Mg-Sr-Ca containing bioactive glass nanoparticles hydrogel modified mineralized collagen scaffold for bone repair.

The aim of this study is to explore the therapeutic effects of Mg-Sr-Ca containing bioactive glass nanoparticles sodium alginate hydrogel modified mineralized collagen scaffold (Mg-Sr-Ca-BGNs-SA-MC) on the repair of osteoporotic bone defect. During the study, Mg-Sr-Ca containing bioactive glass nanoparticles (Mg-Sr-Ca-BGNs) were synthesized using the sol-gel method, and the Mg-Sr-Ca-BGNs-SA-MC scaffold was synthesized by a simple method. The Mg-Sr-Ca-BGNs and the Mg-Sr-Ca-BGNs-SA-MC scaffold were observed by scanning electron microscopy (SEM) and transmission electron microscopy (TEM). The elements of Mg, Sr, Ca and Si were effectively integrated into Mg-Sr-Ca-BGNs. SEM analysis revealed the presence of Mg-Sr-Ca-BGNs on the scaffold's surface. Furthermore, the cytotoxicity of the scaffolds were assessed using a live/dead assay. The result of the live/dead assay demonstrated that the scaffold materials were non-toxic to cell growth. More importantly, the in vivo study indicated that implanted scaffold promoted tissue regeneration and integration with newly formed bone. Overall, the Mg-Sr-Ca-BGNs-SA-MC scaffold is suitable for guided bone regeneration and beneficial to repair of osteoporotic bone defects.

Association between pretreatment emotional distress and immune checkpoint inhibitor response in non-small-cell lung cancer.

Emotional distress (ED), commonly characterized by symptoms of depression and/or anxiety, is prevalent in patients with cancer. Preclinical studies suggest that ED can impair antitumor immune responses, but few clinical studies have explored its relationship with response to immune checkpoint inhibitors (ICIs). Here we report results from cohort 1 of the prospective observational STRESS-LUNG study, which investigated the association between ED and clinical efficacy of first-line treatment of ICIs in patients with advanced non-small-cell lung cancer. ED was assessed by Patient Health Questionnaire-9 and Generalized Anxiety Disorder 7-item scale. The study included 227 patients with 111 (48.9%) exhibiting ED who presented depression (Patient Health Questionnaire-9 score ≥5) and/or anxiety (Generalized Anxiety Disorder 7-item score ≥5) symptoms at baseline. On the primary endpoint analysis, patients with baseline ED exhibited a significantly shorter median progression-free survival compared with those without ED (7.9 months versus 15.5 months, hazard ratio 1.73, 95% confidence interval 1.23 to 2.43, P = 0.002). On the secondary endpoint analysis, ED was associated with lower objective response rate (46.8% versus 62.1%, odds ratio 0.54, P = 0.022), reduced 2-year overall survival rate of 46.5% versus 64.9% (hazard ratio for death 1.82, 95% confidence interval 1.12 to 2.97, P = 0.016) and detriments in quality of life. The exploratory analysis indicated that the ED group showed elevated blood cortisol levels, which was associated with adverse survival outcomes. This study suggests that there is an association between ED and worse clinical outcomes in patients with advanced non-small-cell lung cancer treated with ICIs, highlighting the potential significance of addressing ED in cancer management. ClinicalTrials.gov registration: NCT05477979 .

Superconductivity of thulium substituted clathrate hexahydrides at moderate pressure.

Due to the BCS theory, hydrogen, the lightest element, would be the prospect of room-temperature superconductor after metallization, but because of the difficulty of the hydrogen metallization, the theory about hydrogen pre-compression was proposed that the hydrogen-rich compounds could be a great option for the high Tc superconductors. The superior properties of TmH6, YbH6 and LuH6 indicated the magnificent potential of heavy rare earth elements for low-pressure stability. Here, we designed XTmH12 (X = Y, Yb, Lu, and La) to obtain higher Tc while maintaining low pressure stability. Most prominently, YbTmH12 can stabilize at a pressure of 60 GPa. Compared with binary TmH6 hydride, its Tc was increased to 48 K. The results provide an effective method for the rational design of moderate pressure stabilized hydride superconductors.

Constructing 3D Zincophilic Skeleton in Nitrogen-Doped Carbon Hybrid Fibers for Dendrite-Free Zn Anodes.

The Zn dendrite growth and side reactions are two major issues for the practical use of Zn metal anodes (ZMAs). Herein, an N-doped carbon-based hybrid fiber with the 3D porous skeleton and the zincophilic Cu nanoparticles (denoted as Cu@HLCF) is developed for stable ZMAs. The zincophilic Cu particles in the skeleton work as the active sites to facilitate uniform Zn nucleation. Meanwhile, the abundant pores in the framework of the hybrid fibers provide a large space to relieve the structural stress and suppress the dendrite growth. Moreover, the good mechanical characteristics of the hybrid fiber ensure its high potential applications for flexible electronics. Theoretical analysis results disclose the strong interaction between Zn and Cu sites, and experimental results demonstrate the low voltage hysteresis, high reversibility, and dendrite-free behavior of the Cu@HLCF host for Zn plating/stripping. Moreover, the solid-state Zn-ion battery (ZIB) assembled with a Cu@HLCF/Zn anode shows the prominent flexibility, impressively reliability, and outstanding cycling capability. Therefore, this work not only provides a novel design for the efficient and stable Zn metal anode but also promotes the development of flexible power sources for flexible electronics.

Association between non-alcoholic fatty liver disease and risk of sarcopenia: a systematic review and meta-analysis.

OBJECTIVES: To determine the association of non-alcoholic fatty liver disease (NAFLD) with the incidence of sarcopenia. DESIGN: Systematic review and meta-analysis of observational clinical studies. SETTING AND PARTICIPANTS: Adults with NAFLD. METHODS: Databases such as PubMed, Embase, Cochrane and Web of Science were searched for eligible studies published from the inception of each database up to 4 April 2023. All cross-sectional studies on the association between NAFLD and sarcopenia were included in this study. The quality of the included studies and risk of bias was assessed using the Agency for Healthcare Research and Quality checklist. STATA V.15.1 software was used for statistical analysis. RESULTS: Of the 1524 retrieved articles, 24 were included in this review, involving 88 609 participants. Our findings showed that the prevalence of sarcopenia was higher in the NAFLD group than in the control group (pooled OR 1.74, 95% CI 1.39 to 2.17). In a subgroup analysis by region, patients with NAFLD showed an increased risk of sarcopenia (pooled OR 1.97, 95% CI 1.54 to 2.51) in the Asian group, whereas patients with NAFLD had no statistically significant association with the risk of sarcopenia in the American and European groups, with a pooled OR of 1.31 (95% CI 0.71 to 2.40) for the American group and a pooled OR of 0.99 (95% CI 0.21 to 4.69) for the European group. Similar results were observed in the sensitivity analysis, and no evidence of publication bias was observed. CONCLUSIONS AND IMPLICATIONS: The current study indicated a significant positive correlation between NAFLD and sarcopenia, which may be affected by regional factors. This study provides the correlation basis for the relationship between NAFLD and sarcopenia and helps to find the quality strategy of sarcopenia targeting NAFLD.

Improved Double Deep Q-Network Algorithm Applied to Multi-Dimensional Environment Path Planning of Hexapod Robots.

Detecting transportation pipeline leakage points within chemical plants is difficult due to complex pathways, multi-dimensional survey points, and highly dynamic scenarios. However, hexapod robots' maneuverability and adaptability make it an ideal candidate for conducting surveys across different planes. The path-planning problem of hexapod robots in multi-dimensional environments is a significant challenge, especially when identifying suitable transition points and planning shorter paths to reach survey points while traversing multi-level environments. This study proposes a Particle Swarm Optimization (PSO)-guided Double Deep Q-Network (DDQN) approach, namely, the PSO-guided DDQN (PG-DDQN) algorithm, for solving this problem. The proposed algorithm incorporates the PSO algorithm to supplant the traditional random selection strategy, and the data obtained from this guided approach are subsequently employed to train the DDQN neural network. The multi-dimensional random environment is abstracted into localized maps comprising current and next level planes. Comparative experiments were performed with PG-DDQN, standard DQN, and standard DDQN to evaluate the algorithm's performance by using multiple randomly generated localized maps. After testing each iteration, each algorithm obtained the total reward values and completion times. The results demonstrate that PG-DDQN exhibited faster convergence under an equivalent iteration count. Compared with standard DQN and standard DDQN, reductions in path-planning time of at least 33.94% and 42.60%, respectively, were observed, significantly improving the robot's mobility. Finally, the PG-DDQN algorithm was integrated with sensors onto a hexapod robot, and validation was performed through Gazebo simulations and Experiment. The results show that controlling hexapod robots by applying PG-DDQN provides valuable insights for path planning to reach transportation pipeline leakage points within chemical plants.

Quantized Zeroth-Order Gradient Tracking Algorithm for Distributed Nonconvex Optimization Under Polyak- [Formula: see text] ojasiewicz Condition.

This article focuses on distributed nonconvex optimization by exchanging information between agents to minimize the average of local nonconvex cost functions. The communication channel between agents is normally constrained by limited bandwidth, and the gradient information is typically unavailable. To overcome these limitations, we propose a quantized distributed zeroth-order algorithm, which integrates the deterministic gradient estimator, the standard uniform quantizer, and the distributed gradient tracking algorithm. We establish linear convergence to a global optimal point for the proposed algorithm by assuming Polyak- [Formula: see text] ojasiewicz condition for the global cost function and smoothness condition for the local cost functions. Moreover, the proposed algorithm maintains linear convergence at low-data rates with a proper selection of algorithm parameters. Numerical simulations validate the theoretical results.

PTK6: An emerging biomarker for prognosis and immunotherapeutic response in clear cell renal carcinoma (KIRC).

Kidney renal clear cell carcinoma (KIRC), one of the most prevalent form of kidney carcinoma, is highly aggressive cancer known for significant immune infiltration and high mortality rates. The absence of sensitivity to traditional therapy has spurred the search for new treatments. Protein Tyrosine Kinase 6 (PTK6) is implicated in promoting cancer growth, spread, and metastasis. Our review of The Cancer Genome Atlas database revealed PTK6 overexpression in KIRC, though its specific role in this cancer type was unclear. We investigated PTK6's cancer-promoting roles in KIRC using the database and confirmed our findings with patient-derived tissues. Our analysis showed that elevated PTK6 expression is linked to worse outcomes and higher levels of immune infiltration. It also correlates positively with neo-antigens (NEO) and DNA ploidy changes in KIRC. This research delves into PTK6's role in KIRC development, suggesting PTK6 as a possible biomarker for prognosis and treatment in KIRC.

Eosinophil Recovery Time Is Associated with Clinical Outcomes in Patients with Type A Acute Aortic Dissection: a Retrospective Cohort Study.

Type A acute aortic dissection (TA-AAD) patients are prone to life-threatening complications and death. This study aimed to analyze the association between eosinophil (EOS) recovery and clinical outcomes in TA-AAD. A total of 274 patients with TA-AAD were eligible for inclusion, and 54 patients died within 1 month. The patients with poor clinical outcomes showed significantly lower EOS count within 8 days after surgery. The time-dependent ROC analysis showed that EOS recovery days predicted 1-month death with an AUC of 0.886 and a cutoff of 6 days. EOS recovery within 6 days was associated with a lower incidence of postoperative infection, a poorer prognosis, and a lower risk of 1-month and 6-month mortality than those requiring more recovery days. Collectively, postoperative early recovery of EOS predicted lower mortality and better prognosis and may be applied as an effective, rapid, and simple tool for the risk stratification and prognostic prediction of patients with TA-AAD.Clinical trial registration number: NCT05409677.

Boosting the Faradaic Efficiency of Br--Mediated Photoelectrochemical Epoxidation by Local Acidity on α-Fe2O3.

The redox mediated photoelectrochemical (PEC) or electrochemical (EC) alkene oxidation process is a promising method to produce high value-added epoxides. However, due to the competitive reaction of water oxidation and overoxidation of the mediator, the utilization of the electricity is far below the ideal value, where the loss of epoxidation's faradaic efficiency (FE) is ≈50%. In this study, a Br-/HOBr-mediated method is developed to achieve a near-quantitative selectivity and ≈100% FE of styrene oxide on α-Fe2O3, in which low concentration of Br- as mediator and locally generated acidic micro-environment work together to produce the higher active HOBr species. A variety of styrene derivatives are investigated with satisfied epoxidation performance. Based on the analysis of local pH-dependent epoxidation FE and products distribution, the study further verified that HOBr serves as the true active mediator to generate the bromohydrin intermediate. It is believed that this strategy can greatly overcome the limitation of epoxidation FE to enable future industrial applications.

Pleiotropic role of GAS6 in cardioprotection against ischemia-reperfusion injury.

INTRODUCTION: Myocardial ischemia-reperfusion (IR) injury is a common medical issue contributing to the onset and progression of ischemic heart diseases (IHD). Growth arrest-specific gene 6 (GAS6), a vitamin K-dependent secretory protein, promotes cell proliferation and inhibits inflammation and apoptosis through binding with Tyro3, Axl, and Mertk (TAM) receptors. OBJECTIVES: Our study aimed to examine the effect of GAS6 pathways activation as a potential new treatment in myocardial IR injury. METHODS: Gain- and loss-of-function experiments were utilized to determine the roles of GAS6 in the pathological processes of myocardial IR injury. RESULTS: Our results revealed down-regulated levels of GAS6, Axl, and SIRT1 in murine hearts subjected to IR injury, and cardiomyocytes challenged with hypoxia reoxygenation (HR) injury. GAS6 overexpression significantly improved cardiac dysfunction in mice subjected to myocardial IR injury, accompanied by reconciled mitochondrial dysfunction, oxidative stress, and apoptosis. In vitro experiments also observed a protective effect of GAS6 in cardiomyocytes. SIRT1 was found to function as a downstream regulator for GAS6/Axl signaling axis. Through screening a natural product library, a polyphenol natural compound catechin was identified to exhibit a protective effect by turning on GAS6/Axl-SIRT1 cascade. CONCLUSIONS: Together, our findings indicate that GAS6 emerges as a potential novel target in the management of myocardial IR injury and other related anomalies.

Mixed crushing and competitive leaching of all electrode material components and metal collector fluid in the spent lithium battery.

Hydrometallurgy is a primary method for recovering cathode electrode materials from spent lithium-ion batteries (LIBs). Most of the current research materials are pure cathode electrode materials obtained through manual disassembly. However, the spent LIBs are typically broken as a whole during the actual industrial recycling which makes the electrode materials combined with the collector fluid. Therefore, the competitive leaching between metal collector fluid and electrode material was examined. The pyrolysis characteristics of the electrode materials were analyzed to determine the pyrolysis temperature. The electrode sheet was pyrolyzed and then crushed for competitive leaching. The effect of pyrolysis was analyzed by XPS. The competitive leaching behavior was studied based on leaching agent concentration, leaching time and leaching temperature. The composition and morphology of the residue were determined to prove the competitive leaching results by XRD-SEM. TG results showed that 500 °C was the suitable pyrolysis temperature. XPS analysis demonstrated that pyrolysis can completely remove PVDF. Li and Co were preferentially leached during the competitive leaching while the leaching rates were 90.10% and 93.40% with 50 min leaching at 70 °C. The Al and Cu had weak competitive leachability and the leaching rate was 29.10% and 0.00%. XRD-SEM analysis showed that Li and Co can be fully leached with residual Al and Cu remaining. The results showed that the mixed leaching of electrode materials is feasible based on its excellent selective leaching properties.

Deep eutectic supramolecular polymer functionalized MXene for enhancing mechanical properties, photothermal conversion, and bacterial inactivation of cellulose textiles.

Two-dimensional (2D) transition metal carbides (Ti3C2Tx MXene) have gained significant attention for their potential in constructing diverse functional materials, However, MXene is easily oxidized and weakly bound to the cellulose matrix, which pose challenges in developing MXene-decorated non-woven fabric with strong bonding and stable thermal management properties. Herein, we successfully prepared deep eutectic supramolecular polymer (DESP) functionalized MXene to address these issues. MXene can be wrapped with DESP to be insulated from water and protected from being oxidized. Subsequently, we achieved an efficient in-situ deposition of DESP-functionalized MXene onto fibers through a combination of dip coating and photopolymerization technique. The resulting nonwoven fabric (CNs-DESP@M) exhibited excellent photothermal conversion properties along with rapid thermal response and functional stability. Interestingly, the interface bonding between MXene and the fiber surface was significantly enhanced due to the abundant pyrogallol groups in DESP, resulting in the composite textile exhibiting commendable mechanical properties (2.68 MPa). Moreover, the as-prepared textile demonstrates outstanding bactericidal efficacy against both Escherichia coli (E. coli) and Staphylococcus aureus (S. aureus). The multifunctional textile, created through a facile and efficient approach, demonstrates remarkable potential for applications in smart textiles, catering to the diverse needs of individuals in the future.

Fine-Grained Recognition With Learnable Semantic Data Augmentation.

Fine-grained image recognition is a longstanding computer vision challenge that focuses on differentiating objects belonging to multiple subordinate categories within the same meta-category. Since images belonging to the same meta-category usually share similar visual appearances, mining discriminative visual cues is the key to distinguishing fine-grained categories. Although commonly used image-level data augmentation techniques have achieved great success in generic image classification problems, they are rarely applied in fine-grained scenarios, because their random editing-region behavior is prone to destroy the discriminative visual cues residing in the subtle regions. In this paper, we propose diversifying the training data at the feature-level to alleviate the discriminative region loss problem. Specifically, we produce diversified augmented samples by translating image features along semantically meaningful directions. The semantic directions are estimated with a covariance prediction network, which predicts a sample-wise covariance matrix to adapt to the large intra-class variation inherent in fine-grained images. Furthermore, the covariance prediction network is jointly optimized with the classification network in a meta-learning manner to alleviate the degenerate solution problem. Experiments on four competitive fine-grained recognition benchmarks (CUB-200-2011, Stanford Cars, FGVC Aircrafts, NABirds) demonstrate that our method significantly improves the generalization performance on several popular classification networks (e.g., ResNets, DenseNets, EfficientNets, RegNets and ViT). Combined with a recently proposed method, our semantic data augmentation approach achieves state-of-the-art performance on the CUB-200-2011 dataset. Source code is available at https://github.com/LeapLabTHU/LearnableISDA.

Engineering design and application of large-scale oil-based drilling cuttings treatment project.

Thermal phase separation technology is a new comprehensive treatment technology, which heats oil-based cuttings to a certain temperature to vaporize oil and water components. Based on a large oil-based drilling cuttings comprehensive utilization project, the engineering design and application effect of thermal phase separation technology were analysed. The practice shows that thermal phase separation technology can reduce the oil content of purified residue to 0.1-0.2%, the average recovery rate of base oil is 94.12% and the annual recovery of base oil is about 4800 t; the purified residue does not have corrosive, leaching toxicity and other dangerous characteristics, and can be used for making bricks or building materials. Thermal phase separation technology is a comprehensive utilization and treatment technology with excellent engineering and environmental benefits, which has a high promotion value.

Dictyophora indusiata polysaccharide mediates priming of the NLRP3 inflammasome activation via TLR4/ NF-κB signaling pathway to exert immunostimulatory effects.

Dictyophora indusiata, commonly known as bamboo fungus, is a type of edible mushroom that is highly popular worldwide for its rich flavor and nutritional value. It is also recognized for its pharmaceutical efficacy, with medicinal benefits attributed to its consumption. One of the most important components of Dictyophora indusiata is polysaccharide, which has been acknowledged as a promising regulator of biological response due to its immunostimulatory and anti-inflammatory properties. However, the specific roles of polysaccharide in modulating the NOD-like receptor protein 3 (NLRP3) inflammasome activation within macrophages remain relatively under-researched. To investigate this further, the mechanism by which Dictyophora indusiata polysaccharide (DIP) exerts its immunostimulatory activity in RAW 264.7 macrophages was analyzed. Results indicated that DIP has the potential to facilitate the priming of NLRP3 inflammasome activation by enhancing TLR4 expression, phosphorylation of IκB-α, and nuclear translocation of NF-κB p65 subunit. It was noted that DIP was unable to mediate the second step of NLRP3 inflammasome activation. The findings of this study provide compelling evidence that DIP has immunomodulatory effects by modulating the NLRP3 inflammasome in RAW264.7 macrophages.

[Contamination Characteristics and Ecological Risk Assessment of Pharmaceuticals and Personal Care Products in Drains Flowing into the Yellow River of Ningxia].

Pharmaceuticals and personal care products (PPCPs) are a group of emerging contaminants causing detrimental effects on aquatic living organisms even at low doses. To investigate the contamination characteristics and ecological risks of PPCPs in drains flowing into the Yellow River of Ningxia, 21 PPCPs were detected and analyzed using solid phase extraction and ultra-high performance liquid chromatography-mass spectrometry in this study. All 21 targeted compounds were detected in the drains, with total concentrations ranging from 47.52 to 1 700.96 ng·L-1. Ciprofloxacin, acetaminophen, benzophenone-3, and diethyltoluamide were the more commonly detected compounds, with detection frequencies exceeding 80%. The five highest-concentration PPCPs were acetaminophen, diethyltoluamide, caffeine, benzophenone-3, and levofloxacin, with the maximum concentrations of 597.21, 563.23, 559.00, 477.28, and 473.07 ng·L-1, respectively. Spatial analysis showed that the pollution levels of PPCPs in the drains of the four cities were different, with average concentrations of ∑PPCPs in the order of Yinchuan>Shizuishan>Wuzhong>Zhongwei. The total concentration of PPCPs before flowing into the Yellow River ranged from 124.82 to 1 046.61 ng·L-1. Source analysis showed that livestock and poultry breeding wastewater was the primary source for sulfadiazine and oxytetracycline, whereas medical wastewater was the primary source for levofloxacin and ciprofloxacin. The primary sources of triclocarban and triclosan were domestic sewage and industrial wastewater, whereas the primary source of caffeine and diethyltoluamide was domestic sewage. The pollution of diciofenac, cimetidine, triclocarban, and triclosan in the drains was positively correlated with the regional population and economic development level. The ecological risk assessment indicated that levofloxacin, diclofenac, gemfibrozil, benzophenone-3, and triclocarban posed high risks to aquatic organisms in drains flowing into the Yellow River. It is worthwhile to consider the mixture risk of the PPCPs that exhibited high risk at most sampling sites.

Care, control and complications of hospitalised patients with type 1 diabetes in China: A nationwide-based registry study.

AIMS: To evaluate the status quo of type 1 diabetes (T1D) management and characteristics of hospitalised patients with T1D in China through a nationwide multicentre registry study, the China Diabetes Type 1 Study (CD1S). MATERIALS AND METHODS: Clinical data from the electronic hospital records of all people with T1D were retrospectively collected in 13 tertiary hospitals across 7 regions of China from January 2016 to December 2021. Patients were defined as newly diagnosed who received a diagnosis of diabetes for less than 3 months. RESULTS: Among the 4993 people with T1D, the median age (range) at diagnosis was 23.0 (1.0-87.0) years and the median disease duration was 2.0 years. The median haemoglobin A1c (HbA1c) level was 10.7%. The prevalence of obesity, overweight, dyslipidemia, and hypertension were 2.5%, 10.8%, 62.5% and 25.9%, respectively. The incidence rate of diabetic ketoacidosis at disease onset was 41.1%, with the highest in children <10 years of age (50.6%). In patients not newly diagnosed, 60.7% were diagnosed with at least one chronic diabetic complication, with the highest proportion (45.3%) of diabetic peripheral neuropathy. Chronic complications were detected in 79.2% of people with T1D duration ≥10 years. CONCLUSIONS: In the most recent years, there were still unsatisfactory metabolic control and high incidence of diabetic ketoacidosis as well as chronic diabetic complications among inpatients with T1D in China. The ongoing CD1S prospective study aims to improve the quality of T1D management nationally.

Image detection of aortic dissection complications based on multi-scale feature fusion.

Background: Aortic dissection refers to the true and false two-lumen separation of the aortic wall, in which the blood in the aortic lumen enters the aortic mesomembrane from the tear of the aortic intima to separate the mesomembrane and expand along the long axis of the aorta. Purpose: In view of the problems of individual differences, complex complications and many small targets in clinical aortic dissection detection, this paper proposes a convolution neural network MFF-FPN (Multi-scale Feature Fusion based Feature Pyramid Network) for the detection of aortic dissection complications. Methods: The proposed model uses Resnet50 as the backbone for feature extraction and builds a pyramid structure to fuse low-level and high-level feature information. We add an attention mechanism to the backbone network, which can establish inter-dependencies between feature graph channels and enhance the representation quality of CNN. Results: The proposed method has a mean average precision (MAP) of 99.40% in the task of multi object detection for aortic dissection and complications, which is higher than the accuracy of 96.3% on SSD model and 99.05% on YoloV7 model. It greatly improves the accuracy of small target detection such as cysts, making it more suitable for clinical focus detection. Conclusions: The proposed deep learning model achieves feature reuse and focuses on local important information. By adding only a small number of model parameters, we are able to greatly improve the detection accuracy, which is effective in detecting small target lesions commonly found in clinical settings, and also performs well on other medical and natural datasets.