Explore the vast range of titles available.

Object detection algorithms have evolved from two-stage to single-stage architectures, with foundation models achieving sustained improvements in accuracy. However, in intelligent retail scenarios, small object detection and occlusion issues still lead to significant performance degradation. To address these challenges, this paper proposes an improved model based on YOLOv11, focusing on resolving insufficient multi-scale feature coupling and occlusion sensitivity. First, a multi-scale feature extraction network (MFENet) is designed. It splits input feature maps into dual branches along the channel dimension: the upper branch performs local detail extraction and global semantic enhancement through secondary partitioning, while the lower branch integrates CARAFE (content-aware reassembly of features) upsampling and SENet (squeeze-and-excitation network) channel weight matrices to achieve adaptive feature enhancement. The three feature streams are fused to output multi-scale feature maps, significantly improving small object detail retention. Second, a convolutional block attention module (CBAM) is introduced during feature fusion, dynamically focusing on critical regions through channel–spatial dual attention mechanisms. A fuseModule is designed to aggregate multi-level features, enhancing contextual modeling for occluded objects. Additionally, the extreme-IoU (XIoU) loss function replaces the traditional complete-IoU (CIoU), combined with XIoU-NMS (extreme-IoU non-maximum suppression) to suppress redundant detections, optimizing convergence speed and localization accuracy. Experiments demonstrate that the improved model achieves a mean average precision (mAP50) of 0.997 (0.2% improvement) and mAP50-95 of 0.895 (3.5% improvement) on the RPC product dataset and the 6th Product Recognition Challenge dataset. The recall rate increases to 0.996 (0.6% improvement over baseline). Although frames per second (FPS) decreased compared to the original model, the improved model still meets real-time requirements for retail scenarios. The model exhibits stable noise resistance in challenging environments and achieves 84% mAP in cross-dataset testing, validating its generalization capability and engineering applicability. Video streams were captured using a Zhongweiaoke camera operating at 60 fps, satisfying real-time detection requirements for intelligent retail applications.

BackgroundParkinson's disease (PD) is a common degenerative nervous system disease. At present, there are certain limitations in various treatment options aimed at preventing or delaying the progression of PD. Therefore, the exploration of new drugs for PD is beneficial. Mendelian randomization (MR) analysis can be used to explore the association between drugs and diseases. In this study, MR analysis was adopted to investigate the causal relationship between 23 drugs and PD. These drugs have been approved for the treatment of different diseases, such as salicylic acid and derivatives (collectively called salicylates, e.g., aspirin, used for fever and pain relief), antithrombotic agents (e.g., warfarin, aspirin, used for preventing thrombotic events).MethodsThe GWAS data for the 23 drugs were obtained from the UK Biobank (UKB) project, while the GWAS data for PD were sourced from FinnGen. Single-Nucleotide Polymorphisms (SNPs) were selected as instrumental variables (IVs). We first performed a series of quality control steps (including MR-PRESSO) to select the appropriate SNPs. Two-sample MR analysis was performed using five different methods, including inverse variance weighting (IVW) with random-effects model, weighted median, MR-Egger, simple model, and weighted model. At the same time, sensitivity analysis was carried out using the MR-Egger and Cochran's Q test to ensure the authenticity and reliability of the results.ResultsIn MR-PRESSO, salicylates and antithrombotic agents showed statistically significant associations with PD, respectively. In the main MR analysis (IVW), there was a negative causal relationship between salicylates and PD (OR = 0.73, 95% CI = 0.54–0.98, p = .039). Similarly, there was a negative causal relationship between antithrombotic agents and PD (OR = 0.70, 95%CI = 0.52–0.96, p = .027). No statistically significant association was found between the remaining 21 drugs and PD.ConclusionThis MR study demonstrated that salicylates and antithrombotic agents can reduce the risk of PD, thus providing a novel avenue for future drug exploration in PD.

IntroductionThe SARS-CoV-2 Omicron variant has become the dominant SARS-CoV-2 variant and exhibits immune escape to current COVID-19 vaccines, the further boosting strategies are required.MethodsWe have conducted a non-randomized, open-label and parallel-controlled phase 4 trial to evaluate the magnitude and longevity of immune responses to booster vaccination with intramuscular adenovirus vectored vaccine (Ad5-nCoV), aerosolized Ad5-nCoV, a recombinant protein subunit vaccine (ZF2001) or homologous inactivated vaccine (CoronaVac) in those who received two doses of inactivated COVID-19 vaccines.ResultsThe aerosolized Ad5-nCoV induced the most robust and long-lasting neutralizing activity against Omicron variant and IFNg T-cell response among all the boosters, with a distinct mucosal immune response. SARS-CoV-2-specific mucosal IgA response was substantially generated in subjects boosted with the aerosolized Ad5-nCoV at day 14 post-vaccination. At month 6, participants boosted with the aerosolized Ad5-nCoV had remarkably higher median titer and seroconversion of the Omicron BA.4/5-specific neutralizing antibody than those who received other boosters.DiscussionOur findings suggest that aerosolized Ad5-nCoV may provide an efficient alternative in response to the spread of the Omicron BA.4/5 variant.Clinical trial registrationhttps://www.chictr.org.cn/showproj.html?proj=152729, identifier ChiCTR2200057278.

The sound-evoked electrical compound potential known as auditory brainstem response (ABR) represents the firing of a heterogenous population of auditory neurons in response to sound stimuli, and is often used for clinical diagnosis based on wave amplitude and latency. However, recent ABR applications to detect human cochlear synaptopathy have led to inconsistent results, mainly due to the high variability of ABR wave-1 amplitude. Here, rather than focusing on the amplitude of ABR wave 1, we evaluated the use of ABR wave curvature to detect cochlear synaptic loss. We first compared four curvature quantification methods using simulated ABR waves, and identified that the cubic spline method using five data points produced the most accurate quantification. We next evaluated this quantification method with ABR data from an established mouse model with cochlear synaptopathy. The data clearly demonstrated that curvature measurement is more sensitive and consistent in identifying cochlear synaptic loss in mice compared to the amplitude and latency measurements. We further tested this curvature method in a different mouse model presenting with otitis media. The change in curvature profile due to middle ear infection in otitis media is different from the profile of mice with cochlear synaptopathy. Thus, our study suggests that curvature quantification can be used to address the current ABR variability issue, and may lead to additional applications in the clinic diagnosis of hearing disorders.

Objective Gastric cancer (GC) is one of the most malignant tumors worldwide. Thus, it is necessary to explore the underlying mechanisms of GC progression and develop novel therapeutic regimens. Long non-coding RNAs (lncRNAs) have been demonstrated to be abnormally expressed and regulate the malignant behaviors of cancer cells. Our previous research demonstrated that lncRNA colon cancer-associated transcript 2 (CCAT2) has potential value for GC diagnosis and discrimination. However, the functional mechanisms of lncRNA CCAT2 in GC development remain to be explored. Methods GC and normal adjacent tissues were collected to detect the expression of lncRNA CCAT2, ESRP1 and CD44 in clinical specimens and their clinical significance for GC patients. Cell counting kit-8, wound healing and transwell assays were conducted to investigate the malignant behaviors in vitro. The generation of nude mouse xenografts by subcutaneous, intraperitoneal and tail vein injection was performed to examine GC growth and metastasis in vivo. Co-immunoprecipitation, RNA-binding protein pull-down assay and fluorescence in situ hybridization were performed to reveal the binding relationships between ESRP1 and CD44. Results In the present study, lncRNA CCAT2 was overexpressed in GC tissues compared to adjacent normal tissues and correlated with short survival time of patients. lncRNA CCAT2 promoted the proliferation, migration and invasion of GC cells. Its overexpression modulates alternative splicing of Cluster of differentiation 44 (CD44) variants and facilitates the conversion from the standard form to variable CD44 isoform 6 (CD44v6). Mechanistically, lncRNA CCAT2 upregulated CD44v6 expression by binding to epithelial splicing regulatory protein 1 (ESRP1), which subsequently mediates CD44 alternative splicing. The oncogenic role of the lncRNA CCAT2/ESRP1/CD44 axis in the promotion of malignant behaviors was verified by both in vivo and in vitro experiments. Conclusions Our findings identified a novel mechanism by which lncRNA CCAT2, as a type of protein-binding RNA, regulates alternative splicing of CD44 and promotes GC progression. This axis may become an effective target for clinical diagnosis and treatment.

INTRODUCTION Oculomotor and gait dysfunctions are closely associated with cognition. However, oculo‐gait patterns and their correlation with cognition in cerebral small vessel disease (CSVD) remain unclear. METHODS Patients with CSVD from a hospital‐based cohort (n = 194) and individuals with presumed early CSVD from a community‐based cohort (n = 319) were included. Oculo‐gait patterns were measured using the artificial intelligence (AI) –assisted ‘EyeKnow’ eye‐tracking and ‘ReadyGo’ motor evaluation systems. Multivariable linear and logistic regression models were employed to investigate the association between the oculo‐gait parameters and cognition. RESULTS Anti‐saccade accuracy, stride velocity, and swing velocity were significantly associated with cognition in both patients and community dwellers with CSVD, and could identify cognitive impairment in CSVD with moderate accuracy (area under the curve [AUC]: hospital cohort, 0.787; community cohort, 0.810) after adjusting for age and education. DISCUSSION The evaluation of oculo‐gait features (anti‐saccade accuracy, stride velocity, and swing velocity) may help screen cognitive impairment in CSVD. Highlights Oculo‐gait features (lower anti‐saccade accuracy, stride velocity, and swing velocity) were associated with cognitive impairment in cerebral small vessel disease (CSVD). Logistic model integrating the oculo‐gait features, age, and education level moderately distinguished cognitive status in CSVD. Artificial intelligence–assisted oculomotor and gait measurements provide quick and accurate evaluation in hospital and community settings.

Noise is the most common occupational and environmental hazard, and noise-induced hearing loss (NIHL) is the second most common form of sensorineural hearing deficit. Although therapeutics that target the free-radical pathway have shown promise, none of these compounds is currently approved against NIHL by the United States Food and Drug Administration. The present study has demonstrated that tetrandrine (TET), a traditional Chinese medicinal alkaloid and the main chemical isolate of the Stephania tetrandra S. Moore herb, significantly attenuated NIHL in CBA/CaJ mice. TET is known to exert antihypertensive and antiarrhythmic effects through the blocking of calcium channels. Whole-cell patch-clamp recording from adult spiral ganglion neurons showed that TET blocked the transient Ca2+ current in a dose-dependent manner and the half-blocking concentration was 0.6 + 0.1 μM. Consistent with previous findings that modulations of calcium-based signaling pathways have both prophylactic and therapeutic effects against neural trauma, NIHL was significantly diminished by TET administration. Importantly, TET has a long-lasting protective effect after noise exposure (48 weeks) in comparison to 2 weeks after noise exposure. The otoprotective effects of TET were achieved mainly by preventing outer hair cell damage and synapse loss between inner hair cells and spiral ganglion neurons. Thus, our data indicate that TET has great potential in the prevention and treatment of NIHL.

An approach to evolutionary ensemble learning for classification is proposed in which boosting is used to construct a stack of programs. Each application of boosting identifies a single champion and a residual dataset, i.e. the training records that thus far were not correctly classified. The next program is only trained against the residual, with the process iterating until some maximum ensemble size or no further residual remains. Training against a residual dataset actively reduces the cost of training. Deploying the ensemble as a stack also means that only one classifier might be necessary to make a prediction, so improving interpretability. Benchmarking studies are conducted to illustrate competitiveness with the prediction accuracy of current state-of-the-art evolutionary ensemble learning algorithms, while providing solutions that are orders of magnitude simpler. Further benchmarking with a high cardinality dataset indicates that the proposed method is also more accurate and efficient than XGBoost.

The recently described role of RNA methylation in regulating immune cell infiltration into tumors has attracted interest, given its potential impact on immunotherapy response. YTHDF1 is a versatile and powerful m6A reader, but the understanding of its impact on immune evasion is limited. Here, we reveal that tumor-intrinsic YTHDF1 drives immune evasion and immune checkpoint inhibitor (ICI) resistance. Additionally, YTHDF1 deficiency converts cold tumors into responsive hot tumors, which improves ICI efficacy. Mechanistically, YTHDF1 deficiency inhibits the translation of lysosomal genes and limits lysosomal proteolysis of the major histocompatibility complex class I (MHC-I) and antigens, ultimately restoring tumor immune surveillance. In addition, we design a system for exosome-mediated CRISPR/Cas9 delivery to target YTHDF1 in vivo, resulting in YTHDF1 depletion and antitumor activity. Our findings elucidate the role of tumor-intrinsic YTHDF1 in driving immune evasion and its underlying mechanism. YTHDF1 is an m6A reader that binds to methylated RNA and facilitates translation. Here the authors show that tumor intrinsic YTHDF1 promotes tumorigenesis by regulating lysosomal proteolysis of MHC-I and that YTHDF1 targeting boosts anti-tumor immunity and response to immunotherapy in preclinical cancer models.

Scintillators, which can convert high‐energy ionizing radiation into visible light, have been serving as the core component in radiation detectors for more than a century of history. To address the increasing application demands along with the concern on nuclear security, various strategies have been proposed to develop a next‐generation scintillator with a high performance in past decades, among which the novel approach via structure control has received great interest recently due to its high feasibility and efficiency. Herein, the concept of “structure engineering” is proposed for the exploration of this type of scintillators. Via internal or external structure design with size ranging from micro size to macro size, this promising strategy cannot only improve scintillator performance, typically radiation stopping power and light yield, but also extend its functionality for specific applications such as radiation imaging and therapy, opening up a new range of material candidates. The research and development of various types of structured scintillators are reviewed. The current state‐of‐the‐art progresses on structure design, fabrication techniques, and the corresponding applications are discussed. Furthermore, an outlook focusing on the current challenges and future development is proposed. A comprehensive overview on developing novel scintillators by structure engineering strategy, which focuses on rationally tailoring the structures with typical size spanning micro, meso, and macroranges, is provided. The state‐of‐the‐art progresses on structure design, fabrication techniques, and the corresponding applications are systematically discussed. Future perspectives focusing on current challenges are presented as well.