CrossLinkNet: An Explainable and Trustworthy AI Framework for Whole-Slide Images Segmentation

In the intelligent medical diagnosis area,Artificial Intelligence(AI)’s trustworthiness,reliability,and interpretability are critical,especially in cancer diagnosis.Traditional neural networks,while excellent at processing natural images,often lack interpretability and adaptability when processing high-resolution digital pathological images.This limitation is particularly evident in pathological diagnosis,which is the gold standard of cancer diagnosis and relies on a pathologist’s careful examination and analysis of digital pathological slides to identify the features and progression of the disease.Therefore,the integration of interpretable AI into smart medical diagnosis is not only an inevitable technological trend but also a key to improving diagnostic accuracy and reliability.In this paper,we introduce an innovative Multi-Scale Multi-Branch Feature Encoder(MSBE)and present the design of the CrossLinkNet Framework.The MSBE enhances the network’s capability for feature extraction by allowing the adjustment of hyperparameters to configure the number of branches and modules.The CrossLinkNet Framework,serving as a versatile image segmentation network architecture,employs cross-layer encoder-decoder connections for multi-level feature fusion,thereby enhancing feature integration and segmentation accuracy.Comprehensive quantitative and qualitative experiments on two datasets demonstrate that CrossLinkNet,equipped with the MSBE encoder,not only achieves accurate segmentation results but is also adaptable to various tumor segmentation tasks and scenarios by replacing different feature encoders.Crucially,CrossLinkNet emphasizes the interpretability of the AI model,a crucial aspect for medical professionals,providing an in-depth understanding of the model’s decisions and thereby enhancing trust and reliability in AI-assisted diagnostics.

A Linked List Encryption Scheme for Image Steganography without Embedding

Information steganography has received more and more attention from scholars nowadays,especially in the area of image steganography,which uses image content to transmit information and makes the existence of secret information undetectable.To enhance concealment and security,the Steganography without Embedding(SWE)method has proven effective in avoiding image distortion resulting from cover modification.In this paper,a novel encrypted communication scheme for image SWE is proposed.It reconstructs the image into a multi-linked list structure consisting of numerous nodes,where each pixel is transformed into a single node with data and pointer domains.By employing a special addressing algorithm,the optimal linked list corresponding to the secret information can be identified.The receiver can restore the secretmessage fromthe received image using only the list header position information.The scheme is based on the concept of coverless steganography,eliminating the need for any modifications to the cover image.It boasts high concealment and security,along with a complete message restoration rate,making it resistant to steganalysis.Furthermore,this paper proposes linked-list construction schemeswithin theproposedframework,which caneffectively resist a variety of attacks,includingnoise attacks and image compression,demonstrating a certain degree of robustness.To validate the proposed framework,practical tests and comparisons are conducted using multiple datasets.The results affirm the framework’s commendable performance in terms of message reduction rate,hidden writing capacity,and robustness against diverse attacks.

2型糖尿病患者心率变异性降低的危险因素分析

目的·探讨2型糖尿病患者心率变异性(heart rate variability,HRV)降低的相关危险因素。方法·选取上海交通大学附属第一人民医院2013年1月—2014年12月收治的210例2型糖尿病患者,分别依据尿白蛋白肌酐比(urinary albumin creatinine ratio,UACR)、血清三酰甘油(triacylglycerol,TAG)水平和是否合并高血压进行分组。通过比较组间病例临床特征和HRV等指标的差异,探讨HRV指标及其影响因素间的相关关系。结果·UACR升高组较UACR正常组24h平均心率升高,SDNN[正常窦性心搏RR间期(NN间期)标准差]降低(均P<0.05);TAG升高组较TAG正常组24h平均心率升高,SDNN和pNN50(相邻NN间期差值超过50ms的心搏数占总心搏数的百分比)降低(均P<0.05);合并高血压组较对照组最小频域功率小时降低(P<0.05)。回归分析显示,TAG和SDNN线性相关(P<0.05),舒张压和24h平均心率、SDNN、频域功率24h、最小频域功率小时线性相关(均P<0.05),年龄和24h平均心率、SDNN、SDANN(每5min NN间期平均值的标准差)、频域功率24h、最小频域功率小时、最大频域功率小时线性相关(均P<0.05)。结论·年龄、血清TAG水平和是否合并高血压是2型糖尿病患者HRV降低的危险因素,早期对HRV的降低进行检测将有助于预防糖尿病心血管事件的发生。

Cell-free circulating tumor DNA in cancer

Cancer is a common cause of death worldwide.Despite significant advances in cancer treatments,the morbidity and mortality are still enormous.Tumor heterogeneity,especially intratumoral heterogeneity,is a significant reason underlying difficulties in tumor treatment and failure of a number of current therapeutic modalities,even of molecularly targeted therapies.The development of a virtually noninvasive "liquid biopsy" from the blood has been attempted to characterize tumor heterogeneity.This review focuses on cell-free circulating tumor DNA(ctDNA) in the bloodstream as a versatile biomarker.ctDNA analysis is an evolving field with many new methods being developed and optimized to be able to successfully extract and analyze ctDNA,which has vast clinical applications.ctDNA has the potential to accurately genotype the tumor and identify personalized genetic and epigenetic alterations of the entire tumor.In addition,ctDNA has the potential to accurately monitor tumor burden and treatment response,while also being able to monitor minimal residual disease,reducing the need for harmful adjuvant chemotherapy and allowing more rapid detection of relapse.There are still many challenges that need to be overcome prior to this biomarker getting wide adoption in the clinical world,including optimization,standardization,and large multicenter trials.

Zinc-doped g-C_3N_4/BiVO_4 as a Z-scheme photocatalyst system for water splitting under visible light

A two‐step photocatalytic water splitting system,termed a“Z‐scheme system”,was achieved using Zn‐doped g‐C3N4for H2evolution and BiVO4for O2evolution with Fe2+/Fe3+as a shuttle redox mediator.H2and O2were evaluated simultaneously when the doping amount of zinc was10%.Moreover,Zn‐doped(10%)g‐C3N4synthesized by an impregnation method showed superior active ability to form the Z‐scheme with BiVO4than by in‐situ synthesis.X‐ray diffraction,UV‐Vis spectroscopy,scanning electron microscopy,and X‐ray photoelectron spectroscopy were used to characterize the samples.It was determined that more Zn?N bonds could be formed on the surface of g‐C3N4by impregnation,which could facilitate charge transfer.

Age and geochemistry of Early Ordovician A-type granites in the Northeastern Songnen Block,NE China

Early Ordovician A-type granites in the northeastern(NE) Songnen Block NE China were studied to better understand the geodynamic settings in this region.This research presents new zircon U–Pb ages and wholerock geochemical data for the Early Ordovician granites in the NE Songnen Block. Zircon U–Pb dating indicates that the granite in the Cuibei, Hongxing, and Meixi areas in the NE Songnen Block formed in the Early Ordovician with ages of 471–479 Ma. The granites show geochemical characteristics of high SiO2 and K2 O compositions and low FeOT, MgO, CaO, and P2 O5 compositions. They belong to a high K calc-alkaline series and display a weak peraluminous featurPe with A/CNK values of 0.98–1.14. The rocks have aREE composition of 249.98–423.94 ppm,and are enriched in LREE with(La/Yb)Nvalues of2.87–9.87, and display obvious Eu anomalies(d Eu =0.01–0.29). Trace elements of the studied granites are characterized by enrichment in Rb, Th, U, Pb, Hf, and Sm,and depletion of Ba, Nb, Ta, and Sr. They display geochemical features of high Zr +Y + Nb+Ce values(324–795 ppm) and Ga/Al ratios consistent with A-type granites. Based on particular geochemical features, such as high Rb/Nb(7.98–24.19) and Y/Nb(1.07–3.43), the studied A-type granites can be further classified as an A2-type subgroup. This research indicates that the Early Ordovician A-type granites were formed by the partial melting of ancient crust in an extensional setting. Lower Sr/Y and(Ho/Yb)Nratios indicate that plagioclase and amphibole are residual in the source, and garnet is absent, implying that the magma was generated at low levels of pressure. By contrast, the contemporaneous granites in the SE Xing'an Block suggest a subduction-related tectonic setting, and its adakitic property indicates a thickened continental crust.We suggest that the Paleo-Asian Ocean plate between the Xing'an and Songnen blocks subducted northward during the Early Ordovician. Meanwhile, the NE Songnen Block was exposed to a passive continental margin tectonic setting.

归脾汤对心脾两虚型贫血患者红细胞携氧能力影响的临床研究

目的研究归脾汤提高心脾两虚型贫血患者红细胞携氧能力的作用机制。方法心脾两虚型贫血患者35例,随机分成治疗组20例和对照组15例,治疗组给予归脾汤口服,对照组给予安慰剂口服,疗程均为1周。用药前后采用酶联免疫吸附法(ELISA)检测血浆2,3-二磷酸甘油酸(2,3-Diphosphoglycerate,2,3-DPG)浓度、化学比色法检测红细胞Na^+-K^+-ATP酶活性,综合评价红细胞携氧能力。结果治疗后,治疗组Hb、RET#均有所上升与治疗前比较,差异有统计学意义(P<0.05);且治疗组RET#增高与对照组比较,差异有统计学意义(P<0.05)。治疗组中度贫血患者2,3-DPG浓度上升与治疗前比较,差异有统计学意义(P<0.05)。治疗组体倦乏力、头晕目眩、心悸的症状积分下降与治疗前比较,差异有统计学意义(P<0.01);且治疗组体倦乏力、头晕目眩的症状积分下降与对照组比较,差异有统计学意义(P<0.05)。两组红细胞Na^+-K^+-ATP酶活性与治疗前比较均无明显改变,差异无统计学意义(P>0.05);两组间红细胞Na^+-K^+-ATP酶活性变化比较,差异无统计学意义(P>0.05)。治疗后两组中医证候疗效比较,差异有统计学意义(P<0.05)。结论归脾汤对红细胞Na^+-K^+-ATP酶的活性无明显影响,但有增加2,3-DPG浓度的趋势,尤其对中度贫血患者2,3-DPG水平升高明显。提示归脾汤改善缺氧症状可能与其改善红细胞携氧能力有关。

Nicotine protects against ulcerative colitis through regulating microRNA-124 and STAT3

OBJECTIVE Although it is generally believed that nicotine accounts for the beneficial effect of smoking on ulcerative colitis,the underlying mechanisms remain not well-understood.Our previous finding that nicotine inhibits inflammatory responses through inducing miRNA-124 prompted us to ask whether the miRNA is involved in the protective action of nicotine on UC.METHODS Mi R-124 expression in colon tissues and cells was determined by q-PCR and in situ hybridization.The effect of miR-124 on protective role of nicotine in ulcerative colitis was evaluated in DSS-treated mice and IL-6-treated Caco-2 colon epithelial cells.Expression of p-STAT3/STAT3 was detected by immunohistochemistry and Western blot analysis.RESULTS miR-124 expression is upregulated in colon tissues from patients and DSS-induced colitis.Nicotine treatment further elevated miR-124 level in colon tissues of the mice,in infiltrated lymphocytes and epithelial cells,and augmented miR-124 expression in lymphocytes isolated from human ulcerative colon tissues.Administration of nicotine also reduced weight loss,improved DAI and decreased HE score in DSS-induced colitis.Moreover,knockdown of miR-124 in vivo significantly diminished the beneficial effect of nicotine,and in vitro on IL-6-treated Caco-2 colon epithelial cells.Further analysis indicated that nicotine inhibited STAT3 activation in vivo and in IL-6-treated Caco-2 colon epithelial cells and Jurkat human T lymphocytes,in whichmiR-124 knockdown led to increased activation of STAT3.CONCLUSION These data indicated that nicotine exerts its protective action in UC through inducing miR-124 and its effect on STAT3,suggesting that the miR-124/STAT3 system is a potential target for the therapeutic intervention of UC.

MIA-UNet:Multi-Scale Iterative Aggregation U-Network for Retinal Vessel Segmentation

As an important part of the new generation of information technology,the Internet of Things(IoT)has been widely concerned and regarded as an enabling technology of the next generation of health care system.The fundus photography equipment is connected to the cloud platform through the IoT,so as to realize the realtime uploading of fundus images and the rapid issuance of diagnostic suggestions by artificial intelligence.At the same time,important security and privacy issues have emerged.The data uploaded to the cloud platform involves more personal attributes,health status and medical application data of patients.Once leaked,abused or improperly disclosed,personal information security will be violated.Therefore,it is important to address the security and privacy issues of massive medical and healthcare equipment connecting to the infrastructure of IoT healthcare and health systems.To meet this challenge,we propose MIA-UNet,a multi-scale iterative aggregation U-network,which aims to achieve accurate and efficient retinal vessel segmentation for ophthalmic auxiliary diagnosis while ensuring that the network has low computational complexity to adapt to mobile terminals.In this way,users do not need to upload the data to the cloud platform,and can analyze and process the fundus images on their own mobile terminals,thus eliminating the leakage of personal information.Specifically,the interconnection between encoder and decoder,as well as the internal connection between decoder subnetworks in classic U-Net are redefined and redesigned.Furthermore,we propose a hybrid loss function to smooth the gradient and deal with the imbalance between foreground and background.Compared with the UNet,the segmentation performance of the proposed network is significantly improved on the premise that the number of parameters is only increased by 2%.When applied to three publicly available datasets:DRIVE,STARE and CHASE DB1,the proposed network achieves the accuracy/F1-score of 96.33%/84.34%,97.12%/83.17%and 97.06%/84.10%,respectively.The experimental results show that the MIA-UNet is superior to the state-of-the-art methods.

Random Group Recommendation Model Based on Fuzzy Clustering

The group recommendation system is a viral requirement for the Internet service provider to provide recommendation services for all the users in a group. Due to the shared or different interests among users in the group, it is difficult for traditional personal recommendation algorithms to predict items that can meet the requirements of all the users in the group. In this paper, a random group recommendation model is proposed to recommend the top K most appealing items for all the users in a random group. By analyzing item ratings of all the users in the group, the recommendation model can abstract the group as a virtual user. Then a personal recommendation algorithm is applied to suggest the top K most appealing items for the virtual user. And the preference score and fuzzy clustering algorithm based on multiclass are applied to optimize the recommendation result of the group recommendation model. Finally, the Movie Lens-100 K dataset is applied to verify the efficiency of the recommendation model. The experimental results show that the items recommended by the proposed group recommendation model are more popular for all the users in the group than the items recommended by traditional group recommendation algorithms.

Nicotine protects against DSS colitis through regulating microRNA-124 and STAT3

OBJECTIVE Although it is generally believed that nicotine accounts for the beneficial effect of smoking on ulcerative colitis,the underlying mechanisms remain not well understood.Our previous finding that nicotine inhibits inflammatory responses through inducing miRNA-124 prompted us to ask whether the miRNA is involved in the protective action of nicotine on UC.METHODS MiR-124 expres.sion in colon tissues and cells was determined by q-PCR and in situ hybridization.The effect of miR-124 on protective role of nicotine in ulcerative colitis was evaluated in DSS-treated mice and IL-6-treated Caco-2 colon epithelial cells.Expression of p-STAT3/STAT3 was detected by immunohistochemistry and Western-blot analysis.RESULTS miR-124 expression is upregulated in colon tissues from UC patients and DSS-induced colitis mice.Nicotine treatment further elevated miR-124 level in lympho.cytes isolated from human ulcerative colonic mucosa and ulcerative colon tissues from DSS mice,both in infiltrated lymphocytes and epithelial cells.Administration of nicotine also reduced weight loss,improved DAI and decreased HE score in DSS-induced colitis mice.Moreover,knockdown of miR-124 in vivo significantly diminished the beneficial effect of nicotine on murine colitis,and in vitro on IL-6-treated Caco-2 colon epithelial cells.Further analysis indicated that nicotine inhibited STAT3 activation in vivo and in IL-6-treated Caco-2 colon epithelial cells and Jurkat human T lymphocytes,in which miR-124 knockdown led to increased activation of STAT3.Blocking STAT3 activity alone is beneficial for DSS colitis and also abolished nicotine′s protective effect in this model.CONCLUSION These data indicated that nicotine exerts its protective action in UC through inducing miR-124 and its effect on STAT3,and suggest that the miR-124/STAT3 system is a potential target for the therapeutic intervention of UC.

Recommending Authors and Papers Based on ACTTM Community and Bilayer Citation Network

Citation network is often used for academic recommendation. However, it is difficult to achieve high recommendation accuracy and low time complexity because it is often very large and sparse and different citations have different purposes. What's more, some citations include unreasonable information, such as in case of intentional self-citation. To improve the accuracy of citation network-based academic recommendation and reduce the time complexity, we propose an academic recommendation method for recommending authors and papers. In which, an author-paper bilayer citation network is built, then an enhanced topic model, Author Community Topic Time Model(ACTTM) is proposed to detect high quality author communities in the author layer, and a set of attributes are proposed to comprehensively depict the author/paper nodes in the bilayer citation network. Experimental results prove that the proposed ACTTM can detect high quality author communities and facilitate low time complexity, and the proposed academic recommendation method can effectively improve the recommendation accuracy.

企业广告投入如何影响违约风险:“言多而实”抑或“言多而虚”?

学术界关于企业广告投入对其能否健康发展、良性经营存在“言多而实”与“言多而虚”的意见分歧。基于沪深A股上市企业2012—2020年的数据实证研究发现,企业广告投入强度越高,其违约风险越低,即企业广告投入发挥了“言多而实”的积极作用,且该结论通过了一系列稳健性检验。机制分析表明,企业广告投入能通过债务替代效应减少短期债务融资需求,能通过信息传递效应缓解企业内外部信息不对称,并能通过监督治理效应降低企业代理成本,从而改善企业财务境况、提升企业治理水平、降低违约风险。进一步的异质性分析表明,企业广告投入在经济政策确定性强、法律制度完善、社会信任度高的环境下,在国有企业、税法遵从度高、客户集中度低的企业中能够更好地发挥违约风险降低作用。以上结果拓展了广告投入的研究范畴,丰富了相关领域文献,并为政府部门防范违约风险、企业管理者制定广告营销战略提供了重要建议。

miRNA-124 in immune system and immune disorders

In recent years,miR-124 has emerged as a critical modulator of immunity and inflammation.Here,we summarize studies on the function and mechanism of miR-124 in the immune system and immunity-related diseases.They indicated that miR-124 exerts a crucial role in the development of immune system,regulation of immune responses,and inflammatory disorders.It is evident that miR-124 may serve as an informative diagnostic biomarker and therapeutic target in the future.

Performance of CO_2 absorption in a diameter-varying spray tower

The application of spray towers for CO2 capture is a development trend in recent years. However, most of the previous jobs were conducted in a cylindrical tower by using a single spray nozzle, whose configuration and performance is not good enough for industrial application. To solve this problem, the present work proposed a diameter-varying spray tower and a new spray mode of dual-nozzle opposed impinging spray to enhance the heat and mass transfer of CO2 absorption process. Experiments were performed to investigate the mass transfer performance （in terms of the CO2 removal rate （η） and the overall mass transfer coefficient （KGae）） of the improved spray tower under various operating conditions. Experimental results showed that the liquid to gas ratio and mole ratio of MEA to C02 are major factors, which affect the absorption performance and the maximums of η and KGae that are 94.0% and 0.574 kmol. m^-3·h^-1·kPa^-1, respectively, under the experimental conditions. Furthermore, new correlations to predict the mass transfer coefficient of the proposed spray tower are developed in various CO2 concentrations with a Pearson Correlation Coefficient over 90%.

AI+ Medical Image Analysis Oriented Postgraduate Training

In modern medicine,medical image examination has become an important method and tool to deal with clinical diseases.The inherent defects of artificial analysis of medical images make medical images become the most valuable application scenario of artificial intelligence(AI).This paper aims at how to effectively adapt to economic development and cultivate talents who combine artificial intelligence and medicine,which is a difficult problem and challenge facing schools and educators.A new AI+medical imaging talent training model was proposed,and suggestions for improvement were introduced from the course design,assessment system,faculty team,and course textbooks,and the teaching effect was explained through the training process,supporting conditions,and training mechanism,so as to promote the scientific and technological progress of colleges and universities.and development.

An updated role of astragaloside Ⅳ in heart failure

Heart failure has become a global public health problem that seriously threatens human health.Due to "multi-target" effect,traditional Chinese medicine has unique advantages in the treat.ment of heart failure.Astragaloside Ⅳ is one of the main active ingredients of astragalus membrana.ceus.It has the functions of protecting the heart and neovascularization,anti-inflammation,anti-oxida.tion,regulating energy metabolism,neuroprotection and anti-cancer effects.This article reviews the recent progresses of astragaloside Ⅳ in the treatment of heart failure.Data show that astragaloside Ⅳ can inhibit heart fibrosis,attenuate excessively activation of renin-angiotensin system,increase energy metabolism,promote positive inotropic action,inhibit myocardial cell apoptosis,etc,which are all involved in the protective role of astragalosideⅣ in rodents or cellular models of heart failure.Astragalo.side Ⅳ may be a potential active ingredient in traditional Chinese medicine for the treatment of heart failure.

Optimal Deployment Density for Maximum Coverage of Drone Small Cells

With the proliferation of small and mini drones, Drone Small Cells(DSCs) can cooperative multiple drones to provide communication service for ground users as emergency means or supplementary ones of traditional terrestrial cellular networks. In this paper, we study the fundamental problem of optimizing the deployment density of DSCs to achieve the maximum coverage performance. Most related works do not consider cumulative inter-cell interference when studying the coverage performance of DSCs. First, we derive an approximate and closed-form expression of the cumulative inter-cell interference which comes from both probabilistic Line-of-Sight(Lo S) and Non-Line-of-Sight(NLo S) links. Then, we analyze the coverage performance of DSCs and derive the transcendental function of optimal deployment density to obtain the maximum coverage. Last, we propose an algorithm to get the optimal deployment density with low complexity. We conduct both field experiments and Matlab simulations to verify the correctness of theoretical analysis. In addition, we show the impact of some factors on the relation between the deployment density and coverage performance through extensive numerical simulations.

Research on the intelligent internet nursing model based on the child respiratory and asthma control test scale for asthma management of preschool children

BACKGROUND Childhood asthma is a common respiratory ailment that significantly affects preschool children.Effective asthma management in this population is particularly challenging due to limited communication skills in children and the necessity for consistent involvement of a caregiver.With the rise of digital healthcare and the need for innovative interventions,Internet-based models can potentially offer relatively more efficient and patient-tailored care,especially in children.AIM To explore the impact of an intelligent Internet care model based on the child respiratory and asthma control test(TRACK)on asthma management in preschool children.METHODS The study group comprised preschoolers,aged 5 years or younger,that visited the hospital's pediatric outpatient and emergency departments between January 2021 and January 2022.Total of 200 children were evenly and randomly divided into the observation and control groups.The control group received standard treatment in accordance with the 2016 Guidelines for Pediatric Bronchial Asthma and the Global Initiative on Asthma.In addition to above treatment,the observation group was introduced to an intelligent internet nursing model,emphasizing the TRACK scale.Key measures monitored over a six-month period included the frequency of asthma attack,emergency visits,pulmonary function parameters(FEV1,FEV1/FVC,and PEF),monthly TRACK scores,and the SF-12 quality of life assessment.Post-intervention asthma control rates were assessed at six-month follow-up.RESULTS The observation group had fewer asthma attacks and emergency room visits than the control group(P<0.05).After six months of treatment,the children in both groups had higher FEV1,FEV1/FVC,and PEF(P<0.05).Statistically significant differences were observed between the two groups(P<0.05).For six months,children in the observation group had a higher monthly TRACK score than those in the control group(P<0.05).The PCS and MCSSF-12 quality of life scores were relatively higher than those before the nursing period(P<0.05).Furthermore,the groups showed statistically significant differences(P<0.05).The asthma control rate was higher in the observation group than in the control group(P<0.05).CONCLUSION TRACK based Intelligent Internet nursing model may reduce asthma attacks and emergency visits in asthmatic children,improve lung function,quality of life,and the TRACK score and asthma control rate.The effect of nursing was significant,allowing for development of an asthma management model.

Exploration and Practice of Postgraduate Training Mode Based on Medical Imaging Information Security

In the process of continuous maturity and development of medical imaging diagnosis,it is common to transmit images through public networks.How to ensure the security of transmission,cultivate talents who combine medical imaging and information security,and explore and cultivate new discipline growth points are difficult problems and challenges for schools and educators.In order to cope with industrial changes,a new round of scientific and technological revolution,and the challenges of the further development of artificial intelligence in medicine,this article will analyze the existing problems in the training of postgraduates in medical imaging information security by combining the actual conditions and characteristics of universities,and put forward countermeasures and suggestions to promote the progress of technology in universities.