Posted on No Comments on “Saving and Loading” Nerve Signals

“Saving and Loading” Nerve Signals

Electrical stimulation of peripheral nerves can treat patients without necessitating pharmaceutical drugs. Stimulation of the vagus nerve, for instance, treats epilepsy, depression, arthritis, IBS, and more. However, nerve stimulation can lead to side effects when done improperly—that’s why we are working to optimize “Spatially Selective” stimulation, which delivers electricity to only the locations in a nerve which control desired effects. We use a multi-contact cuff electrode for stimulation and recording.

We have developed two algorithms which optimize spatially selective stimulation. First, we determine where the electrical current needs to be delivered, using a combination of imaging tools and custom source localization algorithms. Secondly, we determine the correct amount of current to apply to each electrode to precisely activate the target locations on the nerve. Our in-Silico and physical model findings demonstrate that we can use recording and stimulation together, to “save” a neural signal, and “load” that signal later

Posted on No Comments on “Brain Copying”

“Brain Copying”

In the field of neuroscience, we all dream of direct brain-to-brain communication. Our lab is paving the way towards making that dream into a reality.

By combining brain recording tools on one individual with brain stimulation methodologies on another individual, we are working towards “copying” a signal from one brain into another. By recording activity in the first subject’s brain, we can find the origin of each signal—then use stimulation to apply electrical activity to the same region of the second subject’s brain. This entire process can be performed non-invasively.

Our group has demonstrated the precision of our stimulation and recording techniques in-Silico, and we are working on the development of a stimulator that can be used to test out “Brain Copying” on animal models.

Brain Copying Fundamentals:
Brain Copying requires cutting-edge recording and stimulation tools. Our lab has developed both (images from our publications https://doi.org/10.3389/fnins.2016.00543, and https://doi.org/10.3390/a15050169)

 

Posted on No Comments on Spatial method artifact removal technology (SMART) for neural signal recovery during closed-loop neuromodulation

Spatial method artifact removal technology (SMART) for neural signal recovery during closed-loop neuromodulation

Closed-loop neuromodulation requires recording design to have high gain and low noise to capture sub-mV neural signals but artifacts exceeding 1 V saturates conventional recording system. Artifact needs to be removed before amplification to avoid data loss.

We developed a custom chip to leverage the differing propagation speed between artifact and neural response to remove artifacts before they saturate the amplifier. The artifact travels in tissue as electro-magnetic waves at a speed of 3*10^7 m/s while the neural signal travels at a much slower speed at around 10m/s. The 5 orders of speed difference provide a robust basis for selective removal.

Posted on No Comments on Full duplex Biomimetic inspired Neural interface (BIND)

Full duplex Biomimetic inspired Neural interface (BIND)

Closed-loop neuromodulation delivers stimulation based on real-time neural feedback. Such a system requires a versatile hardware platform and advanced closed-loop algorithm.  Existing platforms are either constrained by hardware capability or software programmability and are limited to a narrow parametric space during development, hindering the exploration of optimal treatment.

We distribute and integrate the control logics of BIND system across three key tiers: GUI and AI closed-loop control software, microcontroller firmware, and customized integrated circuit hardware. The software GUI sends command wirelessly to the remote platform. The central firmware seamlessly translates software commands into hardware instructions to control the customized SoC of recording system with online artifact removal, the arbitrary stimulator SoC, and the wireless module.

The BIND system enables full-duplex neural communication, delivering user-defined stimuli while simultaneously monitoring immediate changes in neural dynamics. We envision our BIND system to facilitate the closed-loop biomedical applications and advance the disease treatments.

Posted on No Comments on Seizure Interruption in Personalized Computational Brains

Seizure Interruption in Personalized Computational Brains

Epilepsy affects ~50 million people globally, and nearly one-third do not respond to medication. Surgical resection has long been an alternative but remains highly invasive with significant risks. Responsive neurostimulation offers a less invasive option, but its lack of specificity limits effectiveness. Adaptive neurostimulation instead responds directly to epileptic features to maximize seizure-stopping capabilities. Recent breakthroughs in patient-specific computational brain modeling enable simulation of brain dynamics and responses to neurostimulation in silico, offering a powerful framework to design and optimize adaptive stimulation strategies before clinical deployment. Individualized models built from neuroimaging and electrophysiological data help identify seizure onset zones, simulate propagation, and test targeted interventions under controlled conditions. This enables precise tuning of parameters, such as timing, amplitude, and location, to maximize seizure suppression and minimize side effects. Compared to traditional approaches, virtual testing accelerates development of safer, more effective, and personalized therapies for epilepsy.

Posted on No Comments on Interpretable AI Powered Prognosis Tool for β-Amyloid Plaque Burden

Interpretable AI Powered Prognosis Tool for β-Amyloid Plaque Burden

We developed interpretable machine learning models to predict five-year β-Amyloid (Aβ) plaque progression in individuals at early risk for Alzheimer’s Disease (AD). Focusing on subjects with initially low Aβ burden (Centiloid < 24) from the ADNI cohort, we integrated demographic information, APOE genotype, cognitive assessments, and PET-derived features—including regional SUVRs, brain volumes and their change rates. Using support vector machine, random forest, and multilayer perceptron models, we achieved strong performance (F1-scores up to 0.866), with consistent generalization to the independent OASIS-3 dataset.

To ensure transparency, we applied SHAP (Shapley Additive Explanations) and found that changes in prefrontal SUVR, regional volumes, and SUVRs in parietal and posterior cingulate regions were among the most influential predictors. Our approach offers an interpretable and practical tool for identifying individuals at high risk of Aβ buildup, supporting early diagnosis and timely intervention in AD.

A: Prognosis pipeline for β-Amyloid plaque burden.
B: ML model performance (weighted F1-score).
C: PET feature contributions based on averaged normalized SHAP values from MLP outputs.

Posted on No Comments on Longitudinal analysis on epileptogenesis in Alzheimer’s Disease

Longitudinal analysis on epileptogenesis in Alzheimer’s Disease

Alzheimer’s disease (AD), which accounts for ~70% of dementia cases, shares key mechanisms with late-onset epilepsy, including neuroinflammation and amyloid buildup. Seizures further accelerate Aβ and tau accumulation, worsening cognitive decline, as seen in hAPP-J20 mice.

We conducted a longitudinal study tracking spatial learning, memory loss, and Aβ plaque buildup in Tg and non-Tg mice from birth to 27 weeks. Behavioral tests, immunostaining (NPY, CaMK2, PV), and video-EEG were performed every 3 weeks.

Our results link Aβ deposition to seizure activity, reduced neuronal density, and rising HFOs, especially fast ripples and pathological ripples, highlighting their potential as early biomarkers of epileptogenesis in AD.

Temporal analysis of HFO incidence from chronic CA1 recordings: Ripple (80–200 Hz, top) and fast ripple (250–500 Hz, bottom) rates were similar between nTg and Tg mice before 15 weeks (pre-plaque stage), but showed a significant increase in Tg mice after 17–18 weeks.

Published Paper: https://alz-journals.onlinelibrary.wiley.com/doi/10.1002/alz.087939

Posted on No Comments on A machine learning algorithm for CPG signal analysis

A machine learning algorithm for CPG signal analysis

Electrical stimulation of the central pattern generator (CPG) shows promise for restoring locomotion in spinal cord injury patients. Biomimetic neural modulation protocols, designed to mimic natural signals, outperform traditional methods in sustaining fictive locomotion (FL), but require extensive trials for fine-tuning—highlighting the need for automated CPG signal analysis.

We developed a peak-based oscillation classification algorithm (POCA) to detect and analyze locomotion-related activity. Instead of adopting epoch-based feature extraction framework which was often used in other biological oscillation detection, POCA extracts features at the peak level, offering better accuracy, simpler training, and more direct oscillation characterization.

Tested across three protocols, our rbf-SVM model achieved an F1-score of 0.923 and 0.966 accuracy, surpassing alternative approaches. POCA’s rhythm characterizations also aligned well with expert assessments, providing a reliable and scalable tool to support large-scale optimization of biomimetic CPG stimulation protocols.

Posted on No Comments on Ingestible Device for Medical Interaction with the Gastrointestinal Tract and Surrounding Tissues

Ingestible Device for Medical Interaction with the Gastrointestinal Tract and Surrounding Tissues

Current gastrointestinal (GI) treatments often require costly, invasive procedures with limited accuracy. Traditional monitoring methods, such as endoscopies and surface electrogastrograms, are constrained by the physical limitations of external tools and epicutaneous measurements, which are prone to noise and lack spatial precision. There is a growing need for more specific, temporally precise, and less invasive approaches to improve diagnostic and therapeutic outcomes. Ingestible devices present a promising solution by providing direct access to the GI tract and enteric nervous system. These miniaturized, biocompatible capsules can monitor key physiological signals such as pH, temperature, pressure, and biomolecular activity while preserving natural GI function. Integrated multi-electrode systems allow for improved electrogastrogram recordings, tissue impedance testing, and neuromodulation of enteric and autonomic systems. These features position ingestible devices as a transformative tool for improving the precision, efficiency, and patient experience of GI care.