Huperzine A as a potential therapeutic drug for diabetic nephropathy: Insights from transcriptome, metabolome, microbiome, and network pharmacology analysis.

AIMS: Diabetic nephropathy (DN) is a major complication of diabetes mellitus (DM) without curative interventions currently. Huperzine A (Hup A), a natural alkaloid, has demonstrated significant hypoglycemic and anti-inflammatory effects. We aim to investigate the protective effects of Hup A on DN and explore the underlying mechanisms METHODS: We applied STZ induced diabetic rats as DN model and leveraged combination analysis of the transcriptome, metabolome, microbiome, and network pharmacology (NP). The total effect of Hup A on DN was detected (i.e. urine protein, renal tissue structure) and the differential genes were further verified at the level of diabetic patients, db/db mice and cells. Clinical data and small interfering RNA (siRNA)-Apoe were adopted. RESULTS: Hup A alleviated kidney injury in DN rats. Transcriptomics data and Western blot indicated that the improvement in DN was primarily associated with Apoe and Apoc2. Additionally, metabolomics data demonstrated that DN-induced lipid metabolism disruption was regulated by Hup A, potentially involving sphingosine. Hup A also enriched microbial diversity and ameliorated DN-induced microbiota imbalance. Spearman's correlation analysis demonstrated significant associations among the transcriptome, metabolome, and microbiome. Apoe level was positively correlated with clinical biomarkers in DN patients. Si-Apoe also played protective role in podocytes. NP analysis also suggested that Hup A may treat DN by modulating lipid metabolism, microbial homeostasis, and apoptosis, further validating our findings. CONCLUSIONS: Collectively, we provide the first evidence of the therapeutic effect of Hup A on DN, indicating that Hup A is a potential drug for the prevention and treatment of DN.

CTH-Net: A CNN and Transformer hybrid network for skin lesion segmentation.

Automatically and accurately segmenting skin lesions can be challenging, due to factors such as low contrast and fuzzy boundaries. This paper proposes a hybrid encoder-decoder model (CTH-Net) based on convolutional neural network (CNN) and Transformer, capitalizing on the advantages of these approaches. We propose three modules for skin lesion segmentation and seamlessly connect them with carefully designed model architecture. Better segmentation performance is achieved by introducing SoftPool in the CNN branch and sandglass block in the bottleneck layer. Extensive experiments were conducted on four publicly accessible skin lesion datasets, ISIC 2016, ISIC 2017, ISIC 2018, and PH2 to confirm the efficacy and benefits of the proposed strategy. Experimental results show that the proposed CTH-Net provides better skin lesion segmentation performance in both quantitative and qualitative testing when compared with state-of-the-art approaches. We believe the CTH-Net design is inspiring and can be extended to other applications/frameworks.

Baroreflex activation therapy for heart failure with reduced ejection fraction: A comprehensive systematic review and meta-analysis.

Background: In recent years, baroreflex activation therapy (BAT) has been utilized to treat heart failure with reduced ejection fraction (HFrEF). However, the supporting literature on its efficacy and safety is still limited. This investigation elucidates the effects of BAT in HFrEF patients to provide a reference for future clinical applications. Methods: This investigation follows Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) 2020 guidelines. Relevant investigations on the use of BAT in HFrEF patients were searched and selected from 5 databases, including Web of Science, MEDLINE, PubMed, Embase, and Cochrane Library, from inception to December 2022. The methodological quality of eligible articles was assessed via the Cochrane risk of bias tool, and for meta-analysis, RevMan (5.3) was used. Results: Randomized controlled trials comprising 343 participants were selected for the meta-analysis, which revealed that in HFrEF patients, BAT enhanced the levels of LVEF (MD: 2.97, 95 % CI: 0.53 to 5.41), MLHFQ (MD: -14.81, 95 % CI: -19.57 to -10.06) and 6MWT (MD: 68.18, 95 % CI: 51.62 to 84.74), whereas reduced the levels of LVEDV (MD: -15.79, 95 % CI: -32.96 to 1.37) and DBP (MD: -2.43, 95 % CI: -4.18 to -0.68). Conclusion: It was concluded that BAT is an efficient treatment option for HFrEF patients. However, to validate this investigation, further randomized clinical trials with multiple centers and large sample sizes are needed.

Qihuang Zhuyu formula alleviates coronary microthrombosis by inhibiting PI3K/Akt/αIIbß3-mediated platelet activation.

BACKGROUND: Coronary microembolism (CME) is commonly seen in the peri-procedural period of Percutaneous Coronary Intervention (PCI), where local platelet activation and endothelial cell inflammation crosstalk may lead to micro thrombus erosion and rupture, with serious consequences. Qihuang Zhuyu Formula (QHZYF) is a Chinese herbal compound with high efficacy against coronary artery disease, but its antiplatelet mechanism is unclear. HYPOTHESIS/PURPOSE: This study aimed to elucidate the effects and mechanisms of QHZYF on sodium laurate-induced CME using network pharmacology and in vitro and in vivo experiments. METHODS: We employed high-performance liquid chromatography mass spectrometry to identify the main components of QHZYF. Network pharmacology analysis, molecular docking and surface plasmon resonance (SPR) were utilized to predict the primary active components, potential therapeutic targets, and intervention pathways mediating the effects of QHZYF on platelet activation. Next, we pretreated a sodium laurate-induced minimally invasive CME rat model with QHZYF. In vivo experiments were performed to examine cardiac function in rats, to locate coronary arteries on heart sections to observe internal microthrombi, to extract rat Platelet-rich plasma (PRP) for adhesion assays and CD62p and PAC-1 (ITGB3/ITGA2B) flow assays, and to measure platelet-associated protein expression in PRP. In vitro clot retraction and Co-culture of HUVECs with PRP were performed and the gene pathway was validated through flow cytometry and immunofluorescence. RESULTS: Combining UPLC-Q-TOF/MS technology and database mining, 78 compounds were finally screened as the putative and representative compounds of QHZYF, with 75 crossover genes associated with CME. QHZYF prevents CME mainly by regulating key pathways of the inflammation and platelets, including Lipid and atherosclerosis, Fluid shear stress, platelet activation, and PI3K-Akt signaling pathways. Five molecules including Calyson, Oroxin A, Protosappanin A,Kaempferol and Geniposide were screened and subjected to molecular docking and SPR validation in combination with Lipinski rules (Rule of 5, Ro5). In vivo experiments showed that QHZYF not only improved myocardial injury but also inhibited formation of coronary microthrombi. QHZYF inhibited platelet activation by downregulating expression of CD62p receptor and platelet membrane protein αIIbß3 and reduced the release of von Willebrand Factor (vWF), Ca2+ particles and inflammatory factor IL-6. Further analysis revealed that QHZYF inhibited the activation of integrin αIIbß3, via modulating the PI3K/Akt pathways. In in vitro experiments, QHZYF independently inhibited platelet clot retraction. Upon LPS induction, the activation of platelet membrane protein ITGB3 was inhibited via the PI3K/Akt pathway, revealing an important mechanism for attenuating coronary microthrombosis. We performed mechanistic validation using PI3K inhibitor LY294002 and Akt inhibitor MK-2206 to show that QHZYF inhibited platelet membrane protein activation and inflammation to improved coronary microvessel embolism by regulating PI3K/Akt/αIIbß3 pathways, mainly by inhibiting PI3K and Akt phosphorylation. CONCLUSION: QHZYF interferes with coronary microthrombosis through inhibition of platelet adhesion, activation and inflammatory crosstalk, thus has potential in clinical anti-platelet applications. Calyson, Oroxin A, Protosappanin A, Kaempferol and Geniposide may be the major active ingredient groups of QHZYF that alleviate coronary microthrombosis.

Guanxin V alleviates ventricular remodeling after acute myocardial infarction with circadian disruption by regulating mitochondrial dynamics.

PURPOSE: Circadian disruption has been a common issue due to modern lifestyles. Ventricular remodeling (VR) is a pivotal progressive pathologic change after acute myocardial infarction (AMI) and circadian disruption may have a negative influence on VR according to the latest research. Whether or not Guanxin V (GXV) has a positive effect on VR after AMI with circadian disruption drew our interest. METHODS: Rats were randomly divided into a sham group, an AMI group, an AMI with circadian disruption group, and an AMI with circadian disruption treated with the GXV group according to a random number table. RNA sequencing (RNA-Seq) was utilized to confirm the different expressed genes regulated by circadian disruption. Cardiac function, inflammation factors, pathological evaluation, and mitochondrial dynamics after the intervention were conducted to reveal the mechanism by which GXV regulated VR after AMI with circadian disruption. RESULTS: RNA-Seq demonstrated that NF-κB was up-regulated by circadian disruption in rats with AMI. Functional and pathological evaluation indicated that compared with the AMI group, circadian disruption was associcataed with deteriorated cardiac function, expanded infarcted size, and exacerbated fibrosis and cardiomyocyte apoptosis. Further investigation demonstrated that mitochondrial dynamics imbalance was induced by circadian disruption. GXV intervention reversed the inflammatory status including down-regulation of NF-κB. Reserved cardiac function, limited infarct size, and ameliorated fibrosis and apoptosis were also observed in the GXV treated group. GXV maintained mitochondrial fission/fusion imbalance through suppressed expression of mitochondrial fission-associated proteins. CONCLUSION: The study findings suggest that identified mitochondrial dysfunctions may underlie the link between circadian disruption and VR. GXV may exert cardioprotection after AMI with circadian disruption through regulating mitochondrial dynamics.

Integrated bioinformatics and experiment revealed that cuproptosis is the potential common pathogenesis of three kinds of primary cardiomyopathy.

Cuproptosis is a recently reported new mode of programmed cell death which might be a potential co-pathogenesis of three kinds of primary cardiomyopathy. However, no investigation has reported a clear relevance between primary cardiomyopathy and cuproptosis. In this study, the differential cuproptosis-related genes (CRGs) shared by three kinds of primary cardiomyopathy were identified in training sets. As a result, four CRGs shared by three kinds of primary cardiomyopathy were acquired and they were mainly related to biological processes such as cell death and immuno-inflammatory response through differential analysis, correlation analysis, GSEA, GSVA and immune cell infiltration analysis. Then, three key CRGs (K-CRGs) with high diagnostic value were identified by LASSO regression. The results of nomogram, machine learning, ROC analysis, calibration curve and decision curve indicated that the K-CRGs exhibited outstanding performance in the diagnosis of three kinds of primary cardiomyopathy. After that, in each disease, two molecular subtypes clusters were distinguished. There were many differences between different clusters in the biological processes associated with cell death and immunoinflammation and K-CRGs had excellent molecular subtype identification efficacy. Eventually, results from validation datasets and in vitro experiments verified the role of K-CRGs in diagnosis of primary cardiomyopathy, identification of primary cardiomyopathic molecular subtypes and pathogenesis of cuproptosis. In conclusion, this study found that cuproptosis might be the potential common pathogenesis of three kinds of primary cardiomyopathy and K-CRGs might be promising biomarkers for the diagnosis and molecular subtypes identification of primary cardiomyopathy.

Evaluation the role of cuproptosis-related genes in the pathogenesis, diagnosis and molecular subtypes identification of atherosclerosis.

Background: At present, the pathogenesis of atherosclerosis has not been fully elucidated, and the diagnosis and treatment face great challenges. Cuproptosis is a novel cell death pattern that might be involved in the development of atherosclerosis. However, no research has reported the correlation between cuproptosis and atherosclerosis. Methods: The differential cuproptosis-related genes (CRGs) between atherosclerosis group and control group (A-CRGs) were discovered via differential expression analysis. The correlation analysis, PPI network analysis, GO, KEGG and GSEA analysis were performed to investigate the function of A-CRGs. The differences of biological function between atherosclerosis group and control group were investigated via immune infiltration analysis and GSVA. The LASSO regression, nomogram and machine learning models were constructed to predict atherosclerosis risk. The atherosclerosis molecular subtypes clusters were discovered via unsupervised cluster analysis. Subsequently, we used the above research methods to analyze the differential CRGs between clusters (M-CRGs) and evaluate the molecular subtypes identification performance of M-CRGs. Finally, we verified the diagnostic value for atherosclerosis and role in cuproptosis of these CRGs through the validation set and in vitro experiments. Results: Five A-CRGs were identified and they were mainly related to the biological function of copper ion metabolism and immune inflammatory response. The diagnostic models and nomogram of atherosclerosis based on 5 A-CRGs indicated that these genes had well diagnostic value. A total of two molecular subtypes clusters were obtained in the atherosclerosis group. There were many differences in biological functions between these two molecular subtypes clusters, such as mitochondrial outer membrane permeabilization and primary immunodeficiency. In addition, 3 M-CRGs were identified in the 2 clusters. Machine learning models and nomogram constructed based on M-CRGs showed that these genes had well molecular subtypes identification efficacy. In the end, the results of in vitro experiment and validation set confirmed the diagnostic value for atherosclerosis and role in cuproptosis of these genes. Conclusion: The cuproptosis may be a potential pathogenesis of atherosclerosis and CRGs may be promising markers for the diagnosis and molecular subtypes identification of atherosclerosis.

HI-MViT: A lightweight model for explainable skin disease classification based on modified MobileViT.

Objective: To develop an explainable lightweight skin disease high-precision classification model that can be deployed to the mobile terminal. Methods: In this study, we present HI-MViT, a lightweight network for explainable skin disease classification based on Modified MobileViT. HI-MViT is mainly composed of ordinary convolution, Improved-MV2, MobileViT block, global pooling, and fully connected layers. Improved-MV2 uses the combination of shortcut and depth classifiable convolution to substantially decrease the amount of computation while ensuring the efficient implementation of information interaction and memory. The MobileViT block can efficiently encode local and global information. In addition, semantic feature dimensionality reduction visualization and class activation mapping visualization methods are used for HI-MViT to further understand the attention area of the model when learning skin lesion images. Results: The International Skin Imaging Collaboration has assembled and made available the ISIC series dataset. Experiments using the HI-MViT model on the ISIC-2018 dataset achieved scores of 0.931, 0.932, 0.961, and 0.977 on F1-Score, Accuracy, Average Precision (AP), and area under the curve (AUC). Compared with the top five algorithms of ISIC-2018 Task 3, Marco's average F1-Score, AP, and AUC have increased by 6.9%, 6.8%, and 0.8% compared with the suboptimal performance model. Compared with ConvNeXt, the most competitive convolutional neural network architecture, our model is 5.0%, 3.4%, 2.3%, and 2.2% higher in F1-Score, Accuracy, AP, and AUC, respectively. The experiments on the ISIC-2017 dataset also achieved excellent results, and all indicators were better than the top five algorithms of ISIC-2017 Task 3. Using the trained model to test on the PH2 dataset, an excellent performance score is obtained, which shows that it has good generalization performance. Conclusions: The skin disease classification model HI-MViT proposed in this article shows excellent classification performance and generalization performance in experiments. It demonstrates how the classification outcomes can be applied to dermatologists' computer-assisted diagnostics, enabling medical professionals to classify various dermoscopic images more rapidly and reliably.

Embolization of unruptured wide-necked aneurysms at the MCA bifurcation using the Neuroform atlas stent-assisted coiling: a two-center retrospective study.

Background: The management of middle cerebral artery (MCA) aneurysms remains a controversial topic, and MCA aneurysms have traditionally been treated primarily by surgical clipping. The Neuroform Atlas Stent™ (NAS, available from Stryker Neurovascular, Fremont, California) represents the latest generation of intracranial stents with improved stent delivery system capabilities. Objective: This study aims to investigate the safety, feasibility and efficacy exhibited by NAS in treating unruptured aneurysms at the MCA bifurcation. Methods: This was a two-center retrospective study involving 42 patients with unruptured wide-necked aneurysms (WNAs) of the MCA treated with the NAS from October 2020 to July 2022. Results: The stent was used to treat 42 cases of unruptured WNA at the MCA bifurcation. Endovascular treatment techniques had a 100% success rate. Immediate postoperative angiography found complete aneurysm occlusion in 34 patients (80.9%) (mRRC 1), neck remnant in 7 patients (16.7%) (mRRC 2), and residual aneurysm in 1 patient (2.4%) (mRRC 3). The thromboembolic complication rate was 2.4% (1/42). The follow-up period was 8.7 months on average (3-16 months). The last angiographic follow-up results revealed complete aneurysm occlusion in 39 patients (92.9%) (mRRC 1), neck remnant in 3 (7.1%) patients (mRRC 2), no aneurysm recanalization or recurrence, and no cases of stent intimal hyperplasia. During the latest clinical follow-up, all patients had an mRS score of 0. Conclusion: Our study demonstrates that the NAS can be applied to treat unruptured WNAs at the MCA bifurcation with favorable safety, feasibility, and efficacy.

Investigation of the shared molecular mechanisms and hub genes between myocardial infarction and depression.

Background: The pathogenesis of myocardial infarction complicating depression is still not fully understood. Bioinformatics is an effective method to study the shared pathogenesis of multiple diseases and has important application value in myocardial infarction complicating depression. Methods: The differentially expressed genes (DEGs) between control group and myocardial infarction group (M-DEGs), control group and depression group (D-DEGs) were identified in the training set. M-DEGs and D-DEGs were intersected to obtain DEGs shared by the two diseases (S-DEGs). The GO, KEGG, GSEA and correlation analysis were conducted to analyze the function of DEGs. The biological function differences of myocardial infarction and depression were analyzed by GSVA and immune cell infiltration analysis. Four machine learning methods, nomogram, ROC analysis, calibration curve and decision curve were conducted to identify hub S-DEGs and predict depression risk. The unsupervised cluster analysis was constructed to identify myocardial infarction molecular subtype clusters based on hub S-DEGs. Finally, the value of these genes was verified in the validation set, and blood samples were collected for RT-qPCR experiments to further verify the changes in expression levels of these genes in myocardial infarction and depression. Results: A total of 803 M-DEGs, 214 D-DEGs, 13 S-DEGs and 6 hub S-DEGs (CD24, CSTA, EXTL3, RPS7, SLC25A5 and ZMAT3) were obtained in the training set and they were all involved in immune inflammatory response. The GSVA and immune cell infiltration analysis results also suggested that immune inflammation may be the shared pathogenesis of myocardial infarction and depression. The diagnostic models based on 6 hub S-DEGs found that these genes showed satisfactory combined diagnostic performance for depression. Then, two molecular subtypes clusters of myocardial infarction were identified, many differences in immune inflammation related-biological functions were found between them, and the hub S-DEGs had satisfactory molecular subtypes identification performance. Finally, the analysis results of the validation set further confirmed the value of these hub genes, and the RT-qPCR results of blood samples further confirmed the expression levels of these hub genes in myocardial infarction and depression. Conclusion: Immune inflammation may be the shared pathogenesis of myocardial infarction and depression. Meanwhile, hub S-DEGs may be potential biomarkers for the diagnosis and molecular subtype identification of myocardial infarction and depression.

Dioscin ameliorates doxorubicin-induced heart failure via inhibiting autophagy and apoptosis by controlling the PDK1-mediated Akt/mTOR signaling pathway.

Heart failure (HF) is a disease with high mortality and morbidity rate. Autophagy is critically implicated in HF progression. The current research was designed to investigate the function of Dioscin on oxidative stress, autophagy, and apoptosis in HF. In this study, doxorubicin (Dox) was employed to induce HF model and HL-1 cell damage model. Echocardiography implied that Dioscin could dramatically relieve heart function in vivo. Western blotting determined that Dioscin treatment reversed the promotive effect of autophagy caused by Dox through modulating levels of key autophagy-associated molecules, including Atg5 and Beclin1. Dioscin also impaired apoptosis by regulating apoptosis-related protein, including Bcl-2 and cleaved caspase-3 following Dox treatment in vivo and in vitro. Furthermore, the impacts of Dioscin were mediated by upregulation of PDK1-mediated Akt/mTOR signaling. The mTOR inhibitor (rapamycin) could counteract the therapeutic impact of Dioscin in vitro. Taken together, Dioscin could relieve cardiac function through blocking apoptosis and autophagy by activating the PDK1-elicited Akt/mTOR pathway.

Adaptive evolution of the enigmatic Takakia now facing climate change in Tibet.

The most extreme environments are the most vulnerable to transformation under a rapidly changing climate. These ecosystems harbor some of the most specialized species, which will likely suffer the highest extinction rates. We document the steepest temperature increase (2010-2021) on record at altitudes of above 4,000 m, triggering a decline of the relictual and highly adapted moss Takakia lepidozioides. Its de-novo-sequenced genome with 27,467 protein-coding genes includes distinct adaptations to abiotic stresses and comprises the largest number of fast-evolving genes under positive selection. The uplift of the study site in the last 65 million years has resulted in life-threatening UV-B radiation and drastically reduced temperatures, and we detected several of the molecular adaptations of Takakia to these environmental changes. Surprisingly, specific morphological features likely occurred earlier than 165 mya in much warmer environments. Following nearly 400 million years of evolution and resilience, this species is now facing extinction.

Qihuang Zhuyu Formula Attenuates Atherosclerosis via Targeting PPARγ to Regulate Cholesterol Efflux and Endothelial Cell Inflammation.

At present, due to the limitations of drug therapy targets for atherosclerosis, some patients fail to achieve satisfactory efficacy. Cholesterol efflux dysfunction and endothelial cell inflammation are considered to be important factors in the development of atherosclerosis. Peroxisome proliferator-activated receptor gamma (PPARγ), a promising therapeutic target for atherosclerosis, plays a dual role in regulating cholesterol efflux and endothelial cell inflammation. However, the use of PPARγ agonist in clinical practice is greatly limited as it could lead to water and sodium retention and hence result in congestive heart failure. Qihuang Zhuyu Formula (QHZYF) is a hospital preparation of Jiangsu Province Hospital of Chinese Medicine which has definite effect in the treatment of atherosclerosis, but its pharmacological mechanism has not been clear. In this study, we successfully predicted that QHZYF might regulate cholesterol efflux and endothelial inflammation via targeting PPARγ-mediated PPARγ/LXRα/ABCA1-ABCG1 and PPARγ/NF-κB p65 pathways by using UPLC-Q-TOF/MS, network pharmacology, bioinformatics analysis, and molecular docking technology. Subsequently, we confirmed in vivo that QHZYF could attenuate atherosclerosis in ApoE-/- mice and regulate the expression levels of related molecules in PPARγ/LXRα/ABCA1-ABCG1 and PPARγ/NF-κB p65 pathways of ApoE-/- mice and C57BL/6 wild-type mice. Finally, in in vitro experiments, we found that QHZYF could reduce lipid content and increase cholesterol efflux rate of RAW 264.7 cells, inhibit the inflammatory response of HUVECs, and regulate the expression levels of related molecules in the two pathways. In addition, the above effects of QHZYF were significantly weakened after PPARγ knockdown in the two kinds of cells. In conclusion, our study revealed that QHZYF attenuates atherosclerosis via targeting PPARγ-mediated PPARγ/LXRα/ABCA1-ABCG1 and PPARγ/NF-κB p65 pathways to regulate cholesterol efflux and endothelial cell inflammation. More importantly, our study offers a promising complementary and alternative therapy which is expected to make up for the limitation of current drug treatment methods and provide a valuable reference for new drugs development in the future.

Insights into glycosidic bond specificity of an engineered selective α-L-rhamnosidase N12-Rha via activity assays and molecular modelling.

αL-rhamnosidase (EC 3.2.1.40) has been widely used in food processing and pharmaceutical preparation. The recombinant α-L-rhamnosidase N12-Rha from Aspergillus niger JMU-TS528 had significantly higher catalytic activity on α-1,6 glycosidic bond than α-1,2 glycosidic bond, and had no activity on α-1,3 glycosidic bond. The activities of hydrolyzed hesperidin and naringin were 7240 U/mL and 945 U/mL, respectively, which are 10.63 times that of native α-L-rhamnosidase. The activity could maintain more than 80% at pH 3-6 and 40-60℃. Quantum chemistry calculations showed that charge difference of the C-O atoms of the α-1,2, α-1,3 and α-1,6 bonds indicated that α-1,6 bond is most easily broken and α-1,3 bond is the most stable. Molecular dynamics simulations revealed that the key residue Trp359 that may affect substrate specificity and the main catalytic sites of N12-Rha are located in the (α/α)6-barrel domain.

DE-MRI myocardial fibrosis segmentation and classification model based on multi-scale self-supervision and transformer.

OBJECTIVE: The segmentation and categorization of fibrotic tissue in time-lapse enhanced MRI scanning are quite challenging, and it is mainly done manually for myocardial DE-MRI images. On the other hand, DE-MRI instructions for segmenting and classifying cardiac hypertrophy are complex and prone to inaccuracy. Developing cardiac DE-MRI classification and prediction methods is crucial. METHODS: This paper introduces a self-supervised myocardial histology segmentation algorithm with multi-scale portrayal consistency to address the degree of sophistication of cardiology DE-MRI. The model retrieves multi-scale representations from multiple expanded viewpoints using a Siamese system and uses resemblance learning instruction to achieve unlabeled representations. The DE-MRI data train the network weights to generate a superior segmentation effect by accurately reflecting the exact scale information. The paper provides an end-to-end method for detecting myocardial fibrosis tissue using a Transformer as a result of the poor classification outcomes of myocardial fibrosis substance in DE-MRI. A deep learning model is created using the Pre-LN Transformer decoded simultaneously with the Multi-Scale Transformer backbone structure developed in this paper. In addition, the joint regression cost, which incorporates the CIoU Loss and the L1 Loss, is used to determine the distance between forecast blocks and labels. RESULTS: Increasing the independent evaluation and annotations position compared enhances performance compared to the segmentation method without canvas matching by 1.76%, 1.27%, 0.93%, and -1.17 mm on Dice, PPV, SEN, and HD, respectively. Based on the strongest of the three single-scale representation methodologies, the segmentation model in this study is enhanced by 0.71%, 0.79%, and 1.47%, as well as -1.49 mm on Dice, PPV, SEN, and HD, respectively. The effectiveness and reliability of the segmentation model are confirmed. Additionally, testing results show that this study's recognition system's mAP is 84.97%, which is greater than the benchmark techniques used in most other studies. The framework converges round is compressed by 18.1% compared to the DETR detection approach, and the identification rate is improved by 3.5%, proving the strategy's value. CONCLUSION: The self-supervised cardiac fibrosis segmentation method with multi-scale portrayal consistency and end-to-end myocardial histology categorization is introduced in this study. To solve the challenges of segmentation and myocardial fibrosis identification in cardiology DE-MRI, a Transformer-based detection approach is put forth. It may address the issue of the myocardial scarring material's low accuracy in segmentation and classification in DE-MRI, as well as provide clinicians with a fibrosis diagnosis that is supplementary to the conventional therapy of heart ailments.

Brain metastasis from colorectal cancer: Treatment, survival, and prognosis.

To investigate the clinical characteristics, survival, prognostic factors, and treatment of brain metastasis (BM) from colorectal cancer (CRC). Twenty-one patients with BM from CRC were retrospectively reviewed. Predictive factors for BM and prognostic factors after the diagnosis of BM were examined by univariate and multivariate COX analysis. The time from the development of extracranial metastases, including lung, bone, and liver, to the occurrence of BM was recorded separately. The median overall survival time was 7 months. In univariate prognostic analysis, median survival with multimodal therapy was better than that with unimodal therapy (10 months vs 3 months, P = .000). In addition, median survival with Karnofsky performance status (KPS) < 70, 1 BM lesion, primary tumor stage of II-III, extracranial lesions < 2, and no extracranial metastasis were much better than the other groups (P < .05 of all). Although there was not a significant difference in median survival between patients receiving combination treatment with bevacizumab and those who did not, treatment with bevacizumab was associated with better survival (10 months vs 5 months, P = .436). The time intervals from bone, liver, and lung metastases to BM were 3, 6.5, and 11 months, respectively. Based on multivariate Cox analysis, KPS and treatment modalities were independent prognosis factors (P = .039 and P = .000, respectively). CRC patients with a high KPS and multimodal treatment have improved survival.

Unsupervised domain adaptive myocardial infarction MRI classification diagnostics model based on target domain confused sample resampling.

OBJECTIVE: Inefficient circulatory system due to blockage of blood vessels leads to myocardial infarction and acute blockage. Myocardial infarction is frequently classified and diagnosed in medical treatment using MRI, yet this method is ineffective and prone to error. As a result, there are several implementation scenarios and clinical significance for employing deep learning to develop computer-aided algorithms to aid cardiologists in the routine examination of cardiac MRI. METHODS: This research uses two distinct domain classifiers to address this issue and achieve domain adaptation between the particular field and the specific part is a problem Current research on environment adaptive systems cannot effectively obtain and apply classification information for unsupervised scenes of target domain images. Insufficient information interchange between specific domains and specific domains is a problem. In this study, two different domain classifiers are used to solve this problem and achieve domain adaption. To effectively mine the source domain images for classification understanding, an unsupervised MRI classification technique for myocardial infarction called CardiacCN is proposed, which relies on adversarial instructions related to the interpolation of confusion specimens in the target domain for the conflict of confusion specimens for the target domain classification task. RESULTS: The experimental results demonstrate that the CardiacCN model in this study performs better on the six domain adaption tasks of the Sunnybrook Cardiac Dataset (SCD) dataset and increases the mean target area myocardial infarction MRI classification accuracy by approximately 1.2 percent. The classification performance of the CardiacCN model on the target domain does not vary noticeably when the temperature-controlled duration hyper-parameter rl falls in the region of 5-30. According to the experimental findings, the CardiacCN model is more resistant to the excitable rl. The CardiacCN model suggested in this research may successfully increase the accuracy of the source domain predictor for the target domain myocardial infarction clinical scanning classification in unsupervised learning, as shown by the visualization analysis infrastructure provision nurture. It is evident from the visualization assessment of embedded features that the CardiacCN model may significantly increase the source domain classifier's accuracy for the target domain's classification of myocardial infarction in clinical scans under unsupervised conditions. CONCLUSION: To address misleading specimens with the inconsistent classification of target-domain myocardial infarction medical scans, this paper introduces the CardiacCN unsupervised domain adaptive MRI classification model, which relies on adversarial learning associated with resampling target-domain confusion samples. With this technique, implicit image classification information from the target domain is fully utilized, knowledge transfer from the target domain to the specific domain is encouraged, and the classification effect of the myocardial ischemia medical scan is improved in the target domain of the unsupervised scene.

Classification of myocardial fibrosis in DE-MRI based on semi-supervised semantic segmentation and dual attention mechanism.

OBJECTIVE: It is essential to utilize cardiac delayed-enhanced magnetic resonance imaging (DE-MRI) to diagnose cardiovascular disease. By segmenting myocardium DE-MRI images, it provides critical information for the evaluation and treatment of myocardial infarction. As a consequence, it is vital to investigate the segmentation and classification technique of myocardial DE-MRI. METHODS: Firstly, an end-to-end minimally supervised and semi-supervised semantic DE-MRI myocardial fibrosis segmentation framework is proposed, which combines image classification and semantic segmentation branches based on the self-attention mechanism. Following that, a residual hole network fused with the dual attention mechanism was built, and a double attention metabolic pathway classification method for cardiac fibrosis in DE-MRI images was developed. RESULTS: By adding pixel-level labels to an extra 40 training images, the segmentation model may enhance semantic segmentation performance by 2.6 percent (from 61.2 percent to 63.8 percent). When the number of pixel-level labels is increased to 80, semi-supervised feature extraction increases by 4.7 percent when compared to weakly guided semantic segmentation. Adding an attention mechanism to the critical network DRN (Deep Residual Network) can increase the classifier's performance by a small amount. Experiments revealed that the models worked effectively. CONCLUSION: This paper investigates the segmentation and classification of cardiac fibrosis in DE-MRI data using a semi-supervised semantic segmentation and dual attention mechanism, dealing with the issue that existing segmentation algorithms have difficulty segmenting myocardial fibrosis tissue. In the future, we can consider optimizing the design of the attention module to reduce the module computation.

Which patients are prone to suffer liver metastasis? A review of risk factors of metachronous liver metastasis of colorectal cancer.

BACKGROUND: In recent years, with the increasing incidence of colorectal cancer (CRC) and its high fatality rate, CRC has seized the attention of the world. And liver metastasis, as the main cause of death of CRC, has become the leading cause of treatment failure in CRC, especially metachronous liver metastasis, have caused patients who underwent bowel resection to experience multiple tortures. MAIN BODY: Metachronous liver metastasis has severely affected the quality of life and prognosis of patients. Therefore, in this review, we discuss risk factors for metachronous liver metastasis of CRC, which is the premise for effective intervention for CRC patients who suffer metachronous liver metastasis after undergoing surgery, as well as the signaling pathways associated with CRC. CONCLUSION: The occurrence of metachronous liver metastasis is closely related to histology-based prognostic biomarkers, serum-based biomarkers, tumor microenvironment, pre-metastatic niche, liquid biopsy and tissue-based biomarkers. Further research is required to explore the risk factors associated with liver metastasis of CRC.

Classification of Tea Quality Levels Using Near-Infrared Spectroscopy Based on CLPSO-SVM.

In this paper, we propose a method for classifying tea quality levels based on near-infrared spectroscopy. Firstly, the absorbance spectra of Huangshan Maofeng tea samples were obtained in a wavenumber range of 10,000~4000 cm-1 using near-infrared spectroscopy. The spectral data were then converted to transmittance and smoothed using the Savitzky-Golay (SG) algorithm. The denoised transmittance spectra were dimensionally reduced using principal component analysis (PCA). The characteristic variables obtained using PCA were used as the input variables and the tea level was used as the output to establish a support vector machine (SVM) classification model. The penalty factor c and the kernel function parameter g in the SVM model were optimized using particle swarm optimization (PSO) and comprehensive-learning particle swarm optimization (CLPSO) algorithms. The final experimental results show that the CLPSO-SVM method had the best classification performance, and the classification accuracy reached 99.17%.