

Cortical multielectrode arrays (MEAs).

Au electrodes on individual devices were electrochemically coated with a porous layer of platinum black to reduce their impedance through a customized process of platinization (

Carbon nanotubes were synthesized by the arc-discharge method using graphite electrodes and a Ni/Y 4/1% metal catalyst mixture. As-grown single-walled carbon nanotubes (agSWCNTs; initial nanotube concentration: 4 mg/ml) were dispersed ultrasonically in aqueous 1% sodium dodecylbenzenesulfonates (SDBS) solution. Afterward, the dispersion was centrifuged at 13,000 rpm for 30 min (Hermle Z383, Hermle Labortechnik, Wehingen, Germany) in order to increase their purity and decrease their metal content (

Electrodeposition of the composite material was carried out in galvanostatic conditions (0.13 mg/ml gSWCNTs, buffer phosphate with 0.05 M dihydrogen phosphate and 0.05 M monohydrogen phosphate solutions, 3.2 mM SDBS and 0.14 M pyrrole) using a constant current value of 3 mA ⋅ cm^{-2} during 120 s. An Ag/AgCl (3 M NaCl) electrode was used as a reference electrode, and a graphite bar was used as a counter electrode.

Figure

This study was carried out in accordance with Spanish regulatory laws (BOE-A-2013-6271), which comply with the European Union guidelines on protection of vertebrates used for experimentation (Directive 2010/63/EU of the European Parliament and the Council of September 22, 2010). The protocol was approved by the ethics committee of Hospital Clinic Barcelona. Two ferrets (5-month-old, male) were anesthetized with sodium pentobarbital and decapitated. The entire forebrain was rapidly removed and placed in oxygenated cold (4–10°C) bathing medium. Coronal slices (0.4-mm thick) from the occipital cortex containing primary and secondary visual cortical areas (areas 17, 18, and 19) were used (_{4}, 2; NaH_{2}PO_{4}, 1.25; CaCl_{2}, 2; NaHCO_{3}, 26; dextrose, 10, and was aerated with 95% O_{2}, 5% CO_{2} to a final pH of 7.4. The modified solution had the same ionic composition except for different levels of (in mM): KCl, 4; MgSO_{4}, 1 and CaCl_{2}, 1–1.2 (

Multielectrode arrays attached to a ZIF connector were placed on the slices. The data acquisition system comprised a 16-channel preamplifier (μPA16, Multichannel Systems, Germany) and amplifier (PGA16, Multichannel Systems, Germany) with a 100× gain factor, and a CED 1401 digitizer and Spike 2 software (Cambridge Electronic Design, United Kingdom). The sampling frequency of the recordings was set to 5 kHz.

Recordings of 20–60 s duration only from operative tritrodes and stereotrodes were selected for the analysis. From optical imaging and EIS characterization (Figure _{Pt} = _{CNTs} = 102 and _{Au} = 67 recordings.

Signal analysis was performed using MATLAB 2012a (The MathWorks Inc., Natick, MA, United States). Up and Down state detection was performed as in

Once the detection was performed, the PSD with a resolution of 1024 points of the fast Fourier transform (FFT) was calculated for every Up and Down state separately using Welch’s method (window size 1024 time bins with an overlap of 512 time bins). The mean PSD of the Up states and Down states in the recording fragment were calculated. The same approach was employed to calculate the mean peak-to-peak amplitude of all the Up states and the mean SD of all the Down states.

The Spectral SNR was calculated for every electrode recording using Eq. (2). From the Spectral SNR, AUC was calculated by a trapezoidal numerical integration along the three different defined frequency bands. FLOD was estimated by smoothing the spectral SNR curve to easily find the intersection with zero. The smoothing filter we used is based on a moving average method with a span of 10 ms. vSNR was calculated as the mean peak-to-peak amplitude of Up states divided by the mean SD of the Down states.

For the statistical analyses, the Kolmogorov–Smirnov test was performed for every SNR estimator distribution separately for each material to test the normality. Because none of the distributions was normal, non-parametric tests were applied to assess statistical differences between materials. More specifically, we used the Wilcoxon signed-rank test to compare the SNR distributions of different materials at every frequency, the Mann–Whitney test to assess differences in estimator distributions between different materials, and Pearson correlation coefficient to quantify the degree of association between SNR estimators. A non-parametric ANOVA test equivalent for independent samples (Kruskal–Wallis test) was performed for all the data separately for each MEA, tritrode/stereotrode and material using IBM SPSS 22 statistics software.

Five MEAs with electrodes of the three different materials (Au, CNTs and Pt) arranged in tritrodes and stereotrodes were tested on seven different visual cortical slices that generated spontaneous slow oscillations (Figure

Local field potential (LFP) traces from a representative tritrode showing the recording of spontaneous cortical slow oscillations

Since the electrode SNR depends, among other things, on the impedance, the SNR is frequency-dependent. For this reason, measuring the SNR at different biological frequencies is crucial in electrode characterization. The spectral SNR curve was computed for each electrode recording and the results were grouped into materials in order to compare them. Overall, from the spectral SNR analysis, we found that Pt as well as CNTs electrodes showed significantly higher SNR values than Au electrodes for all the functional frequencies (frequencies with SNR > 0 dB) (Figure

Spectral signal-to-noise ratio (SNR). SNR was calculated as in Eq. (2) giving a SNR value for each frequency ranging from 5 to 1500 Hz. The spectral SNR curve was calculated for the electrodes of the three different materials and the mean SNR curve of the five MEAs was tested in seven slices. The horizontal line at zero represents _{PSD} = _{PSD}). Vertical lines separate the three frequency bands: low, 5–30; medium, 30–200; and high, 200–1500 Hz. Inset; Mean power spectral density of Up and Down states (solid and dotted lines, respectively). ^{∗}

More specifically, SNR values for the low-frequency band (5–30 Hz) were almost constant for the three materials (Figure _{PSD}/_{PSD} = 10^{SNR/10}). For frequencies over 50 Hz, the SNR decayed almost linearly following the typical 1/

The SNR distribution curves represent the mean behavior of different stereotrodes and tritrodes (Figure

Spectral SNR distribution and area under the spectral SNR curve (AUC) for three different frequency bands. ^{∗}^{∗∗∗}_{Pt} = _{CNTs} = 102 and _{Au} = 67 electrode recordings.

The area under the spectral SNR curve (AUC) was calculated as an SNR estimator, and the distributions of normalized AUC values for the three defined frequency bands (low: 5–30 Hz, middle: 30–200 Hz, high: 200–1500 Hz) were represented in boxplots for the three different materials. For the three frequency bands, the AUC for the Pt and CNTs electrodes was significantly higher than for the Au electrodes (

The results from the spectral SNR analysis shed light on the recording performance of the electrodes for the whole spectral range from 5 to 1500 Hz. The analyzed data show significant differences between Au and Pt, and between Au and CNTs electrodes, indicating that Pt and CNTs electrodes record the brain signals better than Au electrodes for the whole range of studied frequencies. No significant differences were found between Pt and CNTs electrodes but our results suggest that Pt electrodes had a slightly better performance than CNTs electrodes. Finally, our findings validate that the AUC estimator, computed at different selected frequency bands, properly describes the overall behavior of the electrodes in terms of SNR for low, middle, and high frequency ranges.

As described above, vSNR and FLOD were calculated as estimators to complement and validate the results obtained with the spectral SNR analysis. Our findings show that vSNR, FLOD, and AUC show the same qualitative results, reinforcing the outcome of the previous SNR analysis (Figure

vSNR and FLOD estimators for lower and higher frequencies, respectively. ^{∗∗}^{∗∗∗}

As vSNR is calculated using the amplitude of the signal during Up states and the SD of the Down states, vSNR values are expected to describe the SNR at frequencies related to the slow oscillations (>1 Hz); that is, very low frequencies. In agreement with this, the results shown in the vSNR boxplot (Figure

To confirm that vSNR is related to the SNR at lower frequencies, a linear correlation was performed with the different AUC distributions at the three frequency bands (Figure

Correlation between SNR estimators (vSNR, FLOD and total AUC) and AUC for different frequency ranges.

Since FLOD is the value of the frequency at which the SNR is zero, it is easy to relate this estimator to the SNR value at the highest frequencies. Comparing the results of FLOD distributions for each material (Figure

The total AUC distribution is dominated by high frequencies (200–1500 Hz) since there are more frequency points within this range and, despite the SNR values being low, the AUC is large due to the frequency variable (note that in the spectral SNR in Figure

In this work, we have developed and validated a novel method for characterizing the performance of brain recording devices based on a spectral SNR analysis using cortical slow oscillations. The validation was performed by applying this method to characterize and compare electrodes made of three different materials (Au, CNTs and Pt) organized in tritrodes. We also report here that electrodes made of platinum black and carbon nanotubes have better recording performance than electrodes made of gold for the whole functional frequency range that we explored (from 5 to 1500 Hz). Furthermore, Pt electrodes showed a trend toward working better than CNTs electrodes even though the difference did not reach statistical significance. Although these results can be qualitatively predicted from impedance characterization (i.e., directly related to the specific surface area of the electrode site; see Supplementary Figure

The design of the probes was intended to compare the materials while minimizing the interferences derived from recording from different neuronal populations by using co-localized electrodes arranged in tritrodes and stereotrodes. Because our

There are some differences between measurements carried out by injecting artificial currents in saline solution electrolyte (as in EIS; see Supplementary Figure

The results from the spectral SNR analysis provide a large amount of data since they give an SNR value for each frequency. Therefore, the use of SNR estimators that give an overall idea of the behavior under certain conditions is especially helpful. Because of this, we defined and validated some SNR estimators extracted from the spectral SNR analysis. On the one hand, we defined several SNR estimators from the spectral SNR analysis: total AUC, the AUC for different frequency bands of biological interest (5–30 Hz, 30–200 Hz and 200–1500 Hz), and the FLOD. On the other hand, we also calculated the vSNR, which is the standard approach to calculating SNR in LFP recordings (

Searching in the literature for SNR calculation methods, we found two different methodologies estimating the SNR at different frequencies that we consider to be worthy of note. The first one involved estimating the SNR from recordings of spike and wave discharges (SWDs) during spontaneous epileptiform activity in an animal model of absence epilepsy (

In order to overcome these drawbacks, we propose a SNR methodology based on the slow oscillatory state that arises during anesthesia and during non-REM sleep in typical

To sum up, we present a detailed SNR analysis to quantify and compare the performance of different devices to record brain activity. Neural MEAs with electrodes of different materials arranged in co-localized tritrodes and stereotrodes were used to record slow oscillations from the cerebral cortex network. This approach was designed to avoid the interferences from external variables and thus enable a proper comparison between electrodes. The results shed light on the recording behavior of electrodes made of different materials in a broad range of biological frequencies showing that platinum black as well as carbon nanotubes electrodes have better working performance than gold electrodes. Furthermore, the results obtained here parallel previous studies involving some of the tested materials, hence reinforcing the validation of the proposed SNR approach. The work here exposed is also intended to validate and standardize a methodology for quantifying the SNR in different types of brain recording devices such as electrodes or transistors.

GG and MVSV designed the MEA and tritrodes. GG, XI, AGB, JHF, MM, and RV fabricated and characterized the MEAs. BR and MVSV designed and performed the

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

We would like to thank Núria Tort-Colet for suggestions for data analysis and Cristina Gonzalez-Liencres and Tony Donegan for editing assistance. This work has made use of the Spanish ICTS Network MICRONANOFABS partially supported by MINECO and the ICTS ‘NANBIOSIS’, more specifically by the Micro-NanoTechnology Unit of the CIBER in Bioengineering, Biomaterials & Nanomedicne (CIBER-BBN) at the IMB-CNM.

The Supplementary Material for this article can be found online at: