Multi-input mutual supervision network for single-pixel computational imaging.

In this study, we propose a single-pixel computational imaging method based on a multi-input mutual supervision network (MIMSN). We input one-dimensional (1D) light intensity signals and two-dimensional (2D) random image signal into MIMSN, enabling the network to learn the correlation between the two signals and achieve information complementarity. The 2D signal provides spatial information to the reconstruction process, reducing the uncertainty of the reconstructed image. The mutual supervision of the reconstruction results for these two signals brings the reconstruction objective closer to the ground truth image. The 2D images generated by the MIMSN can be used as inputs for subsequent iterations, continuously merging prior information to ensure high-quality imaging at low sampling rates. The reconstruction network does not require pretraining, and 1D signals collected by a single-pixel detector serve as labels for the network, enabling high-quality image reconstruction in unfamiliar environments. Especially in scattering environments, it holds significant potential for applications.

Calibration-free quantitative phase imaging in multi-core fiber endoscopes using end-to-end deep learning.

Quantitative phase imaging (QPI) through multi-core fibers (MCFs) has been an emerging in vivo label-free endoscopic imaging modality with minimal invasiveness. However, the computational demands of conventional iterative phase retrieval algorithms have limited their real-time imaging potential. We demonstrate a learning-based MCF phase imaging method that significantly reduced the phase reconstruction time to 5.5 ms, enabling video-rate imaging at 181 fps. Moreover, we introduce an innovative optical system that automatically generated the first, to the best of our knowledge, open-source dataset tailored for MCF phase imaging, comprising 50,176 paired speckles and phase images. Our trained deep neural network (DNN) demonstrates a robust phase reconstruction performance in experiments with a mean fidelity of up to 99.8%. Such an efficient fiber phase imaging approach can broaden the applications of QPI in hard-to-reach areas.

Serum phosphorus concentration and its association with the degree and pattern of intracranial arterial calcification.

BACKGROUND AND AIM: The aim of this study was to determine whether the serum phosphorus concentrations (SPC) are associated with the degree and pattern of intracranial arterial calcification (IAC) in patients with normal renal function or mild-moderate renal impairment. METHODS AND RESULTS: A total of 513 patients were enrolled in this study. The degree of IAC measured by IAC scores was evaluated on non-contrast head computed tomography (CT) images and IAC was classified as intimal or medial calcification. Study participants were classified according to IAC degrees (mild, moderate and severe) and patterns (intimal and medial calcification). A multivariate regression model was used to assess the independent relationship of SPC with IAC scores and patterns. Of 513 study participants (mean [SD] age, 68.3 [10.3] years; 246 females [48%]), the mean SPC was 1.07 ± 0.17 mmol/L and IAC scores was 4.0 (3.0-5.0). Multivariate analysis showed that higher serum phosphorus was a significant risk factor for moderate/severe IAC in both patients with eGFR ≥60 ml/min/1.73 m2 (odds ratio [OR], 1.27; 95% confidence interval [CI], 1.01-1.59; P < 0.05) and eGFR <60 ml/min/1.73 m2 (OR, 1.92; 95% CI, 1.04-3.57; P < 0.05), when those with mild IAC were considered as the reference group. However, higher SPC was associated with an increased odds of medial calcification only in patients with eGFR <60 ml/min/1.73 m2 (OR, 1.67; 95% CI, 1.08 to 2.61). CONCLUSIONS: High levels of serum phosphorus were positively correlated with the degree of IAC, and this significant effect on medial IAC was only present in patients with impaired renal function (eGFR <60 ml/min/1.73 m2).

ASF-Transformer: neutralizing the impact of atmospheric turbulence on optical imaging through alternating learning in the spatial and frequency domains.

Atmospheric turbulence, a pervasive and complex physical phenomenon, challenges optical imaging across various applications. This paper presents the Alternating Spatial-Frequency (ASF)-Transformer, a learning-based method for neutralizing the impact of atmospheric turbulence on optical imaging. Drawing inspiration from split-step propagation and correlated imaging principles, we propose the Alternating Learning in Spatial and Frequency domains (LASF) mechanism. This mechanism utilizes two specially designed transformer blocks that alternate between the spatial and Fourier domains. Assisted by the proposed patch FFT loss, our model can enhance the recovery of intricate textures without the need for generative adversarial networks (GANs). Evaluated across diverse test mediums, our model demonstrated state-of-the-art performance in comparison to recent methods. The ASF-Transformer diverges from mainstream GAN-based solutions, offering a new strategy to combat image degradation introduced by atmospheric turbulence. Additionally, this work provides insights into neural network architecture by integrating principles from optical theory, paving the way for innovative neural network designs in the future.

Association between Obstructive Sleep Apnea and Intracranial Artery Calcification Stratified by Gender and Body Mass Index: A Hospital-Based Observational Study.

BACKGROUND AND OBJECTIVES: Obstructive sleep apnea (OSA) is an independent risk factor for stroke. Furthermore, intracranial arterial calcification (IAC) has been validated as a marker for subclinical cerebrovascular disease. However, the relationship between OSA with IAC was less studied compared with its established association with coronary artery calcification. In this study, we aimed to investigate the association between the severity of OSA and the degree of IAC in hospitalized patients without preexisting cardiovascular disease. METHODS: This hospital-based observational study was conducted from June 1, 2017, to May 1, 2019. In total, 901 consecutive patients who underwent head computed tomography scans and portable sleep monitoring were included. On the basis of the apnea-hypopnea index (AHI), patients were divided into four OSA severity groups (normal: AHI <5/h; mild: 5≤ AHI <15/h; moderate: 15≤ AHI <30/h; severe: AHI ≥30/h). Associations of OSA with IAC scores were assessed by using multivariate logistic regression analysis. RESULTS: Of the 901 patients, 484 (53.7%) were men; the mean (SD) age was 66.1 (10.0) years. The non-OSA group included 207 (23.0%) patients; mild OSA, 209 (23.2%); moderate OSA, 235 (26.1%); and severe OSA, 169 (18.8%). Mean IAC scores were higher in the severe OSA group compared with non-, mild, and moderate OSA groups (4.79 vs. 2.58; 4.79 vs. 2.94; 4.79 vs. 3.39; p < 0.001). Multivariate analysis adjusted for confounding factors revealed that only severe OSA was associated with a higher IAC score (odds ratio [OR]: 1.65; 95% confidence interval [CI]: 1.43-1.91; p < 0.001). In stratified analyses by BMI, among participants with a BMI <25 kg/m2, the positive association between AHI values and IAC scores was found in the moderate OSA group (OR: 1.23; 95% CI: 1.05, 1.43; p = 0.01) and the severe OSA group (OR: 1.96; 95% CI: 1.55, 2.48; p < 0.001). When stratified by gender, in women, the positive association was found in the moderate OSA group (adjusted OR: 1.21; 95% CI: 1.02-1.51; p = 0.016) and the severe OSA group (adjusted OR: 1.76; 95% CI: 1.36-2.25; p < 0.001). For the men group, a positive association between IAC scores and AHI was only observed in the severe OSA group. DISCUSSION: These findings suggest that OSA, in particular severe OSA (AHI ≥30), is independently associated with higher IAC scores. Women and no-obesity individuals appeared more susceptible to adverse OSA-related subclinical cerebrovascular disease as measured by IAC scores.

Intracranial artery calcification as an independent predictor of ischemic stroke: a systematic review and a meta-analysis.

BACKGROUND AND PURPOSE: The association between intracranial artery calcification (IAC) and the risk of ischemic stroke occurrence or poor prognosis had not yet been fully understood. In this study, we conducted a meta-analysis of existing studies aimed to assess whether IAC can be used to predict future ischemic stroke and post-stroke mortality. METHODS: Medline, Cochrane, Web of Science and Google Scholar databases were searched up to June 30, 2022. Studies were included if they reported risk ratio (RR) or odds ratios (OR) and corresponding 95% confidence intervals (CI) of stroke concerning the presence of IAC. Random or fixed effects model meta-analyses were performed. Meta-analysis was conducted by using Stata version 16.0. RESULTS: Twelve studies involving 9346 participants were included. Compared with those without IAC, patients with IAC had a higher risk of stroke occurrence (adjusted OR 1.62, 95% CI 1.18-2.23, P = 0.001) and stroke recurrence (adjusted OR 1.77, 95% CI 1.25-2.51, P = 0.003). However, we did not find a significant correlation between IAC and post-stroke mortality (pooled OR 1.12, 95% CI 0.80-1.56, P = 0.504). CONCLUSIONS: Our meta-analysis demonstrated that the presence of IAC was identified as an independent risk factor for ischemic stroke occurrence and recurrence but is not a predictor of post-stroke mortality.

OH planar laser-induced fluorescence imaging system using a kilohertz-rate 283 nm UV Ti:sapphire laser.

A narrow linewidth Ti:sapphire laser is developed and characterized for the generation of an ultraviolet nanosecond laser pulses for the planar laser-induced fluorescence (PLIF) imaging of hydroxyl (OH). With a pump power of 11.4 W at 1 kHz, the Ti:sapphire laser produces 3.5 mJ at 849 nm with pulse duration of 17 ns and achieves a conversion efficiency of 28.2%. Accordingly, its third-harmonic generation outputs 0.56 mJ at 283 nm in BBO with type I phase match. An OH PLIF imaging system has been built; a 1 to 4 kHz fluorescent image of OH of a propane Bunsen burner has been captured based on this laser system.

Inferring subgroup-specific driver genes from heterogeneous cancer samples via subspace learning with subgroup indication.

MOTIVATION: Detecting driver genes from gene mutation data is a fundamental task for tumorigenesis research. Due to the fact that cancer is a heterogeneous disease with various subgroups, subgroup-specific driver genes are the key factors in the development of precision medicine for heterogeneous cancer. However, the existing driver gene detection methods are not designed to identify subgroup specificities of their detected driver genes, and therefore cannot indicate which group of patients is associated with the detected driver genes, which is difficult to provide specifically clinical guidance for individual patients. RESULTS: By incorporating the subspace learning framework, we propose a novel bioinformatics method called DriverSub, which can efficiently predict subgroup-specific driver genes in the situation where the subgroup annotations are not available. When evaluated by simulation datasets with known ground truth and compared with existing methods, DriverSub yields the best prediction of driver genes and the inference of their related subgroups. When we apply DriverSub on the mutation data of real heterogeneous cancers, we can observe that the predicted results of DriverSub are highly enriched for experimentally validated known driver genes. Moreover, the subgroups inferred by DriverSub are significantly associated with the annotated molecular subgroups, indicating its capability of predicting subgroup-specific driver genes. AVAILABILITY AND IMPLEMENTATION: The source code is publicly available at https://github.com/JianingXi/DriverSub. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Association Between Preoperative Blood Transfusion and Postoperative Venous Thromboembolism: Review Meta-Analysis.

BACKGROUND: Several studies have shown that preoperative blood transfusion is associated with postoperative venous thromboembolism (VTE). In this study, a meta-analysis was performed to explore the relationship between preoperative blood transfusion and postoperative VTE. METHODS: Published articles were identified through a comprehensive review of PubMed and EMBASE. Data from studies reporting relative risks, odds ratios, or hazard ratios comparing the risk of postoperative VTE among participants who had preoperative blood transfusion versus those without preoperative blood transfusion were analyzed. A random-effect model was used to calculate pooled odds ratios and 95% confident intervals (CIs). RESULTS: Eight studies, which included 3,504,778 participants, aligned with our inclusion criteria and were included in the meta-analysis. Pooled analysis showed an association between preoperative blood transfusion and postoperative VTE, with an odds ratio of 2.95 (95% CI: 1.65-5.30; I2 = 89.1%). In subgroup analyses, the positive association between preoperative blood transfusion and postoperative VTE was still exist in studies with confounders adjustment. Sensitivity analysis by one-study-removed analysis confirmed the robustness of our results. CONCLUSIONS: Our study indicated that preoperative blood transfusion was associated with higher odds of postoperative VTE. Further large-scale prospective cohort studies are needed to investigate the causality between preoperative blood transfusion and postoperative VTE.

Punishment diminishes the benefits of network reciprocity in social dilemma experiments.

Network reciprocity has been widely advertised in theoretical studies as one of the basic cooperation-promoting mechanisms, but experimental evidence favoring this type of reciprocity was published only recently. When organized in an unchanging network of social contacts, human subjects cooperate provided the following strict condition is satisfied: The benefit of cooperation must outweigh the total cost of cooperating with all neighbors. In an attempt to relax this condition, we perform social dilemma experiments wherein network reciprocity is aided with another theoretically hypothesized cooperation-promoting mechanism-costly punishment. The results reveal how networks promote and stabilize cooperation. This stabilizing effect is stronger in a smaller-size neighborhood, as expected from theory and experiments. Contrary to expectations, punishment diminishes the benefits of network reciprocity by lowering assortment, payoff per round, and award for cooperative behavior. This diminishing effect is stronger in a larger-size neighborhood. An immediate implication is that the psychological effects of enduring punishment override the rational response anticipated in quantitative models of cooperation in networks.

Simultaneous Segmentation of Fetal Hearts and Lungs for Medical Ultrasound Images via an Efficient Multi-scale Model Integrated With Attention Mechanism.

Large scale early scanning of fetuses via ultrasound imaging is widely used to alleviate the morbidity or mortality caused by congenital anomalies in fetal hearts and lungs. To reduce the intensive cost during manual recognition of organ regions, many automatic segmentation methods have been proposed. However, the existing methods still encounter multi-scale problem at a larger range of receptive fields of organs in images, resolution problem of segmentation mask, and interference problem of task-irrelevant features, obscuring the attainment of accurate segmentations. To achieve semantic segmentation with functions of (1) extracting multi-scale features from images, (2) compensating information of high resolution, and (3) eliminating the task-irrelevant features, we propose a multi-scale model with skip connection framework and attention mechanism integrated. The multi-scale feature extraction modules are incorporated with additive attention gate units for irrelevant feature elimination, through a U-Net framework with skip connections for information compensation. The performance of fetal heart and lung segmentation indicates the superiority of our method over the existing deep learning based approaches. Our method also shows competitive performance stability during the task of semantic segmentations, showing a promising contribution on ultrasound based prognosis of congenital anomaly in the early intervention, and alleviating the negative effects caused by congenital anomaly.

Cutibacterium acnes Type II strains are associated with acne in Chinese patients.

Acne is a common inflammatory skin disease, especially in adolescents. Certain Cutibacterium acnes subtypes are associated with acne, although more than one subtype of C. acnes strains may simultaneously reside on the surface of the skin of an individual. To better understand the relationship between the genomic characteristics of C. acnes subtypes and acnes, we collected 50 C. acnes strains from the facial skin of 10 people (5 healthy individuals, 5 patients with acne) in Liaoning, China and performed whole genome sequencing of all strains. We demonstrated that the six potential pathogenic C. acnes strains were all Type II subtype, and discovered 90 unique genes of the six strains related to acne using pan-genome analysis. The distribution of 2 of the 90 genes was identified by PCR in bacterial cultures collected from the facial skin of 171 individuals (55 healthy individuals, 52 patients with mild acne and 64 patients with moderate to severe acne). Both the genes were significantly associated with acne (Chi square test, P < 0.01). We conclude that Type II strains are associated with acne in Chinese patients.

Vascular endothelial growth factor aggravates cerebral ischemia and reperfusion-induced blood-brain-barrier disruption through regulating LOC102640519/HOXC13/ZO-1 signaling.

BACKGROUND/OBJECTIVE: Vascular endothelial growth factor (VEGF) has been recognized to be a potential pharmaceutical target for treating ischemic stroke, but its severe side effects hinder its widely application. Here, the present study was designed to investigate the effects of VEGF on blood-brain-barrier (BBB) disruption and the underlying mechanisms. METHODS: A mouse model of middle cerebral artery occlusion (MCAO) was constructed and treated with or without VEGF. Meanwhile, mice brain microvascular endothelial cells in co-culture with astrocytes were subjected to 1, 2 and 4 h oxygen-glucose deprivation followed by 24 h of reperfusion (OGD/R) in the absence or presence of VEGF. The mRNA and protein expression were assessed by real-time PCR and Western blotting. Fluorescence in situ hybridization (FISH) was utilized to validate LOC102640519 expression in OGD/R cell models. Chromatin Immunoprecipitation (ChIP) assay was used to confirm the regulatory mechanism of LOC102640519 to HOXC13. Interactions between HOXC13 and ZO-1 were measured by a luciferase reporter assay and RNA pull down assay. RESULTS: Our results showed that administration of VEGF significantly aggravated BBB by upregulating LOC102640519 and HOXC13 expression in vitro and vitro model of cerebral ischemia. Furthermore, LOC102640519 positively regulated the expression of HOXC13, thus negatively regulated the expression of ZO-1, Occludin and Claudin-5 in OGD/R model in the absence or presence of VEGF. CONCLUSIONS: VEGF aggravated BBB disruption after cerebral I/R-induced injury probably by increasing LOC102640519 and HOXC13 through inhibition of ZO-1, Occludin and Claudin-5.

Liberating carotid arteries: measuring arterial pressure through femoral artery in mice.

Researches involving arterial pressure measurements in mice have primarily relied on carotid arterial catheterization. However, in some circumstances, measuring arterial pressure through the carotid arterial impairs accuracy. This study was aimed to evaluate whether femoral artery could displace carotid artery for the blood pressure (BP) measurements in mice. Fifty-six Swiss mice (n = 14 in each group) were randomized into four groups: control, left femoral artery, right femoral artery, and union group, in which BP was measured through left carotid, left femoral, right femoral artery, and simultaneously from right femoral artery and left carotid artery, respectively. Arterial pressure was recorded for 5 min after catheterization. There was no significant difference of the success rate and mortality rate among four groups (P > 0.05), and no obvious difference (P > 0.05) of catheterization time among the first three groups. For intergroup comparison of arterial pressure, there was no significant difference (P > 0.05) of the systolic blood pressure (SBP), diastolic BP, mean arterial pressure, and pulse pressure among the first three groups. For intragroup comparison, SBP, diastolic blood pressure (DBP), mean arterial pressure (MAP) monitored from right femoral artery were similar (P > 0.05) with those from left carotid artery, with significantly positive correlation. The mean values of difference of SBP, DBP, and MAP were -1.3, 1.2, and 0.5 mmHg, respectively. Our results indicated that femoral artery catheterization could be a safe, feasible, reliable, and accuracy alternative for the direct measurement of arterial pressure in anesthesia mice.

Association Between Carotid-Cerebral Pulse Wave Velocity and Acute Ischemic Stroke: Clinical Trial Protocol.

BACKGROUND: Pulse wave velocity is commonly regarded as the most effective and noninvasive indicator for evaluating arterial stiffness, while increased arterial stiffness is known to be related to atherosclerosis, which has been proved to play a significant role on the onset of acute ischemic stroke. However, it is still only used in the assessment of central and peripheral arteries. Our previous studies have found that carotid-cerebral pulse wave velocity measured using transcranial Doppler may be a promising method for the assessment of human cerebral arterial stiffness. This trial was designed to examine the association between carotid-cerebral pulse wave velocity and acute ischemic stroke. METHODS: In a single-center, single-arm, prospective clinical trial, patients with acute ischemic stroke who had anterior circulation infarcts confirmed by magnetic resonance imaging are eligible to receive measurement of carotid-cerebral pulse wave velocity, which is measured in the supine position with transcranial Doppler that using 2-MHz and 4-MHz ultrasound probes by 2 experienced operators. Subjects will be received follow-up for 1 year. Vascular and nonvascular death at follow-up will be assessed as primary outcomes. Secondary outcomes include intracerebral hemorrhage, subarachnoid hemorrhage, transient ischemic attack, recurrence or aggravation of ischemic stroke. CONCLUSION: This trial will be the first to evaluate carotid-cerebral pulse wave velocity in patients with acute ischemic stroke using transcranial Doppler. The results may provide more valuable theoretical basis for the prevention, treatment, and prognosis of acute ischemic stroke.

Is Metabolic Syndrome Associated with the Risk of Recurrent Stroke: A Meta-Analysis of Cohort Studies.

BACKGROUND: The association between metabolic syndrome (MetS) and recurrence of stroke remains unknown. We summarized the evidence by a meta-analysis of prospective cohort studies. METHODS: We searched the PubMed, EMBASE, and Google Scholar databases from their inception until July 2016 for cohort studies investigating this research question; relevant information was extracted by 2 independent investigators, and then aggregated using the random-effects meta-analysis approach. RESULTS: We identified 5 studies, including 7752 stroke patients who had a history of stroke or transient ischemic attack. Compared with persons without MetS, persons with MetS have a significantly higher risk of recurrent stroke, and the pooled relative risk (RR) was 1.52 (95% confidence interval (CI): 1.17-1.97). The strength of this association is greater than individual MetS components such as elevated blood pressure (RR = 1.05, 95% CI: .72-1.52), elevated triglycerides (RR = 1.04, 95% CI: .84-1.29), low high-density lipoprotein cholesterol (RR = 1.16, 95% CI: .91-1.48), or obesity (RR = 1.12, 95% CI: .89-1.41). The risk of recurrent stroke was highest in the group with elevated glycemia (RR = 1.70, 95% CI: 1.12-2.56). CONCLUSIONS: This meta-analysis suggests that MetS might be an important predictor of recurrent stroke. Among the 5 components of MetS, elevated glycemia was a stronger predictor for recurrent stroke.

An End-to-End Deep Graph Clustering via Online Mutual Learning.

In clustering fields, the deep graph models generally utilize the graph neural network to extract the deep embeddings and aggregate them according to the data structure. The optimization procedure can be divided into two individual stages, optimizing the neural network with gradient descent and generating the aggregation with a machine learning-based algorithm. Hence, it means that clustering results cannot guide the optimization of graph neural networks. Besides, since the aggregating stage involves complicated matrix computation such as decomposition, it brings a high computational burden. To address these issues, a unified deep graph clustering (UDGC) model via online mutual learning is proposed in this brief. Specifically, it maps the data into the deep embedding subspace and extracts the deep graph representation to explore the latent topological knowledge of the nodes. In the deep subspace, the model aggregates the embeddings and generates the clustering assignments via the local preserving loss. More importantly, we train a neural layer to fit the clustering results and design an online mutual learning strategy to optimize the whole model, which can not only output the clustering assignments end-to-end but also reduce the computation complexity. Extensive experiments support the superiority of our model.

Vehicle Perception From Satellite.

Satellites are capable of capturing high-resolution videos. It makes vehicle perception from satellite become possible. Compared to street surveillance, drive recorder or other equipments, satellite videos provide a much broader city-scale view, so that the global dynamic scene of the traffic are captured and displayed. Traffic monitoring from satellite is a new task with great potential applications, including traffic jams prediction, path planning, vehicle dispatching, etc. Practically, limited by the resolution and view, the captured vehicles are very tiny (a few pixels) and move slowly. Worse still, these satellites are in Low Earth Orbit (LEO) to capture such high-resolution videos, so the background is also moving. Under this circumstance, traffic monitoring from the satellite view is an extremely challenging task. To attract more researchers into this field, we build a large-scale benchmark for traffic monitoring from satellite. It supports several tasks, including tiny object detection, counting and density estimation. The dataset is constructed based on 12 satellite videos and 14 synthetic videos recorded from GTA-V. They are separated into 408 video clips, which contain 7,336 real satellite images and 1,960 synthetic images. 128,801 vehicles are annotated totally, and the number of vehicles in each image varies from 0 to 101. Several classic and state-of-the-art approaches in traditional computer vision are evaluated on the datasets, so as to compare the performance of different approaches, analyze the challenges in this task, and discuss the future prospects.

Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One.

Graph neural networks (GNN) suffer from severe inefficiency due to the exponential growth of node dependency with the increase of layers. It extremely limits the application of stochastic optimization algorithms so that the training of GNN is usually time-consuming. To address this problem, we propose to decouple a multi-layer GNN as multiple simple modules for more efficient training, which is comprised of classical forward training (FT) and designed backward training (BT). Under the proposed framework, each module can be trained efficiently in FT by stochastic algorithms without distortion of graph information owing to its simplicity. To avoid the only unidirectional information delivery of FT and sufficiently train shallow modules with the deeper ones, we develop a backward training mechanism that makes the former modules perceive the latter modules, inspired by the classical backward propagation algorithm. The backward training introduces the reversed information delivery into the decoupled modules as well as the forward information delivery. To investigate how the decoupling and greedy training affect the representational capacity, we theoretically prove that the error produced by linear modules will not accumulate on unsupervised tasks in most cases. The theoretical and experimental results show that the proposed framework is highly efficient with reasonable performance, which may deserve more investigation.