Stroke risk study based on deep learning-based magnetic resonance imaging carotid plaque automatic segmentation algorithm.

Introduction: The primary factor for cardiovascular disease and upcoming cardiovascular events is atherosclerosis. Recently, carotid plaque texture, as observed on ultrasonography, is varied and difficult to classify with the human eye due to substantial inter-observer variability. High-resolution magnetic resonance (MR) plaque imaging offers naturally superior soft tissue contrasts to computed tomography (CT) and ultrasonography, and combining different contrast weightings may provide more useful information. Radiation freeness and operator independence are two additional benefits of M RI. However, other than preliminary research on MR texture analysis of basilar artery plaque, there is currently no information addressing MR radiomics on the carotid plaque. Methods: For the automatic segmentation of MRI scans to detect carotid plaque for stroke risk assessment, there is a need for a computer-aided autonomous framework to classify MRI scans automatically. We used to detect carotid plaque from MRI scans for stroke risk assessment pre-trained models, fine-tuned them, and adjusted hyperparameters according to our problem. Results: Our trained YOLO V3 model achieved 94.81% accuracy, RCNN achieved 92.53% accuracy, and MobileNet achieved 90.23% in identifying carotid plaque from MRI scans for stroke risk assessment. Our approach will prevent incorrect diagnoses brought on by poor image quality and personal experience. Conclusion: The evaluations in this work have demonstrated that this methodology produces acceptable results for classifying magnetic resonance imaging (MRI) data.

Adsorption and Gas Sensing Properties of the Pt3-MoSe2 Monolayer to SOF2 and SO2F2.

SF6 acts as an insulation gas in gas-insulated switchgear (GIS), which inevitably decomposes under partial discharge caused by insulation defects. This work is devoted to finding a new gas-sensing material for detecting two characteristic SF6 decomposition products: SOF2 and SO2F2. The platinum-cluster-modified molybdenum diselenide (Pt3-MoSe2) monolayer has been proposed as a gas sensing material. Based on first-principles calculations, the adsorption properties and the mechanism were studied by analyzing the adsorption structures, adsorption energy, charge transfer, density of states, and molecular orbitals. The adsorption ability of Pt3-MoSe2 to SO2F2 is stronger than that to SOF2 due to its chemisorption property. The obvious change of conductivity of the adsorption system during the gas adsorption process shows that Pt3-MoSe2 is sensitive to both of the gas molecules. In addition, the modest adsorption energy signifies that the gas adsorption process can be reversible, which confirms the feasibility of Pt3-MoSe2-based gas sensors. Our calculation suggests that Pt3-MoSe2-based gas sensors can be employed in GIS for partial discharge detection.

High-Performance Dye-Sensitized Solar Cells Based on Colloid-Solution Deposition Planarized Fluorine-Doped Tin Oxide Substrates.

The transmittance and conductivity of fluorine-doped tin oxide (FTO) conductive glasses are the critical factors limiting the performance of dye-sensitized solar cells (DSSCs). Here, the transmittance and conductivity of commercial FTO glasses were improved via a colloid-solution deposition planarization (CSDP) process. The process includes two steps. First, the FTO nanocrystal colloid was deposited on the FTO glasses by spin-coating. Secondly, the coated glasses were treated by FTO precursor solution. Compared to the bare FTO glasses, the modified FTO glasses by the CSDP process achieved 4% increase in transmittance (at 550 nm) and 11% decrease in sheet resistance, respectively. In addition, the modified FTO glasses can reduce the aggregation of Pt nanoparticles and improve the electrocatalytic activity of Pt counter electrodes. When the modified FTO glasses were used to assemble DSSCs, the cells got a photoelectric conversion efficiency as high as 9.37%. In contrast, the efficiency of reference cells using bare FTO substrates was about 8.24%.

Decoding Brain States Based on Magnetoencephalography From Prespecified Cortical Regions.

Brain state decoding based on whole-head MEG has been extensively studied over the past decade. Recent MEG applications pose an emerging need of decoding brain states based on MEG signals originating from prespecified cortical regions. Toward this goal, we propose a novel region-of-interest-constrained discriminant analysis algorithm (RDA) in this paper. RDA integrates linear classification and beamspace transformation into a unified framework by formulating a constrained optimization problem. Our experimental results based on human subjects demonstrate that RDA can efficiently extract the discriminant pattern from prespecified cortical regions to accurately distinguish different brain states.

Clustering linear discriminant analysis for MEG-based brain computer interfaces.

In this paper, we propose a clustering linear discriminant analysis algorithm (CLDA) to accurately decode hand movement directions from a small number of training trials for magnetoencephalography-based brain computer interfaces (BCIs). CLDA first applies a spectral clustering algorithm to automatically partition the BCI features into several groups where the within-group correlation is maximized and the between-group correlation is minimized. As such, the covariance matrix of all features can be approximated as a block diagonal matrix, thereby facilitating us to accurately extract the correlation information required by movement decoding from a small set of training data. The efficiency of the proposed CLDA algorithm is theoretically studied and an error bound is derived. Our experiment on movement decoding of five human subjects demonstrates that CLDA achieves superior decoding accuracy over other traditional approaches. The average accuracy of CLDA is 87% for single-trial movement decoding of four directions (i.e., up, down, left, and right).

Task-related MEG source localization via discriminant analysis.

To investigate the neural activity corresponding to different cognitive states, it is of great importance to localize the cortical areas that are associated with task-related modulation. In this paper, we propose a novel discriminant pattern source localization (DPSL) method to analyze MEG data. Unlike most traditional source localization methods that aim to find "dominant" sources, DPSL is developed to capture the "differential" sources that distinguish different cognitive states. As will be demonstrated by the experimental results in this paper, the proposed DPSL method offers superior accuracy to identify the spatial locations of task-related sources.