Faculty Publications

Permanent URI for this collection

https://hdl.handle.net/1911/75173

This collection includes faculty journal articles deposited per Rice's Open Access Policy and additional faculty work. Items found in this collection can also be found in the authors' departmental faculty publication collections.

Browse

Now showing 1 - 14 of 14

A graph-based cardiac arrhythmia classification methodology using one-lead ECG recordings
(Elsevier, 2024) EPMoghaddam, Dorsa; Muguli, Ananya; Razavi, Mehdi; Aazhang, Behnaam
In this study, we present a novel graph-based methodology for an accurate classification of cardiac arrhythmia diseases using a single-lead electrocardiogram (ECG). The proposed approach employs the visibility graph technique to generate graphs from time signals. Subsequently, informative features are extracted from each graph and then fed into classifiers to match the input ECG signal with the appropriate target arrhythmia class. The six target classes in this study are normal (N), left bundle branch block (LBBB), right bundle branch block (RBBB), premature ventricular contraction (PVC), atrial premature contraction (A), and fusion (F) beats. Three classification models were explored, including graph convolutional neural network (GCN), multi-layer perceptron (MLP), and random forest (RF). ECG recordings from the MIT-BIH arrhythmia database were utilized to train and evaluate these classifiers. The results indicate that the multi-layer perceptron model attains the highest performance, showcasing an average accuracy of 99.02%. Following closely, the random forest achieves a strong performance as well, with an accuracy of 98.94% while providing critical intuitions.
Addressing indirect frequency coupling via partial generalized coherence
(Springer Nature, 2021) Young, Joseph; Homma, Ryota; Aazhang, Behnaam
Distinguishing between direct and indirect frequency coupling is an important aspect of functional connectivity analyses because this distinction can determine if two brain regions are directly connected. Although partial coherence quantifies partial frequency coupling in the linear Gaussian case, we introduce a general framework that can address even the nonlinear and non-Gaussian case. Our technique, partial generalized coherence (PGC), expands prior work by allowing pairwise frequency coupling analyses to be conditioned on other processes, enabling model-free partial frequency coupling results. By taking advantage of recent advances in conditional mutual information estimation, we are able to implement our technique in a way that scales well with dimensionality, making it possible to condition on many processes and produce a partial frequency coupling graph. We analyzed both linear Gaussian and nonlinear simulated networks. We then performed PGC analysis of calcium recordings from mouse olfactory bulb glomeruli under anesthesia and quantified the dominant influence of breathing-related activity on the pairwise relationships between glomeruli for breathing-related frequencies. Overall, we introduce a technique capable of eliminating indirect frequency coupling in a model-free way, empowering future research to correct for potentially misleading frequency interactions in functional connectivity analyses.
Computational modeling and minimization of unintended neuronal excitation in a LIFU stimulation
(Springer Nature, 2023) Fan, Boqiang; Goodman, Wayne; Cho, Raymond Y.; Sheth, Sameer A.; Bouchard, Richard R.; Aazhang, Behnaam
The neuromodulation effect of low-intensity focused ultrasound (LIFU) is highly target-specific. Unintended off-target neuronal excitation can be elicited when the beam focusing accuracy and resolution are limited, whereas the resulted side effect has not been evaluated quantitatively. There is also a lack of methods addressing the minimization of such side effects. Therefore, this work introduces a computational model of unintended neuronal excitation during LIFU neuromodulation, which evaluates the off-target activation area (OTAA) by integrating an ultrasound field model with the neuronal spiking model. In addition, a phased array beam focusing scheme called constrained optimal resolution beamforming (CORB) is proposed to minimize the off-target neuronal excitation area while ensuring effective stimulation in the target brain region. A lower bound of the OTAA is analytically approximated in a simplified homogeneous medium, which could guide the selection of transducer parameters such as aperture size and operating frequency. Simulations in a human head model using three transducer setups show that CORB markedly reduces the OTAA compared with two benchmark beam focusing methods. The high neuromodulation resolution demonstrates the capability of LIFU to effectively limit the side effects during neuromodulation, allowing future clinical applications such as treatment of neuropsychiatric disorders.
EMvelop stimulation: minimally invasive deep brain stimulation using temporally interfering electromagnetic waves
(IOP Publishing, 2022) Ahsan, Fatima; Chi, Taiyun; Cho, Raymond; Sheth, Sameer A.; Goodman, Wayne; Aazhang, Behnaam
Objective. Recently, the temporal interference stimulation (TIS) technique for focal noninvasive deep brain stimulation (DBS) was reported. However, subsequent computational modeling studies on the human brain have shown that while TIS achieves higher focality of electric fields than state-of-the-art methods, further work is needed to improve the stimulation strength. Here, we investigate the idea of EMvelop stimulation, a minimally invasive DBS setup using temporally interfering gigahertz (GHz) electromagnetic (EM) waves. At GHz frequencies, we can create antenna arrays at the scale of a few centimeters or less that can be endocranially implanted to enable longitudinal stimulation and circumvent signal attenuation due to the scalp and skull. Furthermore, owing to the small wavelength of GHz EM waves, we can optimize both amplitudes and phases of the EM waves to achieve high intensity and focal stimulation at targeted regions within the safety limit for exposure to EM waves. Approach. We develop a simulation framework investigating the propagation of GHz EM waves generated by line current antenna elements and the corresponding heat generated in the brain tissue. We propose two optimization flows to identify antenna current amplitudes and phases for either maximal intensity or maximal focality transmission of the interfering electric fields with EM waves safety constraint. Main results. A representative result of our study is that with two endocranially implanted arrays of size × each, we can achieve an intensity of 12 V m−1 with a focality of at a target deep in the brain tissue. Significance. In this proof-of-principle study, we show that the idea of EMvelop stimulation merits further investigation as it can be a minimally invasive way of stimulating deep brain targets and offers benefits not shared by prior methodologies of electrical or magnetic stimulation.
Epileptic electroencephalography classification using embedded dynamic mode decomposition
(IOP Publishing, 2022) Hellar, Jennifer; Erfanian, Negar; Aazhang, Behnaam
Objective. Seizure prediction devices for drug-resistant epileptic patients could lead to improved quality of life and new treatment options, but current approaches to classification of electroencephalography (EEG) segments for early identification of the pre-seizure state typically require many features and complex classifiers. We therefore propose a novel spatio-temporal EEG feature set that significantly aids in separation and easy classification of the interictal and preictal states. Approach. We derive key spectral features from the embedded dynamic mode decomposition (EmDMD) of the brain state system. This method linearizes the complex spatio-temporal dynamics of the system, describing the dynamics in terms of a spectral basis of modes and eigenvalues. The relative subband spectral power and mean phase locking values of these modes prove to be good indicators of the preictal state that precedes seizure onset. Main results. We analyze the linear separability and classification of preictal and interictal states based on our proposed features using seizure data extracted from the CHB-MIT scalp EEG and Kaggle American Epilepsy Society Seizure Prediction Challenge intracranial EEG databases. With a light-weight support vector machine or random forest classifier trained on these features, we classify the preictal state with a sensitivity of up to 92% and specificity of up to 89%. Significance. The EmDMD-derived features separate the preictal and interictal states, improving classification accuracy and motivating further work to incorporate them into seizure prediction algorithms.
Epileptic seizure prediction using spectral width of the covariance matrix
(IOP Publishing, 2022) EPMoghaddam, Dorsa; Sheth, Sameer A.; Haneef, Zulfi; Gavvala, Jay; Aazhang, Behnaam
Objective. Epilepsy is a common neurological disorder in which patients suffer from sudden and unpredictable seizures. Seizures are caused by excessive and abnormal neuronal activity. Different methods have been employed to investigate electroencephalogram (EEG) data in patients with epilepsy. This paper introduces a simple yet accurate array-based method to study and predict seizures. Approach. We use the CHB-MIT dataset (all 24 cases), which includes scalp EEG recordings. The proposed method is based on the random matrix theory. After applying wavelet decomposition to denoise the data, we analyze the spatial coherence of the epileptic recordings by looking at the width of the covariance matrix eigenvalue distribution at different time and frequency bins. Main results. We train patient-specific support vector machine classifiers to distinguish between interictal and preictal data with high performance and a false prediction rate as low as 0.09 h−1. The proposed technique achieves an average accuracy, specificity, sensitivity, and area under the curve of 99.05%, 93.56%, 99.09%, and 0.99, respectively. Significance. Our proposed method outperforms state-of-the-art works in terms of sensitivity while maintaining a low false prediction rate. Also, in contrast to neural networks, which may achieve high performance, this work provides high sensitivity without compromising interpretability.
Inferring functional connectivity through graphical directed information
(IOP Publishing, 2021) Young, Joseph; Neveu, Curtis L.; Byrne, John H.; Aazhang, Behnaam
Objective. Accurate inference of functional connectivity is critical for understanding brain function. Previous methods have limited ability distinguishing between direct and indirect connections because of inadequate scaling with dimensionality. This poor scaling performance reduces the number of nodes that can be included in conditioning. Our goal was to provide a technique that scales better and thereby enables minimization of indirect connections. Approach. Our major contribution is a powerful model-free framework, graphical directed information (GDI), that enables pairwise directed functional connections to be conditioned on the activity of substantially more nodes in a network, producing a more accurate graph of functional connectivity that reduces indirect connections. The key technology enabling this advancement is a recent advance in the estimation of mutual information (MI), which relies on multilayer perceptrons and exploiting an alternative representation of the Kullback–Leibler divergence definition of MI. Our second major contribution is the application of this technique to both discretely valued and continuously valued time series. Main results. GDI correctly inferred the circuitry of arbitrary Gaussian, nonlinear, and conductance-based networks. Furthermore, GDI inferred many of the connections of a model of a central pattern generator circuit in Aplysia, while also reducing many indirect connections. Significance. GDI is a general and model-free technique that can be used on a variety of scales and data types to provide accurate direct connectivity graphs and addresses the critical issue of indirect connections in neural data analysis.
Investigating irregularly patterned deep brain stimulation signal design using biophysical models
(Frontiers Media S.A., 2015-06) Summerson, Samantha R.; Aazhang, Behnaam; Kemere, Caleb
Parkinson's disease (PD) is a neurodegenerative disorder which follows from cell loss of dopaminergic neurons in the substantia nigra pars compacta (SNc), a nucleus in the basal ganglia (BG). Deep brain stimulation (DBS) is an electrical therapy that modulates the pathological activity to treat the motor symptoms of PD. Although this therapy is currently used in clinical practice, the sufficient conditions for therapeutic efficacy are unknown. In this work we develop a model of critical motor circuit structures in the brain using biophysical cell models as the base components and then evaluate performance of different DBS signals in this model to perform comparative studies of their efficacy. Biological models are an important tool for gaining insights into neural function and, in this case, serve as effective tools for investigating innovative new DBS paradigms. Experiments were performed using the hemi-parkinsonian rodent model to test the same set of signals, verifying the obedience of the model to physiological trends. We show that antidromic spiking from DBS of the subthalamic nucleus (STN) has a significant impact on cortical neural activity, which is frequency dependent and additionally modulated by the regularity of the stimulus pulse train used. Irregular spacing between stimulus pulses, where the amount of variability added is bounded, is shown to increase diversification of response of basal ganglia neurons and reduce entropic noise in cortical neurons, which may be fundamentally important to restoration of information flow in the motor circuit.
Mutual Information in Frequency and Its Application to Measure Cross-Frequency Coupling in Epilepsy
(IEEE, 2018) Malladi, Rakesh; Johnson, Don H.; Kalamangalam, Giridhar P.; Tandon, Nitin; Aazhang, Behnaam
We define a metric, mutual information in frequency (MI-in-frequency), to detect and quantify the statistical dependence between different frequency components in the data, referred to as cross-frequency coupling and apply it to electrophysiological recordings from the brain to infer cross-frequency coupling. The current metrics used to quantify the cross-frequency coupling in neuroscience cannot detect if two frequency components in non-Gaussian brain recordings are statistically independent or not. Our MI-in-frequency metric, based on Shannon's mutual information between the Cramér's representation of stochastic processes, overcomes this shortcoming and can detect statistical dependence in frequency between non-Gaussian signals. We then describe two data-driven estimators of MI-in-frequency: One based on kernel density estimation and the other based on the nearest neighbor algorithm and validate their performance on simulated data. We then use MI-in-frequency to estimate mutual information between two data streams that are dependent across time, without making any parametric model assumptions. Finally, we use the MI-in-frequency metric to investigate the cross-frequency coupling in seizure onset zone from electrocorticographic recordings during seizures. The inferred cross-frequency coupling characteristics are essential to optimize the spatial and spectral parameters of electrical stimulation based treatments of epilepsy.
NetDI: Methodology Elucidating the Role of Power and Dynamical Brain Network Features That Underpin Word Production
(Society for Neuroscience, 2021) Yellapantula, Sudha; Forseth, Kiefer; Tandon, Nitin; Aazhang, Behnaam
Canonical language models describe eloquent function as the product of a series of cognitive processes, typically characterized by the independent activation profiles of focal brain regions. In contrast, more recent work has suggested that the interactions between these regions, the cortical networks of language, are critical for understanding speech production. We investigated the cortical basis of picture naming (PN) with human intracranial electrocorticography (ECoG) recordings and direct cortical stimulation (DCS), adjudicating between two competing hypotheses: are task-specific cognitive functions discretely computed within well-localized brain regions or rather by distributed networks? The time resolution of ECoG allows direct comparison of intraregional activation measures [high gamma (hγ) power] with graph theoretic measures of interregional dynamics. We developed an analysis framework, network dynamics using directed information (NetDI), using information and graph theoretic tools to reveal spatiotemporal dynamics at multiple scales: coarse, intermediate, and fine. Our analysis found novel relationships between the power profiles and network measures during the task. Furthermore, validation using DCS indicates that such network parameters combined with hγ power are more predictive than hγ power alone, for identifying critical language regions in the brain. NetDI reveals a high-dimensional space of network dynamics supporting cortical language function, and to account for disruptions to language function observed after neurosurgical resection, traumatic injury, and degenerative disease.
Precise measurement of correlations between frequency coupling and visual task performance
(Springer Nature, 2020) Young, Joseph; Dragoi, Valentin; Aazhang, Behnaam
Functional connectivity analyses focused on frequency-domain relationships, i.e. frequency coupling, powerfully reveal neurophysiology. Coherence is commonly used but neural activity does not follow its Gaussian assumption. The recently introduced mutual information in frequency (MIF) technique makes no model assumptions and measures non-Gaussian and nonlinear relationships. We develop a powerful MIF estimator optimized for correlating frequency coupling with task performance and other relevant task phenomena. In light of variance reduction afforded by multitaper spectral estimation, which is critical to precisely measuring such correlations, we propose a multitaper approach for MIF and compare its performance with coherence in simulations. Additionally, multitaper MIF and coherence are computed between macaque visual cortical recordings and their correlation with task performance is analyzed. Our multitaper MIF estimator produces low variance and performs better than all other estimators in simulated correlation analyses. Simulations further suggest that multitaper MIF captures more information than coherence. For the macaque data set, coherence and our new MIF estimator largely agree. Overall, we provide a new way to precisely estimate frequency coupling that sheds light on task performance and helps neuroscientists accurately capture correlations between coupling and task phenomena in general. Additionally, we make an MIF toolbox available for the first time.
Review of wearable technologies and machine learning methodologies for systematic detection of mild traumatic brain injuries
(IOP Publishing, 2021) Schmid, William; Fan, Yingying; Chi, Taiyun; Golanov, Eugene; Regnier-Golanov, Angelique S.; Austerman, Ryan J.; Podell, Kenneth; Cherukuri, Paul; Bentley, Timothy; Steele, Christopher T.; Schodrof, Sarah; Aazhang, Behnaam; Britz, Gavin W.; Neuroengineering Initiative (NEI)
Mild traumatic brain injuries (mTBIs) are the most common type of brain injury. Timely diagnosis of mTBI is crucial in making ‘go/no-go’ decision in order to prevent repeated injury, avoid strenuous activities which may prolong recovery, and assure capabilities of high-level performance of the subject. If undiagnosed, mTBI may lead to various short- and long-term abnormalities, which include, but are not limited to impaired cognitive function, fatigue, depression, irritability, and headaches. Existing screening and diagnostic tools to detect acute and early-stage mTBIs have insufficient sensitivity and specificity. This results in uncertainty in clinical decision-making regarding diagnosis and returning to activity or requiring further medical treatment. Therefore, it is important to identify relevant physiological biomarkers that can be integrated into a mutually complementary set and provide a combination of data modalities for improved on-site diagnostic sensitivity of mTBI. In recent years, the processing power, signal fidelity, and the number of recording channels and modalities of wearable healthcare devices have improved tremendously and generated an enormous amount of data. During the same period, there have been incredible advances in machine learning tools and data processing methodologies. These achievements are enabling clinicians and engineers to develop and implement multiparametric high-precision diagnostic tools for mTBI. In this review, we first assess clinical challenges in the diagnosis of acute mTBI, and then consider recording modalities and hardware implementation of various sensing technologies used to assess physiological biomarkers that may be related to mTBI. Finally, we discuss the state of the art in machine learning-based detection of mTBI and consider how a more diverse list of quantitative physiological biomarker features may improve current data-driven approaches in providing mTBI patients timely diagnosis and treatment.
RT-RCG: Neural Network and Accelerator Search Towards Effective and Real-time ECG Reconstruction from Intracardiac Electrograms
(ACM, 2022) Zhang, Yongan; Banta, Anton; Fu, Yonggan; John, Mathews M.; Post, Allison; Razavi, Mehdi; Cavallaro, Joseph; Aazhang, Behnaam; Lin, Yingyan
There exists a gap in terms of the signals provided by pacemakers (i.e., intracardiac electrogram (EGM)) and the signals doctors use (i.e., 12-lead electrocardiogram (ECG)) to diagnose abnormal rhythms. Therefore, the former, even if remotely transmitted, are not sufficient for doctors to provide a precise diagnosis, let alone make a timely intervention. To close this gap and make a heuristic step towards real-time critical intervention in instant response to irregular and infrequent ventricular rhythms, we propose a new framework dubbed RT-RCG to automatically search for (1) efficient Deep Neural Network (DNN) structures and then (2) corresponding accelerators, to enable Real-Time and high-quality Reconstruction of ECG signals from EGM signals. Specifically, RT-RCG proposes a new DNN search space tailored for ECG reconstruction from EGM signals and incorporates a differentiable acceleration search (DAS) engine to efficiently navigate over the large and discrete accelerator design space to generate optimized accelerators. Extensive experiments and ablation studies under various settings consistently validate the effectiveness of our RT-RCG. To the best of our knowledge, RT-RCG is the first to leverage neural architecture search (NAS) to simultaneously tackle both reconstruction efficacy and efficiency.
Sub-scalp electroencephalography: A next-generation technique to study human neurophysiology
(Elsevier, 2022) Haneef, Zulfi; Yang, Kaiyuan; Sheth, Sameer A.; Aloor, Fuad Z.; Aazhang, Behnaam; Krishnan, Vaishnav; Karakas, Cemal
Sub-scalp electroencephalography (ssEEG) is emerging as a promising technology in ultra-long-term electroencephalography (EEG) recordings. Given the diversity of devices available in this nascent field, uncertainty persists about its utility in epilepsy evaluation. This review critically dissects the many proposed utilities of ssEEG devices including (1) seizure quantification, (2) seizure characterization, (3) seizure lateralization, (4) seizure localization, (5) seizure alarms, (6) seizure forecasting, (7) biomarker discovery, (8) sleep medicine, and (9) responsive stimulation. The different ssEEG devices in development have individual design philosophies with unique strengths and limitations. There are devices offering primarily unilateral recordings (24/7 EEGTM SubQ, NeuroviewTM, Soenia® UltimateEEG™), bilateral recordings (Minder™, Epios™), and even those with responsive stimulation capability (EASEE®). We synthesize the current knowledge of these ssEEG systems. We review the (1) ssEEG devices, (2) use case scenarios, (3) challenges and (4) suggest a roadmap for ideal ssEEG designs.

Browse

Browsing Faculty Publications by Author "Aazhang, Behnaam"

Results Per Page

Sort Options