RESUMEN
Community detection in multi-layer networks stands as a prominent subject within network analysis research. However, the majority of existing techniques for identifying communities encounter two primary constraints: they lack suitability for high-dimensional data within multi-layer networks and fail to fully leverage additional auxiliary information among communities to enhance detection accuracy. To address these limitations, a novel approach named weighted prior tensor training decomposition (WPTTD) is proposed for multi-layer network community detection. Specifically, the WPTTD method harnesses the tensor feature optimization techniques to effectively manage high-dimensional data in multi-layer networks. Additionally, it employs a weighted flattened network to construct prior information for each dimension of the multi-layer network, thereby continuously exploring inter-community connections. To preserve the cohesive structure of communities and to harness comprehensive information within the multi-layer network for more effective community detection, the common community manifold learning (CCML) is integrated into the WPTTD framework for enhancing the performance. Experimental evaluations conducted on both artificial and real-world networks have verified that this algorithm outperforms several mainstream multi-layer network community detection algorithms.
RESUMEN
Mitigating pre-harvest sprouting (PHS) and post-harvest food loss (PHFL) is essential for enhancing food securrity. To reduce food loss, the use of plant derived specialized metabolites can represent a good approach to develop a more eco-friendly agriculture. Here, we have discovered that soybean seeds hidden underground during winter by Tscherskia triton and Apodemus agrarius during winter possess a higher concentration of volatile organic compounds (VOCs) compared to those remaining exposed in fields. This selection by rodents suggests that among the identified volatiles, 3-FurAldehyde (Fur) and (E)-2-Heptenal (eHep) effectively inhibit the growth of plant pathogens such as Aspergillus flavus, Alternaria alternata, Fusarium solani and Pseudomonas syringae. Additionally, compounds such as Camphene (Cam), 3-FurAldehyde, and (E)-2-Heptenal, suppress the germination of seeds in crops including soybean, rice, maize, and wheat. Importantly, some of these VOCs also prevent rice seeds from pre-harvest sprouting. Consequently, our findings offer straightforward and practical approaches to seed protection and the reduction of PHS and PHFL, indicating potential new pathways for breeding, and reducing both PHS and pesticide usage in agriculture.
Asunto(s)
Agricultura , Glycine max , Semillas , Compuestos Orgánicos Volátiles , Semillas/microbiología , Semillas/crecimiento & desarrollo , Compuestos Orgánicos Volátiles/metabolismo , Compuestos Orgánicos Volátiles/análisis , Compuestos Orgánicos Volátiles/farmacología , Animales , Glycine max/microbiología , Glycine max/crecimiento & desarrollo , Agricultura/métodos , Germinación , Productos Agrícolas/microbiología , Productos Agrícolas/crecimiento & desarrollo , Roedores/microbiologíaRESUMEN
Soybean quality and production are determined by seed viability. A seed's capacity to sustain germination via dry storage is known as its seed life. Thus, one of the main objectives for breeders is to preserve genetic variety and gather germplasm resources. However, seed quality and germplasm preservation have become significant obstacles. In this study, four artificially simulated aging treatment groups were set for 0, 24, 72, and 120 hours. Following an aging stress treatment, the transcriptome and metabolome data were compared in two soybean lines with notable differences in seed vigor-R31 (aging sensitive) and R80 (aging tolerant). The results showed that 83 (38 upregulated and 45 downregulated), 30 (19 upregulated and 11 downregulated), 90 (52 upregulated and 38 downregulated), and 54 (25 upregulated and 29 downregulated) DEGs were differentially expressed, respectively. A total of 62 (29 upregulated and 33 downregulated), 94 (49 upregulated and 45 downregulated), 91 (53 upregulated and 38 downregulated), and 135 (111 upregulated and 24 downregulated) differential metabolites accumulated. Combining the results of transcriptome and metabolome investigations demonstrated that the difference between R31 and R80 responses to aging stress was caused by genes related to phenylpropanoid metabolism pathway, which is linked to the seed metabolite caffeic acid. According to this study's preliminary findings, the aging-resistant line accumulated more caffeic acid than the aging-sensitive line, which improved its capacity to block lipoxygenase (LOX) activity. An enzyme activity inhibition test was used to demonstrate the effect of caffeic acid. After soaking seeds in 1 mM caffeic acid (a LOX inhibitor) for 6 hours and artificially aging them for 24 hours, the germination rates of the R31 and R80 seeds were enhanced. In conclusion, caffeic acid has been shown to partially mitigate the negative effects of soybean seed aging stress and to improve seed vitality. This finding should serve as a theoretical foundation for future research on the aging mechanism of soybean seeds.
RESUMEN
The establishment of symbiotic interactions between leguminous plants and rhizobia requires complex cellular programming activated by Rhizobium Nod factors (NFs) as well as type III effector (T3E)-mediated symbiotic signaling. However, the mechanisms by which different signals jointly affect symbiosis are still unclear. Here we describe the mechanisms mediating the cross-talk between the broad host range rhizobia Sinorhizobium fredii HH103 T3E Nodulation Outer Protein L (NopL) effector and NF signaling in soybean. NopL physically interacts with the Glycine max Remorin 1a (GmREM1a) and the NFs receptor NFR5 (GmNFR5) and promotes GmNFR5 recruitment by GmREM1a. Furthermore, NopL and NF influence the expression of GmRINRK1, a receptor-like kinase (LRR-RLK) ortholog of the Lotus RINRK1, that mediates NF signaling. Taken together, our work indicates that S. fredii NopL can interact with the NF signaling cascade components to promote the symbiotic interaction in soybean.
Asunto(s)
Proteínas Bacterianas , Regulación de la Expresión Génica de las Plantas , Glycine max , Proteínas de Plantas , Sinorhizobium fredii , Simbiosis , Glycine max/microbiología , Glycine max/metabolismo , Proteínas de Plantas/metabolismo , Proteínas de Plantas/genética , Sinorhizobium fredii/metabolismo , Sinorhizobium fredii/genética , Proteínas Bacterianas/metabolismo , Proteínas Bacterianas/genética , Transducción de Señal , Nodulación de la Raíz de la Planta/genética , Plantas Modificadas GenéticamenteRESUMEN
The increase in Cervical Spondylosis cases and the expansion of the affected demographic to younger patients have escalated the demand for X-ray screening. Challenges include variability in imaging technology, differences in equipment specifications, and the diverse experience levels of clinicians, which collectively hinder diagnostic accuracy. In response, a deep learning approach utilizing a ResNet-34 convolutional neural network has been developed. This model, trained on a comprehensive dataset of 1235 cervical spine X-ray images representing a wide range of projection angles, aims to mitigate these issues by providing a robust tool for diagnosis. Validation of the model was performed on an independent set of 136 X-ray images, also varied in projection angles, to ensure its efficacy across diverse clinical scenarios. The model achieved a classification accuracy of 89.7%, significantly outperforming the traditional manual diagnostic approach, which has an accuracy of 68.3%. This advancement demonstrates the viability of deep learning models to not only complement but enhance the diagnostic capabilities of clinicians in identifying Cervical Spondylosis, offering a promising avenue for improving diagnostic accuracy and efficiency in clinical settings.
Asunto(s)
Aprendizaje Profundo , Redes Neurales de la Computación , Espondilosis , Espondilosis/diagnóstico por imagen , Humanos , Vértebras Cervicales/diagnóstico por imagen , Rayos X , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
Soybean, a major source of oil and protein, has seen an annual increase in consumption when used in soybean-derived products and the broadening of its cultivation range. The demand for soybean necessitates a better understanding of the regulatory networks driving storage protein accumulation and oil biosynthesis to broaden its positive impact on human health. In this study, we selected a chromosome segment substitution line (CSSL) with high protein and low oil contents to investigate the underlying effect of donor introgression on seed storage through multi-omics analysis. In total, 1479 differentially expressed genes (DEGs), 82 differentially expressed proteins (DEPs), and 34 differentially expressed metabolites (DEMs) were identified in the CSSL compared to the recurrent parent. Based on Gene Ontology (GO) term analysis and the Kyoto Encyclopedia of Genes and Genomes enrichment (KEGG), integrated analysis indicated that 31 DEGs, 24 DEPs, and 13 DEMs were related to seed storage functionality. Integrated analysis further showed a significant decrease in the contents of the seed storage lipids LysoPG 16:0 and LysoPC 18:4 as well as an increase in the contents of organic acids such as L-malic acid. Taken together, these results offer new insights into the molecular mechanisms of seed storage and provide guidance for the molecular breeding of new favorable soybean varieties.
Asunto(s)
Regulación de la Expresión Génica de las Plantas , Glycine max , Semillas , Glycine max/genética , Glycine max/metabolismo , Semillas/genética , Semillas/metabolismo , Cromosomas de las Plantas/genética , Redes Reguladoras de Genes , Fitomejoramiento/métodos , Perfilación de la Expresión Génica/métodos , Ontología de Genes , Transcriptoma/genética , MultiómicaRESUMEN
Substituting slow oxygen evolution reaction (OER) with thermodynamically favorable urea oxidation reaction (UOR) is considered as one of the feasible strategies for achieving energy-saving hydrogen production. Herein, a uniform layer of NiMoO4 nanorods was grown on nickel foam by a hydrothermal method. Then, a series of Ni-MoOx/NF-X nanorod catalysts comprising Ni/NiO and MoOx (MoO2/MoO3) were prepared through regulating annealing atmosphere and reduction temperature. The optimized Ni-MoOx/NF-3 with a large accessible specific area can act as a bifunctional catalyst for electrocatalytic anodic UOR and cathodic hydrogen evolution reaction (HER). At a current density of 100 mA cm-2, the introduction of urea can significantly reduce the overpotential of Ni-MoOx/NF-3 by 210 mV compared to OER. In addition, Ni-MoOx/NF-3 has a higher intrinsic activity than other catalysts. It only requires -0.21 and 1.38 V to reach 100 mA cm-2 in HER and UOR, respectively. Such an excellent performance can be attributed to the synergistic function between Ni and MoOx. The presence of metallic Ni and reduced MoOx in pairs is beneficial for improving the electrical conductivity and modulating the electronic structure, resulting in enhancing the electrocatalytic performance. When assembling Ni-MoOx/NF-3 into an overall urea-water splitting system, it can achieve energy-saving hydrogen production and effective removal of urea-rich wastewater.
RESUMEN
Sports records play a crucial role in understanding the limits of human achievement in sports. However, a thorough exploration of a comprehensive analysis of various sports records utilizing the existing statistical model has been lacking. This study introduces a framework for analyzing the integrated features and evolutionary trends of 23 sports records for men and women. It includes world records and intercontinental records from six continents, covering 6440 athletes from 2001 to 2020. Our findings indicate that human beings have not yet reached sports limits in athletic performance, suggesting a continuous improvement over time. Furthermore, we have investigated the contributions of our model's parameters to the integrated features, emphasizing their robustness and convergence in handling data flow and information entropy. Additionally, our model underscores the significance of integrating various sports for ongoing advancement, in line with the Olympic motto "Together," thereby promoting coordinated development.
Asunto(s)
Rendimiento Atlético , Deportes , Humanos , Masculino , Rendimiento Atlético/fisiología , Femenino , Atletas , Modelos EstadísticosRESUMEN
With the rapid development of high and new technology, rubidium and its compounds show broad application prospect and market demand with their unique characteristics. At present, the production of rubidium metal is mainly prepared by calcium thermal reduction of rubidium chloride. Rubidium metal obtained by reduction requires multi-step vacuum distillation to obtain high-purity rubidium metal. The purity of rubidium metal depends on the purity of the raw material rubidium chloride. Rubidium metal is relatively active and is easy to oxidize and explode in air. Therefore, a method combining vacuum decomposition and vacuum distillation to reduce impurity elements in rubidium chloride from raw materials is proposed in this paper. The experimental results show that under the conditions of pressure of 5-10 Pa, distillation temperature of 823 K and vacuum distillation time of 60 min, the contents of Si and Zn impurities are reduced from 1206 mg/kg and 310 mg/kg to less than 0.1 mg/kg, and the removal rates are 99.99% and 99.97%, respectively. Rubidium chloride has almost no loss, and through one-step vacuum distillation, the impurity elements silicon and zinc can be deeply removed, reducing the flammability and explosiveness, high cost, long process and other problems caused by the subsequent preparation of high-purity rubidium metal.
RESUMEN
Cadmium (Cd) is a heavy metal that significantly impacts human health and the environment. Microorganisms play a crucial role in reducing heavy metal stress in plants; however, the mechanisms by which microorganisms enhance plant tolerance to Cd stress and the interplay between plants and microorganisms under such stress remain unclear. In this study, Oceanobacillus picturae (O. picturae) was isolated for interaction with soybean seedlings under Cd stress. Results indicated that Cd treatment alone markedly inhibited soybean seedling growth. Conversely, inoculation with O. picturae significantly improved growth indices such as plant height, root length, and fresh weight, while also promoting recovery in soil physiological indicators and pH. Metabolomic and transcriptomic analyses identified 157 genes related to aspartic acid, cysteine, and flavonoid biosynthesis pathways. Sixty-three microbial species were significantly associated with metabolites in these pathways, including pathogenic, adversity-resistant, and bioconductive bacteria. This research experimentally demonstrates, for the first time, the growth-promoting effect of the O. picturae strain on soybean seedlings under non-stress conditions. It also highlights its role in enhancing root growth and reducing Cd accumulation in the roots under Cd stress. Additionally, through the utilization of untargeted metabolomics, metagenomics, and transcriptomics for a multi-omics analysis, we investigated the impact of O. picturae on the soil microbiome and its correlation with differential gene expression in plants. This innovative approach unveils the molecular mechanisms underlying O. picturae's promotion of root growth and adaptation to Cd stress.
Asunto(s)
Cadmio , Glycine max , Plantones , Estrés Fisiológico , Glycine max/crecimiento & desarrollo , Glycine max/efectos de los fármacos , Glycine max/microbiología , Glycine max/metabolismo , Plantones/efectos de los fármacos , Plantones/crecimiento & desarrollo , Cadmio/toxicidad , Estrés Fisiológico/efectos de los fármacos , Contaminantes del Suelo/toxicidad , Raíces de Plantas/crecimiento & desarrollo , Raíces de Plantas/efectos de los fármacos , Raíces de Plantas/microbiología , Raíces de Plantas/metabolismo , Bacillaceae/crecimiento & desarrollo , Bacillaceae/metabolismo , Bacillaceae/genética , Bacillaceae/efectos de los fármacos , Microbiología del SueloRESUMEN
BACKGROUND: This study aimed to determine risk factors for poor in-hospital outcomes in a large cohort of older adult patients with acute non-traffic traumatic spinal cord injury (tSCI). METHODS: This is a population-based, retrospective, observational study. Data of older adults ≥65 years with a primary discharge diagnosis of acute non-traffic tSCI were extracted from the US National Inpatient Sample (NIS) database 2005-2018. Traffic-related tSCI admissions or patients lacking complete data on age, sex and outcomes of interest were excluded. Univariate and multivariate logistic regression analysis was used to determine associations between variables and in-hospital outcomes. RESULTS: Data of 49,449 older patients (representing 246,939 persons in the US) were analyzed. The mean age was 79.9 years. Multivariable analyses revealed that severe International Classification of Disease (ICD)-based injury severity score (ICISS) (adjusted odds ratio [aOR] = 3.14, 95% confidence interval [CI]: 2.77-3.57), quadriplegia (aOR = 2.79, 95%CI: 2.34-3.32), paraplegia (aOR = 2.60, 95%CI:1.89-3.58), cervical injury with vertebral fracture (aOR = 2.19, 95%CI: 1.90-2.52), and severe liver disease (aOR = 2.33, 95%CI: 1.34-4.04) were all strong independent predictors of in-hospital mortality. In addition, malnutrition (aOR = 3.19, 95% CI: 2.93-3.48) was the strongest predictors of prolonged length of stay (LOS). CONCLUSIONS: Several critical factors for in-hospital mortality, unfavorable discharge, and prolonged LOS among US older adults with acute non-traffic tSCI were identified. In addition to the factors associated with initial severity, the presence of severe liver disease and malnutrition emerged as strong predictors of unfavorable outcomes, highlighting the need for special attention for these patient subgroups.
RESUMEN
Soybean is the major global source of edible oils and vegetable proteins. Seed size and weight are crucial traits determining the soybean yield. Understanding the molecular regulatory mechanism underlying the seed weight and size is helpful for improving soybean genetic breeding. The molecular regulatory pathways controlling the seed weight and size were investigated in this study. The 100-seed weight, seed length, seed width, and seed weight per plant of a chromosome segment substitution line (CSSL) R217 increased compared with those of its recurrent parent 'Suinong14' (SN14). Transcriptomic and proteomic analyses of R217 and SN14 were performed at the seed developmental stages S15 and S20. In total, 2643 differentially expressed genes (DEGs) and 208 differentially accumulated proteins (DAPs) were detected at S15, and 1943 DEGs and 1248 DAPs were detected at S20. Furthermore, integrated transcriptomic and proteomic analyses revealed that mitogen-activated protein kinase signaling and cell wall biosynthesis and modification were potential pathways associated with seed weight and size control. Finally, 59 candidate genes that might control seed weight and size were identified. Among them, 25 genes were located on the substituted segments of R217. Two critical pathways controlling seed weight were uncovered in our work. These findings provided new insights into the seed weight-related regulatory network in soybean.
RESUMEN
OBJECTIVES: The accurate localization of the foreign bodies (FBs) is essential. This work presents a new noninvasive technique for subcutaneous metallic FBs under a radiographic grid, a system that simplifies the localization of facial FBs removal using a grid with embedded reference points. METHODS: This work designed a retrospective study to evaluate the effect of a radiographic grid on FBs removal surgery. All patients who met the inclusion criteria and attended the Hospital of Stomatology of China Medical University from January 2022 to June 2023 were enrolled and randomly divided into grid and non-grid groups. The assessment of facial swelling, the primary indicator, was conducted on days 2 and 7 post-surgery. The variables were analyzed using the Student t test and a repeated-measures general linear model. RESULTS: The study sample consisted of 20 patients, with 14 males (70%) and 6 females (30%), who had an average age of 30.30 ± 5.38. The average time of operation was 1.85 ± 0.66 h (range 0.7 to 3.2). In the present cases in this report, of the 20 patients' FBs, 14 were metal, 5 were glass, and 1 was residual root. And the FBs were surgically removed with no postoperative complications. Through comparison, it was found that the degree of swelling on day 2 postoperatively was significantly different between the grid group and the non-grid group (P < 0.05). CONCLUSIONS: This study demonstrates that a radiographic grid with mark points is a more efficient approach compared with traditional methods for FBs removal, and this surgical method is more accurate, fast and noninvasive.
Asunto(s)
Cara , Cuerpos Extraños , Femenino , Masculino , Humanos , Adulto Joven , Adulto , Estudios Retrospectivos , China , Cuerpos Extraños/diagnóstico por imagen , Cuerpos Extraños/cirugía , VidrioRESUMEN
Soybean is one of the most economically important crops worldwide and an important source of unsaturated fatty acids and protein for the human diet. Consumer demand for healthy fats and oils is increasing, and the global demand for vegetable oil is expected to double by 2050. Identification of key genes that regulate seed fatty acid content can facilitate molecular breeding of high-quality soybean varieties with enhanced fatty acid profiles. Here, we analysed the genetic architecture underlying variations in soybean seed fatty acid content using 547 accessions, including mainly landraces and cultivars from northeastern China. Through fatty acid profiling, genome re-sequencing, population genomics analyses, and GWAS, we identified a SEIPIN homologue at the FA9 locus as an important contributor to seed fatty acid content. Transgenic and multiomics analyses confirmed that FA9 was a key regulator of seed fatty acid content with pleiotropic effects on seed protein and seed size. We identified two major FA9 haplotypes in 1295 resequenced soybean accessions and assessed their phenotypic effects in a field planting of 424 accessions. Soybean accessions carrying FA9H2 had significantly higher total fatty acid contents and lower protein contents than those carrying FA9H1 . FA9H2 was absent in wild soybeans but present in 13% of landraces and 26% of cultivars, suggesting that it may have been selected during soybean post-domestication improvement. FA9 therefore represents a useful genetic resource for molecular breeding of high-quality soybean varieties with specific seed storage profiles.
Asunto(s)
Ácidos Grasos , Glycine max , Humanos , Ácidos Grasos/metabolismo , Glycine max/genética , Ácidos Grasos Insaturados/metabolismo , Proteínas de Plantas/genética , Proteínas de Plantas/metabolismo , Aceites de Plantas/metabolismo , Semillas/genética , Semillas/metabolismoRESUMEN
OBJECTIVES: Spinal cord injury (SCI) is any spinal cord injury or affliction that results in temporary or permanent impairment of motor or sensory function. This study determined the prevalence of frailty and its impact on in-hospital outcomes of patients admitted with acute traumatic SCI (TSCI). METHODS: This retrospective study extracted data of adults 18 to 85 years with acute TSCI from the US Nationwide Inpatient Sample (NIS) 2016 to 2018. Frailty status were assessed by the 11-factor modified Frailty Index (mFI-11) through claim codes. Patients with an mFI ≥3 were classified as frail. Associations between study variables and in-hospital mortality, discharge status, prolonged length of stay, severe infection, and hospital costs were determined by univariate and multivariable regression analyses. RESULTS: A total of 52,263 TSCI patients were identified, where 12,203 (23.3%) patients were frail. After adjusting for relevant confounders, frailty was independently associated with increased risk for in-hospital mortality [adjusted odds ratio (aOR) = 1.25, 95% CI:1.04-1.49], unfavorable discharge (aOR =1.15, 95% CI: 1.09-1.22), prolonged length of stay (aOR =1.32, 95% CI: 1.24-1.40), and severe infection (aOR =2.52, 95% CI: 2.24-2.83), but not hospital cost. Stratified analyses revealed frailty was associated with higher unfavorable discharge and severe infection regardless of age, Charlson Comorbidity Index, and injury level. CONCLUSIONS: In acute TSCI, frailty is independently associated with increased risk for adverse inpatient outcomes in terms of in-hospital mortality, prolonged hospital stays, unfavorable discharge, and particularly severe infection.
Asunto(s)
Fragilidad , Traumatismos de la Médula Espinal , Adulto , Humanos , Fragilidad/epidemiología , Fragilidad/complicaciones , Estudios Retrospectivos , Pacientes Internos , Traumatismos de la Médula Espinal/complicaciones , Traumatismos de la Médula Espinal/epidemiología , Hospitalización , Tiempo de Internación , Complicaciones Posoperatorias/etiología , Factores de RiesgoRESUMEN
Lead (Pb) and cadmium (Cd) are common heavy metal pollutants that are often found in the soil in soybean agricultural production, adversely impacting symbiotic nitrogen fixation in soybean nodules. In this study, the exposure of soybean nodules to Pb and Cd stress was found to reduce nitrogenase activity. Shifts in the RNA methylation profiles of nodules were subsequently examined by profiling the differential expression of genes responsible for regulating m6A modifications and conducting transcriptome-wide analyses of m6A methylation profiles under Pb and Cd stress condition. Differentially methylated genes (DMGs) that were differentially expressed were closely related to reactive oxygen species activity and integral membrane components. Overall, 19 differentially expressed DMGs were ultimately determined to be responsive to both Pb and Cd stress, including Glyma.20G082450, which encodes GmAMT1;1 and was confirmed to be a positive regulator of nodules tolerance to Pb and Cd. Together, these results are the first published data corresponding to transcriptome-wide m6A methylation patterns in soybean nodules exposed to Cd and Pb stress, and provide novel molecular insight into the regulation of Pb and Cd stress responses in nodules, highlighting promising candidate genes related to heavy metal tolerance, that may also be amenable to application in agricultural production. ENVIRONMENTAL IMPLICATIONS: Lead (Pb) and cadmium (Cd) are prevalent heavy metal pollutants in soil, and pose a major threat to crop production, food security and human health. Here, MeRIP-seq approach was employed to analyze the regulatory network activated in soybean nodules under Pb and Cd stress, ultimately leading to the identification of 19 shared differentially expressed DMGs. When overexpressed, GmATM1;1 was found to enhance the Pb and Cd tolerance of soybean nodules. These results provide a theoretical basis for studies on tolerance to heavy metals in symbiotic nitrogen fixation, and provide an approach to enhancing Pb and Cd tolerance in soybean production.
Asunto(s)
Contaminantes Ambientales , Metales Pesados , Contaminantes del Suelo , Humanos , Cadmio/metabolismo , Transcriptoma , Glycine max , Plomo , Metales Pesados/metabolismo , Metilación , Suelo , Contaminantes del Suelo/metabolismoRESUMEN
Environmental perception plays a fundamental role in decision-making and is crucial for ensuring the safety of autonomous driving. A pressing challenge is the online evaluation of perception uncertainty, a crucial step towards ensuring the safety and the industrialization of autonomous driving. High-definition maps offer precise information about static elements on the road, along with their topological relationships. As a result, the map can provide valuable prior information for assessing the uncertainty associated with static elements. In this paper, a method for evaluating perception uncertainty online, encompassing both static and dynamic elements, is introduced based on the high-definition map. The proposed method is as follows: Firstly, the uncertainty of static elements in perception, including the uncertainty of their existence and spatial information, was assessed based on the spatial and topological features of the static environmental elements; secondly, an online assessment model for the uncertainty of dynamic elements in perception was constructed. The online evaluation of the static element uncertainty was utilized to infer the dynamic element uncertainty, and then a model for recognizing the driving scenario and weather conditions was constructed to identify the triggering factors of uncertainty in real-time perception during autonomous driving operations, which can further optimize the online assessment model for perception uncertainty. The verification results on the nuScenes dataset show that our uncertainty assessment method based on a high-definition map effectively evaluates the real-time perception results' performance.
RESUMEN
For the robust fault-tolerant control of the controllable suspension system, a control strategy driven by knowledge-data fusion is proposed. Firstly, the boundary fuzziness between perturbation type uncertainty and gain type fault is analyzed, and then a data-driven method is introduced to avoid the state estimation of system uncertainty and fault. The proximal policy optimization algorithm in reinforcement learning is selected to construct a "data control law", to deal with uncertainty and fault. On the other hand, based on the classical sky-hook control, the "knowledge control law" for system performance optimization is designed, taking into account the nonlinear and non-stationary characteristics of the system. Furthermore, the dependency between robust fault tolerance and performance optimization control is revealed, and the two control laws are fused by numerical multiplication, to realize the performance matching optimization control of robust fault tolerance of controllable suspension system driven by knowledge-data fusion. Finally, the effectiveness and feasibility of the proposed method are verified by the simulation and real-time experiment of non-stationary excitation and near-stationary excitation under the combination of uncertainty and fault.
RESUMEN
Background Iodinated contrast agents (ICAs), which are widely used in CT angiography (CTA), may cause adverse effects in humans, and their use is time-consuming and costly. Purpose To develop an ICA-free deep learning imaging model for synthesizing CTA-like images and to assess quantitative and qualitative image quality as well as the diagnostic accuracy of synthetic CTA (Syn-CTA) images. Materials and Methods A generative adversarial network (GAN)-based CTA imaging model was trained, validated, and tested on retrospectively collected pairs of noncontrast CT and CTA images of the neck and abdomen from January 2017 to June 2022, and further validated on an external data set. Syn-CTA image quality was evaluated using quantitative metrics. In addition, two senior radiologists scored the visual quality on a three-point scale (3 = good) and determined the vascular diagnosis. The validity of Syn-CTA images was evaluated by comparing the visual quality scores and diagnostic accuracy of aortic and carotid artery disease between Syn-CTA and real CTA scans. Results CT scans from 1749 patients (median age, 60 years [IQR, 50-68 years]; 1057 male patients) were included in the internal data set: 1137 for training, 400 for validation, and 212 for testing. The external validation set comprised CT scans from 42 patients (median age, 67 years [IQR, 59-74 years]; 37 male patients). Syn-CTA images had high similarity to real CTA images (normalized mean absolute error, 0.011 and 0.013 for internal and external test set, respectively; peak signal-to-noise ratio, 32.07 dB and 31.58 dB; structural similarity, 0.919 and 0.906). The visual quality of Syn-CTA and real CTA images was comparable (internal test set, P = .35; external validation set, P > .99). Syn-CTA showed reasonable to good diagnostic accuracy for vascular diseases (internal test set: accuracy = 94%, macro F1 score = 91%; external validation set: accuracy = 86%, macro F1 score = 83%). Conclusion A GAN-based model that synthesizes neck and abdominal CTA-like images without the use of ICAs shows promise in vascular diagnosis compared with real CTA images. Clinical trial registration no. NCT05471869 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Zhang and Turkbey in this issue.
Asunto(s)
Aorta , Angiografía por Tomografía Computarizada , Humanos , Masculino , Persona de Mediana Edad , Anciano , Estudios Retrospectivos , Tomografía Computarizada por Rayos X , Arterias CarótidasRESUMEN
Objective: Pediatric spinal cord injury without radiographic abnormality (SCIWORA) caused by backbend practice is increasing. This study proposed an underlying 'combined injury mechanism' related to the spinal cord and femoral nerve overstretching. Methods: Pediatric patients diagnosed with backbend-associated SCIWORA at the China Rehabilitation Research Center during 2017-2021 were recruited. Clinical and imaging data were collected, and each patient's clinical course and prognosis were determined. Healthy dancers were recruited to simulate the backbend, obtain images, and estimate the spinal cord and femoral nerve stretch ratio. A model for the 'combined injury mechanism' was established using 4-week-old SD rats. Results: Forty-two SCIWORA female patients with an average age of 6 (SD 1) years and an average hospitalization time of 91 (SD 43) days were assessed. The primary initial symptom was pain in the back and/or lower extremities (33, 79%). The average time from injury onset to severe paralysis was 2.0 (SD 0.6) hours. Most patients had complete paraplegia (32, 76%), and neurological levels were distributed mainly in thoracic segments (38, 91%). Patients with elicited tendon reflexes on admission tended to have an incomplete spinal cord injury (p = 0.001) and improved motor recovery (p = 0.018). After one year, the most common complications were scoliosis (31, 74%) and abnormal hips (14, 33%). Injury of the caudal spinal cord torn by nerve roots was confirmed by surgical exploration in a case. The thoracic spinal cord and femoral nerves were overstretched by 148.8 ± 3.6% and111.7 ± 4.0%, respectively, in a full backbend posture. The 'combined injury mechanism' was partially replicated in the animal model. Conclusion: Spinal overstretch and transient dislocation are considered the primary mechanisms by which SCIWORA occurs in children. Overstretching the femoral nerve aggravates spinal cord injuries caused by backbend practice.