The application value of a vendor-specific deep learning image reconstruction algorithm in "triple low" head and neck computed tomography angiography.

Background: Head and neck computed tomography angiography (CTA) technology has become the noninvasive imaging method of choice for the diagnosis and long-term follow-up of vascular lesions of the head and neck. However, issues of radiation safety and contrast nephropathy associated with CTA examinations remain concerns. In recent years, deep learning image reconstruction (DLIR) algorithms have been increasingly used in clinical studies, demonstrating their potential for dose optimization. This study aimed to investigate the value of using a DLIR algorithm to reduce radiation and contrast doses in head and neck CTA. Methods: A total of 100 patients were prospectively enrolled and randomly divided into two groups. Group A (50 patients) consisted of those who underwent 70-kVp CTA with a low contrast volume and injection rate and who were classified according to the reconstruction algorithm into subgroups A1 [DLIR at high weighting (DLIR-H)], A2 [DLIR at low weighting (DLIR-L)], and A3 [volume-based adaptive statistical iterative reconstruction with 50% weighting (ASIR-V50%)]. Meanwhile, group B (50 patients) consisted of those who underwent standard radiation and contrast doses at 100 kVp with ASIR-V50% reconstruction. The computed tomography (CT) attenuation, background noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and subjective image quality score (SIQS) were statistically compared for several vessels among the four groups. Results: Group A showed significant reductions in contrast dosage, injection rate, and radiation dose of 36.09%, 20.88%, and 47.80%, respectively, compared to group B (all P<0.001). The four groups differed significantly in terms of background noise (all P<0.05) with group A1 having the lowest value. Group A1 also had significantly higher SNR and CNR values compared to group B in all vessels (all P<0.05) except the M1 of the middle cerebral artery for the SNR. Group A1 also had the highest SIQS, followed by the A2, B, and A3 groups. The SIQS showed good agreement between the two reviewers in all groups, with κ values between 0.88 and 1. Conclusions: Compared to the standard-dose protocol using 100 kVp and ASIR-V50%, a protocol of 70 kVp combined with DLIR-H significantly reduces the radiation dose, contrast dose, and injection rate in head and neck CTA while still significantly improving image quality for patients with a standard body size.

Adopting an HMI for overtaking assistance - Impact of distance display, advice, and guidance information on driver gaze and performance.

Conveying supporting information by an in-vehicle human-machine interface (HMI) overtaking assistance system represents a promising approach to facilitate safe overtaking maneuvers. Although various researchers have attempted to examine the safety of systems, numerous HMI concepts are not validated and the impacts of systems on driver behavior following exposure to a connected environment remain unclear. Thus, the objective of this study is to assess the effectiveness of various HMI concepts and their effects on drivers' gaze behavior and driving performance in the connected environment. Three types of supporting information, namely distance, advice and guidance, were designed based on implicit and explicit concepts and displayed on the HMI. The guidance information provides more detailed maneuver instructions. A driving simulator experiment was conducted to imitate a connected environment and included an overtaking scenario on a two-lane highway under three distance gaps (short, middle and long) of oncoming vehicles and four HMI conditions including baseline (3*4). 39 participants (mean = 28.3 years, SD = 8.2 years) drove the simulator. Visual attention, driving maneuver, and subjective evaluation data were collected. The results indicated that the supporting information was valid in facilitating overtaking behavior compared without HMI, particularly under the middle distance gap scenario. Advice information was the most effective, required the least attention, exhibited the best performance, and was accepted by drivers. Detailed maneuver instructions were perceived as helpful, although no effect on acceptance was found. The findings of the study provide valuable insights into the development of user-friendly overtaking assistance systems.

Exploring the association and causal effect between white blood cells and psoriasis using large-scale population data.

Introduction: Psoriasis is a chronic inflammatory disease of the skin. A few studies have shown that psoriasis is an immune-mediated disease in which multiple immune cells play crucial roles. However, the association between circulating immune cells and psoriasis remains elusive. Methods: To explore the role of circulating immune cells in psoriasis, 361,322 individuals from the UK Biobank (UKB) and 3,971 patients with psoriasis from China were included to investigate the association between white blood cells and psoriasis via an observational study. Genome-wide association studies (GWAS) and Mendelian randomization (MR) were used to evaluate the causal relationship between circulating leukocytes and psoriasis. Results: The risk of psoriasis increased with high levels of monocytes, neutrophils, and eosinophils (relative risks and 95% confidence intervals, respectively: 1.430 (1.291-1.584) for monocytes, 1.527 (1.379-1.692) for neutrophils, and 1.417 (1.294-1.551) for eosinophils). Upon further MR analysis, eosinophils showed a definite causal relationship with psoriasis (odds ratio of inverse-variance weighted: 1.386, 95% confidence intervals: 1.092-1.759) and a positive correlation with the psoriasis area and severity index (PASI) score (P = 6.6 × 10-5). The roles of the neutrophil-lymphocyte ratio (NLR), platelet-lymphocyte ratio (PLR), and lymphocyte-monocyte ratio (LMR) in psoriasis were also assessed. More than 20,000 genetic variations associated with NLR, PLR, and LMR were discovered in a GWAS analysis using the UKB data. Following adjustment for covariates in the observational study, NLR and PLR were shown to be risk factors for psoriasis, whereas LMR was a protective factor. MR results indicated that there was no causal relationship between these three indicators and psoriasis; however, NLR, PLR, and LMR correlated with the PASI score (NLR: rho = 0.244, P = 2.1 × 10-21; PLR: rho = 0.113, P = 1.4 × 10-5; LMR: rho = -0.242, P = 3.5×10-21). Discussion: Our findings revealed an important association between circulating leukocytes and psoriasis, which is instructive for the clinical practice of psoriasis treatment.

Multi-modality data-driven analysis of diagnosis and treatment of psoriatic arthritis.

Psoriatic arthritis (PsA) is associated with psoriasis, featured by its irreversible joint symptoms. Despite the significant impact on the healthcare system, it is still challenging to leverage machine learning or statistical models to predict PsA and its progression, or analyze drug efficacy. With 3961 patients' clinical records, we developed a machine learning model for PsA diagnosis and analysis of PsA progression risk, respectively. Furthermore, general additive models (GAMs) and the Kaplan-Meier (KM) method were applied to analyze the efficacy of various drugs on psoriasis treatment and inhibiting PsA progression. The independent experiment on the PsA prediction model demonstrates outstanding prediction performance with an AUC score of 0.87 and an AUPR score of 0.89, and the Jackknife validation test on the PsA progression prediction model also suggests the superior performance with an AUC score of 0.80 and an AUPR score of 0.83, respectively. We also identified that interleukin-17 inhibitors were the more effective drug for severe psoriasis compared to other drugs, and methotrexate had a lower effect in inhibiting PsA progression. The results demonstrate that machine learning and statistical approaches enable accurate early prediction of PsA and its progression, and analysis of drug efficacy.

Sphingosine kinase 1 promotes tumor immune evasion by regulating the MTA3-PD-L1 axis.

Immune checkpoint blockade (ICB) exhibits considerable benefits in malignancies, but its overall response rate is limited. Previous studies have shown that sphingosine kinases (SPHKs) are critical in the tumor microenvironment (TME), but their role in immunotherapy is unclear. We performed integrative analyses including bioinformatics analysis, functional study, and clinical validation to investigate the role of SPHK1 in tumor immunity. Functionally, we demonstrated that the inhibition of SPHK1 significantly suppressed tumor growth by promoting antitumor immunity in immunocompetent melanoma mouse models and tumor T-cell cocultures. A mechanistic analysis revealed that MTA3 functions as the downstream target of SPHK1 in transcriptionally regulating tumor PD-L1. Preclinically, we found that anti-PD-1 monoclonal antibody (mAb) treatment significantly rescued tumor SPHK1 overexpression or tumor MTA3 overexpression-mediated immune evasion. Significantly, we identified SPHK1 and MTA3 as biological markers for predicting the efficacy of anti-PD-1 mAb therapy in melanoma patients. Our findings revealed a novel role for SPHK1 in tumor evasion mediated by regulating the MTA3-PD-L1 axis, identified SPHK1 and MTA3 as predictors for assessing the efficacy of PD-1 mAb treatment, and provided a therapeutic possibility for the treatment of melanoma patients.

Characterization of Immune-Related Alternative Polyadenylation Events in Cancer Immunotherapy.

Alternative polyadenylation (APA) is an important posttranscriptional modification commonly involved in tumor development. However, the functional roles of APA in tumor immunity remain largely unknown. Here, we performed an in-depth analysis of the 3'UTR usage of protein-coding genes and tumor immune response in 10,303 tumor samples across 31 cancer types to develop the immune-related APA event (ImmAPA) score pipeline, an integrated algorithm to characterize the regulatory landscape of APA events in cancer immunity-related pathways. Tumor-specific ImmAPAs that strongly correlate with immune cell infiltration and immune checkpoint blockade (ICB) treatment-related biomarkers were identified. Among these ImmAPAs, the top-ranking COL1A1 3'UTR usage was strongly associated with worse prognosis and tumor immune evasion. Furthermore, a machine learning approach to construct an ICB-related ImmAPA score model predicted immunotherapy efficacy. Overall, the characterization of immune-related APA that corresponds to tumor progression and tumor immunity highlights the clinical utility of APA events as potential biomarkers in cancer immunotherapy. SIGNIFICANCE: Elucidation of the landscape of immune-related alternative polyadenylation in cancer identifies alternative polyadenylation events that may play a role in immune modulation and immunotherapy efficacy.

Effect of Superheat Steam on Ejector in Distilled Water Preparation System for Medical Injection.

In this study, a wet steam model was used to investigate the effect of steam superheat on ejector performance and non-equilibrium condensation phenomena. The simulation data for the ejector were validated with experimental data. The simulations show that an increase in primary flow superheat will increase the entrainment ratio, while an increase in secondary flow superheat will decrease the entrainment ratio. The output fluid superheat has little effect on the entrainment ratio. As the primary flow superheat increases from 0 to 20 K, the starting position of non-equilibrium condensation moves backward by 5 mm, and the mass fraction of condensed droplets decreases by 20%. The higher the secondary flow superheat, the lower the mass fraction of liquid in the diffusion chamber. The superheat level of the output fluid has no influence on the non-equilibrium condensation phenomenon of the ejector.

A Hybrid Approach for Turning Intention Prediction Based on Time Series Forecasting and Deep Learning.

At an intersection with complex traffic flow, the early detection of the intention of drivers in surrounding vehicles can enable advanced driver assistance systems (ADAS) to warn the driver in advance or prompt its subsystems to assess the risk and intervene early. Although different drivers show various driving characteristics, the kinematic parameters of human-driven vehicles can be used as a predictor for predicting the driver's intention within a short time. In this paper, we propose a new hybrid approach for vehicle behavior recognition at intersections based on time series prediction and deep learning networks. First, the lateral position, longitudinal position, speed, and acceleration of the vehicle are predicted using the online autoregressive integrated moving average (ARIMA) algorithm. Next, a variant of the long short-term memory network, called the bidirectional long short-term memory (Bi-LSTM) network, is used to detect the vehicle's turning behavior using the predicted parameters, as well as the derived parameters, i.e., the lateral velocity, lateral acceleration, and heading angle. The validity of the proposed method is verified at real intersections using the public driving data of the next generation simulation (NGSIM) project. The results of the turning behavior detection show that the proposed hybrid approach exhibits significant improvement over a conventional algorithm; the average recognition rates are 94.2% and 93.5% at 2 s and 1 s, respectively, before initiating the turning maneuver.

The model of children's social adjustment under the gender-roles absence in single-parent families.

This study aimed to evaluate the effects of the gender-role types and child-rearing gender-role attitude of the single-parents, as well as their children's gender role traits and family socio-economic status, on social adjustment. We recruited 458 pairs of single parents and their children aged 8-18 by purposive sampling. The research tools included the Family Socio-economic Status Questionnaire, Sex Role Scales, Parental Child-rearing Gender-role Attitude Scale and Social Adjustment Scale. The results indicated: (a) single mothers' and their daughters' feminine traits were both higher than their masculine traits, and sons' masculine traits were higher than their feminine traits; the majority gender-role type of single parents and their children was androgyny; significant differences were found between children's gender-role types depending on different raiser, the proportion of girls' masculine traits raised by single fathers was significantly higher than those who were raised by single mothers; (b) family socio-economic status and single parents' gender-role types positively influenced parental child-rearing gender-role attitude, which in turn, influenced the children's gender traits, and further affected children's social adjustment.