Deep Transfer Learning for Parkinson’s Disease Monitoring by Image-Based Representation of Resting-State EEG Using Directional Connectivity

Parkinson’s disease (PD) is characterized by abnormal brain oscillations that can change rapidly. Tracking neural alternations with high temporal resolution electrophysiological monitoring methods such as EEG can lead to valuable information about alterations observed in PD. Concomitantly, there have been advances in the high-accuracy performance of deep neural networks (DNNs) using few-patient data. In this study, we propose a method to transform resting-state EEG data into a deep latent space to classify PD subjects from healthy cases. We first used a general orthogonalized directed coherence (gOPDC) method to compute directional connectivity (DC) between all pairwise EEG channels in four frequency bands (Theta, Alpha, Beta, and Gamma) and then converted the DC maps into 2D images. We then used the VGG-16 architecture (trained on the ImageNet dataset) as our pre-trained model, enlisted weights of convolutional layers as initial weights, and fine-tuned all layer weights with our data. After training, the classification achieved 99.62% accuracy, 100% precision, 99.17% recall, 0.9958 F1 score, and 0.9958 AUC averaged for 10 random repetitions of training/evaluating on the proposed deep transfer learning (DTL) network. Using the latent features learned by the network and employing LASSO regression, we found that latent features (as opposed to the raw DC values) were significantly correlated with five clinical indices routinely measured: left and right finger tapping, left and right tremor, and body bradykinesia. Our results demonstrate the power of transfer learning and latent space derivation for the development of oscillatory biomarkers in PD.

Microdevice for directional axodendritic connectivity between micro 3D neuronal cultures

Neuronal cultures are widely used in neuroscience research. However, the randomness of circuits in conventional cultures prevents accurate in vitro modeling of cortical development and of the pathogenesis of neurological and psychiatric disorders. A basic feature of cortical circuits that is not captured in standard cultures of dissociated cortical cells is directional connectivity. In this work, a polydimethylsiloxane (PDMS)-based device that achieves directional connectivity between micro 3D cultures is demonstrated. The device consists of through-holes for micro three-dimensional (μ3D) clusters of cortical cells connected by microtrenches for axon and dendrite guidance. The design of the trenches relies in part on the concept of axonal edge guidance, as well as on the novel concept of specific dendrite targeting. This replicates dominant excitatory connectivity in the cortex, enables the guidance of the axon after it forms a synapse in passing (an “en passant” synapse), and ensures that directional selectivity is preserved over the lifetime of the culture. The directionality of connections was verified morphologically and functionally. Connections were dependent on glutamatergic synapses. The design of this device has the potential to serve as a building block for the reconstruction of more complex cortical circuits in vitro.

Auditory cortical micro-networks show differential connectivity during voice and speech processing in humans

The temporal voice areas (TVAs) in bilateral auditory cortex (AC) appear specialized for voice processing. Previous research assumed a uniform functional profile for the TVAs which are broadly spread along the bilateral AC. Alternatively, the TVAs might comprise separate AC nodes controlling differential neural functions for voice and speech decoding, organized as local micro-circuits. To investigate micro-circuits, we modeled the directional connectivity between TVA nodes during voice processing in humans while acquiring brain activity using neuroimaging. Results show several bilateral AC nodes for general voice decoding (speech and non-speech voices) and for speech decoding in particular. Furthermore, non-hierarchical and differential bilateral AC networks manifest distinct excitatory and inhibitory pathways for voice and speech processing. Finally, while voice and speech processing seem to have distinctive but integrated neural circuits in the left AC, the right AC reveals disintegrated neural circuits for both sounds. Altogether, we demonstrate a functional heterogeneity in the TVAs for voice decoding based on local micro-circuits.

Feasibility study on adjustment of injection-production system in extremely high water cut period

Entering the stage of ultra-high water cut development, affected by faults and irregular well patterns in some areas, there are problems in the development of oilfields such as imperfect injection-production systems, high oil-water wells ratio, low multi-directional connectivity ratio, and complex injection-production relationships. To this end, combined with well seismic and fine reservoir research results, the feasibility study of the injection-production system adjustment was carried out, based on the fine adjustment of the strata well pattern, and through new drilling, supplementary drilling, re-injection, re-production, etc. The well pattern connection rules are conducive to the purpose of adjustment, thereby increasing the recovery rate and improving the effect of oilfield development.

The human primary somatosensory cortex encodes imagined movement in the absence of sensory information

Classical systems neuroscience positions primary sensory areas as early feed-forward processing stations for refining incoming sensory information. This view may oversimplify their role given extensive bi-directional connectivity with multimodal cortical and subcortical regions. Here we show that single units in human primary somatosensory cortex encode imagined reaches in a cognitive motor task, but not other sensory–motor variables such as movement plans or imagined arm position. A population reference-frame analysis demonstrates coding relative to the cued starting hand location suggesting that imagined reaching movements are encoded relative to imagined limb position. These results imply a potential role for primary somatosensory cortex in cognitive imagery, engagement during motor production in the absence of sensation or expected sensation, and suggest that somatosensory cortex can provide control signals for future neural prosthetic systems.

Neural correlates of cognitive motor signals in primary somatosensory cortex

Classical systems neuroscience positions primary sensory areas as early feed-forward processing stations for refining incoming sensory information. This view may oversimplify their role given extensive bi-directional connectivity with multimodal cortical and subcortical regions. Here we show that single units in human primary somatosensory cortex encode imagined reaches centered on imagined limb positions in a cognitive motor task. This result suggests a broader role of primary somatosensory cortex in cortical function than previously demonstrated.

Mapping epileptic directional brain networks using intracranial EEG data

Summary The human brain is a directional network system, in which brain regions are network nodes and the influence exerted by one region on another is a network edge. We refer to this directional information flow from one region to another as directional connectivity. Seizures arise from an epileptic directional network; abnormal neuronal activities start from a seizure onset zone and propagate via a network to otherwise healthy brain regions. As such, effective epilepsy diagnosis and treatment require accurate identification of directional connections among regions, i.e., mapping of epileptic patients’ brain networks. This article aims to understand the epileptic brain network using intracranial electroencephalographic data—recordings of epileptic patients’ brain activities in many regions. The most popular models for directional connectivity use ordinary differential equations (ODE). However, ODE models are sensitive to data noise and computationally costly. To address these issues, we propose a high-dimensional state-space multivariate autoregression (SSMAR) model for the brain’s directional connectivity. Different from standard multivariate autoregression and SSMAR models, the proposed SSMAR features a cluster structure, where the brain network consists of several clusters of densely connected brain regions. We develop an expectation–maximization algorithm to estimate the proposed model and use it to map the interregional networks of epileptic patients in different seizure stages. Our method reveals the evolution of brain networks during seizure development.

Reconfiguration of directed functional connectivity among triple networks with aging: Considering the role of thalamo-cortical interactions

The human brain undergoes significant structural and functional changes across the lifespan. Our current understanding of the underlying causal relationships of dynamical changes in functional connectivity with age is limited. On average, functional connectivity within resting-state networks (RSNs) weakens in magnitude, while connections between RSNs tend to increase with age. Recent studies show that effective connectivity within and between large scale resting-state functional networks changes over the healthy lifespan. The vast majority of previous studies have focused primarily on characterizing cortical networks, with little work exploring the influence of subcortical nodes such as the thalamus on large-scale network interactions across the lifespan. Using directed connectivity and weighted net causal outflow measures applied to resting-state fMRI data, we examine the age-related changes in both cortical and thalamocortical causal interactions within and between RSNs. The three core neurocognitive networks from the triple network theory (default mode: DMN, salience: SN, and central executive: CEN) were identified independently using ICA and spatial matching of hub regions with these important RSNs previously reported in the literature. Multivariate granger causal analysis (GCA) was performed to test for directional connectivity and weighted causal outflow between selected nodes of RSNs accounting for thalamo-cortical interactions. Firstly, we observe that within-network causal connections become progressively weaker with age, and network dynamics are substantially reconfigured via strong thalamic drive particularly in the young group. Our findings manifest stronger between-network directional connectivity, which is further strongly mediated by the SN in flexible co-ordination with the CEN, and DMN in the old group compared with the young group. Hence, causal within- and between- triple network connectivity largely reflects age-associated effects of resting-state functional connectivity. Thalamo-cortical causality effects on the triple networks with age were next explored. We discovered that left and right thalamus exhibit substantial interactions with the triple networks and play a crucial role in the reconfiguration of directed connections and within network causal outflow. The SN displayed directed functional connectivity in strongly driving both the CEN and DMN to a greater extent in the older group. Notably, these results were largely replicated on an independent dataset of matched young and old individuals. Our findings based on directed functional connectivity and weighted causal outflow measures strengthen the hypothesis that balancing within and between network connectivity is perhaps critical for the preservation and flexibility of cognitive functioning with aging.