A computer-assisted spike detecting system using normalized method for epilepsy diagnosis

This thesis was to solve the problem that tremendous amount of data of neural signal seriously confined the number of transmission channels with a limited bandwidth in a digital telemetry system. Although a spike-detection algorithm designed for data reduction had been reported, the signal in between the spikes was lost. Moreover, various non-ideal factors greatly reduced the accuracy of spike detection. This thesis used the commercialized data-compression algorithm, MPEG Layer 3 (MP3), as our data reduction scheme and evaluated its performance on spike sorting. The evaluation results showed that MP3 kept at least 80% accuracy of unit isolation. For reducing the consumption of hardware resource by MP3, MP3 algorithm was further simplified and the corresponding performance was checked. All the algorithm simplification carried out in this thesis compromised barely discernible performance. At last this thesis discussed a method for multi-channel signal analysis, ICA. The effect of MP3 on ICA after the highest level of simplification was simulated. The results showed that the miss probabilities of MP3 were considerably low, regardless of the encoding bit rate. According to all the results mentioned above, we preliminarily validated MP3 a proper neural signal compressor.

In the clinical diagnosis of epilepsy using electroencephalogram (EEG) data, an accurate automatic epileptic spikes detection system is highly useful and meaningful in that the conventional manual process is not only very tedious and time-consuming, but also subjective since it depends on the knowledge and experience of the doctors. In this paper, motivated by significant advantages and lots of achieved successes of deep learning in data mining, we apply Deep Belief Network (DBN), which is one of the breakthrough models laid the foundation for deep learning, to detect epileptic spikes in EEG data. It is really useful in practice because the promising quality evaluation of the spike detection system is higher than $90$\%. In particular, to construct accurate detection model for non-spikes and spikes, a new set of detailed features of epileptic spikes is proposed. These features were then fed to the DBN which is modified from a generative model into a discriminative model to aim at classification accuracy. The experiment results indicate that it is possible to use deep learning models for epileptic spike detection with very high performance in item of sensitivity, selectivity, specificity and accuracy 92.82%, 97.83% , 96.41%, and 96.87%, respectively.

Performance of automatic spike-detection algorithms and interrater reliability of human EEG reviewers were investigated previously by using scalp EEG recordings. However, it is not known, whether the findings of these studies hold for intracranial recordings. To address this question, we analyzed spike detection in intracranial recordings by two human reviewers and three automatic systems covering major lines in the development of automatic spike-detection systems. Intracranial recordings from subdural and intrahippocampal depth electrode contacts in seven patients were analyzed by two reviewers and three spike-detection systems: (a) The rule-based system by Gotman, (b) a two-stage system consisting of a linear predictor and a second rule-based stage, and (c) a system using wavelet coefficients of the intracranial EEG data. Agreement between the two human reviewers with respect to spike identification was <50%. The automatic systems achieved agreements of 24% (Gotman), 26% (wavelet detector), and 32% (two-stage system) with the individual human reviewers. In spite of the small proportion of agreements, the same anatomic regions were identified by human and automatic EEG analysis as generators for the majority of spikes. The poor agreement between the human EEG reviewers suggests that the definition of spikes and spike-like episodes in intracranial electrodes is far from unequivocal. Nevertheless, localizing information is highly consistent by either visual or automatic spike detection, independent of the algorithm used for automatic spike detection.

The increasing data rate has become a major issue confronting next-generation intracortical brain-machine interfaces (iBMIs). The scaling number of recording sites requires complex analog wiring and lead to huge digitization power consumption. Compressive event-based neural frontends have been used in high-density neural implants to support the simultaneous recording of more channels. Event-based frontends (EBF) convert recorded signals into asynchronous digital events via delta modulation and can inherently achieve considerable compression. But EBFs are prone to false events that do not correspond to neural and may affect the output firing rate, which is the key feature for neural decoding. Spike detection (SPD) is a key process in the iBMI pipeline to detect neural spikes and further reduce the data rate. However, conventional digital SPD suffers from the increasing buffer size and frequent memory access power, and conventional spike emphasizers are not compatible with EBFs. In this work we introduced an event-based spike detection (Ev-SPD) algorithm for scalable compressive EBFs. To implement the algorithm effectively, we proposed a novel low-power 10-T eDRAM-SRAM hybrid random-access memory (HRAM) in-memory computing (IMC) bitcell for event processing. We fabricated the proposed 1024-channel IMC SPD macro in a 65nm process and tested the macro with both synthetic dataset and Neuropixel recordings. The proposed macro achieved a high spike detection accuracy of 96.06% on a synthetic dataset and 95.08% similarity and 0.05 firing pattern MAE on Neuropixel recordings. Our event-based IMC SPD macro achieved a high per channel spike detection energy efficiency of 23.9 nW per channel and an area efficiency of 375 μm2 per channel. Our work presented a SPD scheme compatible with compressive EBFs for high-density iBMIs, achieving ultra-low power consumption with an IMC architecture while maintaining considerable accuracy.

Objective. Translational efforts on spike-signal-based implantable brain-machine interfaces (BMIs) are increasingly aiming to minimise bandwidth while maintaining decoding performance. Developing these BMIs requires advances in neuroscience and electronic technology, as well as using low-complexity spike detection algorithms and high-performance machine learning models. While some state-of-the-art BMI systems jointly design spike detection algorithms and machine learning models, it remains unclear how the detection performance affects decoding. Approach. We propose the co-design of the neural decoder with an ultra-low complexity spike detection algorithm. The detection algorithm is designed to attain a target firing rate, which the decoder uses to modulate the input features preserving statistical invariance in long term (over several months). Main results. We demonstrate a multiplication-free fixed-point spike detection algorithm with an average detection accuracy of 97% across different noise levels on a synthetic dataset and the lowest hardware complexity among studies we have seen. By co-designing the system to incorporate statistically invariant features, we observe significantly improved long-term stability, with decoding accuracy degrading by less than 10% after 80 days of operation. Our analysis also reveals a nonlinear relationship between spike detection and decoding performance. Increasing the detection sensitivity improves decoding accuracy and long-term stability, which means the activity of more neurons is beneficial despite the detection of more noise. Reducing the spike detection sensitivity still provides acceptable decoding accuracy whilst reducing the bandwidth by at least 30%. Significance. Our findings regarding the relationship between spike detection and decoding performance can provide guidance on setting the threshold for spike detection rather than relying on training or trial-and-error. The trade-off between data bandwidth and decoding performance can be effectively managed using appropriate spike detection settings. We demonstrate improved decoding performance by maintaining statistical invariance of input features. We believe this approach can motivate further research focused on improving decoding performance through the manipulation of data itself (based on a hypothesis) rather than using more complex decoding models.

Epilepsy is a neurological disorder classified as the second most serious neurological disease known to humanity, after stroke. Magnetoencephalography (MEG) is performed to localize the epileptogenic zone in the brain. However, the detection of epileptic spikes requires the visual assessment of long MEG recordings. This task is time-consuming and might lead to wrong decisions. Therefore, the introduction of effective machine learning algorithms for the quick and accurate epileptic spikes detection from MEG recordings would improve the clinical diagnosis of the disease. The efficiency of machine learning based algorithms requires a good characterization of the signal by extracting pertinent features. In this paper, we propose new sets of features for MEG signals. These features are based on a Semi-Classical Signal Analysis (SCSA) method, which allows a good characterization of peak shaped signals. Moreover, this method improves the spike detection accuracy and reduces the feature vector size. We could achieve up to 93.68% and 95.08% in average sensitivity and specificity, respectively. We used the 5-folds cross-validation applied to a balanced dataset of 3104 frames, extracted from eight healthy and eight epileptic subjects with a frame size of 100 samples with a step size of 2 samples, using Random Forest (RF) classifier.

Existing deep learning models for wheat ear counting are structurally complex with a large number of parameters, making them difficult to deploy on storage-limited drone edge devices. Moreover, the dense arrangement and mutual occlusion of wheat ear in the field present significant challenges for accurate automated counting. To address these, this paper proposes an innovative lightweight network for detecting and counting wheat ear. It overcomes the deployment challenges of existing models on edge devices due to complexity and designs a drone edge computing solution for real-time counting. This solution incorporates a result caching mechanism to optimize data processing and storage, improving task efficiency and system response. The improved model introduces a gather-and-distribute mechanism for efficient multi-scale feature fusion and integrates an attention-scale sequence fusion module to enhance small target detection. Additionally, the dynamic head detection module optimizes the model's ability to perceive scale, spatial details, and task-specific features. For lightweight optimization, pruning and knowledge distillation techniques reduce computational requirements while maintaining high accuracy. Experimental results show that the improved YOLOv8n model achieves 95.2% mAP and 93.8% detection accuracy in spike detection, an increase of 3.0% and 2.4%, respectively, over the previous version. After lightweight optimization, the model size reduces to 5.6MB, and the FPS reaches 369.2, resulting in a 57.3% reduction in model size and a 116% increase in FPS. These results indicate that the model occupies fewer resources and storage space while ensuring accuracy, making it suitable for deployment on drone edge devices for real-time, accurate wheat ear counting.

Real time on-chip spike detection is the first step in decoding neural spike trains in implantable brain machine interface systems. Nonlinear Energy Operator (NEO) is a transform widely used to distinguish neural spikes from background noise. In this paper we define a general form of energy operators, of which NEO is a specific example, which gives better spike-noise separation than NEO and its derivatives. This is because of a non-linear scaling applied to the general discrete energy operator. Using two well-known publically available datasets, the performance of several operators is compared. On data sets that contain multi-unit spikes with low Signal to Noise ratio, the detection accuracy was improved by approximately 15%.

This paper introduces a novel greedy model for spike detection system aimed to neural signal obtained from the brain such as EEG, ECOG. This Presented algorithm combines wavelet transform and simultaneous orthogonal matching pursuit (SOMP). The proposed method is capable of data compression for spike detection. The spike detection experiment demonstrates the TPR in ROC curve is up to 98.76% and the compact factor reaches 42.52 when the length of window we used is 500. Moreover, our method is simple for low power system design and real-time hardware realization.

Spike detection approaches for noisy neuronal data: Assessment and comparison

In this research, we study the effect of feature selection in the spike detection and sorting accuracy. We introduce a new feature representation for neural spikes from multichannel recordings. The features selection plays a significant role in analyzing the response of brain neurons. The more precise selection of features leads to a more accurate spike sorting, which can group spikes more precisely into clusters based on the similarity of spikes. Proper spike sorting will enable the association between spikes and neurons. Different with other threshold-based methods, the cepstrum of spike signals is employed in our method to select the candidates of spike features. To choose the best features among different candidates, the Kolmogorov-Smirnov (KS) test is utilized. Then, we rely on the super paramagnetic method to cluster the neural spikes based on KS features. Simulation results demonstrate that the proposed method not only achieve more accurate clustering results but also reduce computational burden, which implies that it can be applied into real-time spike analysis.

Real time spike detection is an important requirement for developing brain machine interfaces (BMIs). We examined three classes of spike-detection algorithms to determine which is best suited for a wireless BMI with a limited transmission bandwidth and computational capabilities. The algorithms were analyzed by tabulating true and false detections when applied to a set of realistic artificial neural signals with known spike times and varying signal to noise ratios. A design-specific cost function was developed to score the relative merits of each detector; correct detections increased the score, while false detections and computational burden reduced it. Test signals both with and without overlapping action potentials were considered. We also investigated the utility of rejecting spikes that violate a minimum refractory period by occurring within a fixed time window after the preceding threshold crossing. Our results indicate that the cost-function scores for the absolute value operator were comparable to those for more elaborate nonlinear energy operator based detectors. The absolute value operator scores were enhanced when the refractory period check was used. Matched-filter-based detectors scored poorly due to their relatively large computational requirements that would be difficult to implement in a real-time system.

Paper fibers allow the high dispersion of a fluorescent polythiophene chemosensor for the suppression of aggregation-induced quenching, which is applied to the solid-state fluorescent quantitative sensing of metal ions using imaging analysis and pattern recognition techniques.

Detection of interictal discharges is a key element of interpreting EEGs during the diagnosis and management of epilepsy. Because interpretation of clinical EEG data is time-intensive and reliant on experts who are in short supply, there is a great need for automated spike detectors. However, attempts to develop general-purpose spike detectors have so far been severely limited by a lack of expert-annotated data. Huge databases of interictal discharges are therefore in great demand for the development of general-purpose detectors. Detailed manual annotation of interictal discharges is time consuming, which severely limits the willingness of experts to participate. To address such problems, a graphical user interface "SpikeGUI" was developed in our work for the purposes of EEG viewing and rapid interictal discharge annotation. "SpikeGUI" substantially speeds up the task of annotating interictal discharges using a custom-built algorithm based on a combination of template matching and online machine learning techniques. While the algorithm is currently tailored to annotation of interictal epileptiform discharges, it can easily be generalized to other waveforms and signal types.

Smoke spikes occurring during transient engine operation have detrimental health effects and increase fuel consumption by requiring more frequent regeneration of the diesel particulate filter. This paper proposes a decision tree approach to real-time detection of smoke spikes for control and on-board diagnostics purposes. A contemporary, electronically controlled heavy-duty diesel engine was used to investigate the deficiencies of smoke control based on the fuel-to-oxygen-ratio limit. With the aid of transient and steady state data analysis and empirical as well as dimensional modeling, it was shown that the fuel-to-oxygen ratio was not estimated correctly during the turbocharger lag period. This inaccuracy was attributed to the large manifold pressure ratios and low exhaust gas recirculation flows recorded during the turbocharger lag period, which meant that engine control module correlations for the exhaust gas recirculation flow and the volumetric efficiency had to be extrapolated. The engine control module correlations were based on steady state data and it was shown that, unless the turbocharger efficiency is artificially reduced, the large manifold pressure ratios observed during the turbocharger lag period cannot be achieved at steady state. Additionally, the cylinder-to-cylinder variation during this period were shown to be sufficiently significant to make the average fuel-to-oxygen ratio a poor predictor of the transient smoke emissions. The steady state data also showed higher smoke emissions with higher exhaust gas recirculation fractions at constant fuel-to-oxygen-ratio levels. This suggests that, even if the fuel-to-oxygen ratios were to be estimated accurately for each cylinder, they would still be ineffective as smoke limiters. A decision tree trained on snap throttle data and pruned with engineering knowledge was able to use the inaccurate engine control module estimates of the fuel-to-oxygen ratio together with information on the engine control module estimate of the exhaust gas recirculation fraction, the engine speed, and the manifold pressure ratio to predict 94% of all spikes occurring over the Federal Test Procedure cycle. The advantages of this non-parametric approach over other commonly used parametric empirical methods such as regression were described. An application of accurate smoke spike detection in which the injection pressure is increased at points with a high opacity to reduce the cumulative particulate matter emissions substantially with a minimum increase in the cumulative nitrogrn oxide emissions was illustrated with dimensional and empirical modeling.