Improving scalability in systems neuroscience

Chen, Zhe; Pesaran, Bijan

doi:10.1016/j.neuron.2021.03.025

Cited by 22 publications

(26 citation statements)

References 157 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Put together, in comparison with the previous clusterless decoding algorithm ( Kloosterman et al, 2014 ; Hu et al, 2018 ; Ciliberti et al, 2018 ), the low sampling rate requirement, simple feature extraction (high-pass filtering and Hilbert transform), efficiency decoding method (OLE, linear mapping/matrix multiplication), and the stability and longevity of signals make our approach more suitable for online closed-loop neural manipulation experiments. The scalable computation also enables the feasibility of many hippocampal replay studies based on large-scale neural recordings, especially for closed-loop neuroscience experiments ( Chen and Pesaran, 2021 ).…”

Section: Resultsmentioning

confidence: 99%

Uncovering spatial representations from spatiotemporal patterns of rodent hippocampal field potentials

Cao

Varga

Chen

2021

Cell Reports Methods

Self Cite

View full text Add to dashboard Cite

SUMMARY Spatiotemporal patterns of large-scale spiking and field potentials of the rodent hippocampus encode spatial representations during maze runs, immobility, and sleep. Here, we show that multisite hippocampal field potential amplitude at ultra-high-frequency band (FPA uhf ), a generalized form of multiunit activity, provides not only a fast and reliable reconstruction of the rodent’s position when awake, but also a readout of replay content during sharp-wave ripples. This FPA uhf feature may serve as a robust real-time decoding strategy from large-scale recordings in closed-loop experiments. Furthermore, we develop unsupervised learning approaches to extract low-dimensional spatiotemporal FPA uhf features during run and ripple periods and to infer latent dynamical structures from lower-rank FPA uhf features. We also develop an optical flow-based method to identify propagating spatiotemporal LFP patterns from multisite array recordings, which can be used as a decoding application. Finally, we develop a prospective decoding strategy to predict an animal’s future decision in goal-directed navigation.

show abstract

Section: Resultsmentioning

confidence: 99%

Uncovering spatial representations from spatiotemporal patterns of rodent hippocampal field potentials

Cao

Varga

Chen

2021

Cell Reports Methods

Self Cite

View full text Add to dashboard Cite

show abstract

“…The relationship between every dependable variable and the randomized variable is causal, whereas the relationship between non-randomized variables and behavior, remains correlational [332]. Closed-loop experimental design would help to test the potential causality [333]. In human experiments, we classify closed-loop testing into two categories: one being fully automated, and the other being closedhuman-in-the-loop.…”

Section: Explainable Ai and Causality Testing In Psychiatrymentioning

confidence: 99%

“…Human neuroimaging alone only demonstrates correlations but not causation. To understand the causal mechanisms, it is important to close the loop in experiments by manipulating or perturbing the brain circuits and measuring its outcome, as commonly done in animal experiments [332], [333]. Unfortunately, a rigorous and causal grounding of clinical symptoms and behavior in specific neural circuit alternations is still missing.…”

Section: Closing the Loop For Testing Causalitymentioning

confidence: 99%

Modern Views of Machine Learning for Precision Psychiatry

Chen¹,

Prathamesh²,

Kulkarni³

et al. 2022

Preprint

View full text Add to dashboard Cite

In light of the NIMH’s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of the ML methodologies and applications by combining neuroimaging, neuromodulation and advanced mobile technologies in psychiatry practice. Additionally, we review the role of ML in molecular phenotyping, cross-species biomarker identification in precision psychiatry. We further discuss explainable AI (XAI) and causality testing in a closed-human-in-the-loop manner, and highlight the ML potential in multimedia information extraction and multimodal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.

show abstract

“…The past decade has seen the development of an impressive armament of new tools for neuroscientists to understand the structure and function of the brain in animal models, many of which are designed specifically for simultaneous recording from large numbers of single neurons (Chen and Pesaran, 2021). Many of these advances have been driven by high-density microfabricated electrode arrays and associated developments in integration (Bere ´nyi et al, 2014;Chung et al, 2019;Jun et al, 2017;Musk and Neuralink, 2019;Shobe et al, 2015;Steinmetz et al, 2021), thereby providing access to spatial and temporal scales required to understanding information processing across the cortical microcircuit (Larkum, 2013).…”

Section: Introductionmentioning

confidence: 99%