Semi-Supervised Graph Structure Learning via Dual Reinforcement of Label and Prior Structure.

Graph neural networks (GNNs) have achieved considerable success in dealing with graph-structured data by the message-passing mechanism. Actually, this mechanism relies on a fundamental assumption that the graph structure along which information propagates is perfect. However, the real-world graphs are inevitably incomplete or noisy, which violates the assumption, thus resulting in limited performance. Therefore, optimizing graph structure for GNNs is indispensable and important. Although current semi-supervised graph structure learning (GSL) methods have achieved a promising performance, the potential of labels and prior graph structure has not been fully exploited yet. Inspired by this, we examine GSL with dual reinforcement of label and prior structure in this article. Specifically, to enhance label utilization, we first propose to construct the prior label-constrained matrices to refine the graph structure by identifying label consistency. Second, to adequately leverage the prior structure to guide GSL, we develop spectral contrastive learning that extracts global properties embedded in the prior graph structure. Moreover, contrastive fusion with prior spatial structure is further adopted, which promotes the learned structure to integrate local spatial information from the prior graph. To extensively evaluate our proposal, we perform sufficient experiments on seven benchmark datasets, where experimental results confirm the effectiveness of our method and the rationality of the learned structure from various aspects.

Intersection-union dual-stream cross-attention Lova-SwinUnet for skin cancer hair segmentation and image repair.

Skin cancer images have hair occlusion problems, which greatly affects the accuracy of diagnosis and classification. Current dermoscopic hair removal methods use segmentation networks to locate hairs, and then uses repair networks to perform image repair. However, it is difficult to segment hair and capture the overall structure between hairs because of the hair being thin, unclear, and similar in color to the entire image. When conducting image restoration tasks, the only available images are those obstructed by hair, and there is no corresponding ground truth (supervised data) of the same scene without hair obstruction. In addition, the texture information and structural information used in existing repair methods are often insufficient, which leads to poor results in skin cancer image repair. To address these challenges, we propose the intersection-union dual-stream cross-attention Lova-SwinUnet (IUDC-LS). Firstly, we propose the Lova-SwinUnet module, which embeds Lovasz loss function into Swin-Unet, enabling the network to better capture features of various scales, thus obtaining better hair mask segmentation results. Secondly, we design the intersection-union (IU) module, which takes the mask results obtained in the previous step for pairwise intersection or union, and then overlays the results on the skin cancer image without hair to generate the labeled training data. This turns the unsupervised image repair task into the supervised one. Finally, we propose the dual-stream cross-attention (DC) module, which makes texture information and structure information interact with each other, and then uses cross-attention to make the network pay attention to the more important texture information and structure information in the fusion process of texture information and structure information, so as to improve the effect of image repair. The experimental results show that the PSNR index and SSIM index of the proposed method are increased by 5.4875 and 0.0401 compared with the other common methods. Experimental results unequivocally demonstrate the effectiveness of our approach, which serves as a potent tool for skin cancer detection, significantly surpassing the performance of comparable methods.

Ku70 Binding to YAP Alters PARP1 Ubiquitination to Regulate Genome Stability and Tumorigenesis.

YAP is a central player in cancer development with functions extending beyond its recognized role in cell growth regulation. Recent work has identified a link between YAP/TAZ and the DNA damage response. Here, we investigated the mechanistic underpinnings of the crosstalk between DNA damage repair and YAP activity. Ku70, a key component of the non-homologous end joining pathway to repair DNA damage, engaged in a dynamic competition with TEAD4 for binding to YAP, limiting the transcriptional activity of YAP. Depletion of Ku70 enhanced interaction between YAP and TEAD4 and boosted YAP transcriptional capacity. Consequently, Ku70 loss enhanced tumorigenesis in colon cancer and hepatocellular carcinoma (HCC) in vivo. YAP impeded DNA damage repair and elevated genome instability by inducing PARP1 degradation through the SMURF2-mediated ubiquitin-proteasome pathway. Analysis of HCC patient samples substantiated the link between Ku70 expression, YAP activity, PARP1 levels, and genome instability. In conclusion, this research provides insight into the mechanistic interactions between YAP and key regulators of DNA damage repair, highlighting the role of a Ku70-YAP-PARP1 axis in preserving genome stability.

Study on the Application of Kramers-Kronig Relation for Polyurethane Mixture.

Polyurethane (PU) mixture, which is a new pavement mixture, exhibits different dynamic properties compared to a hot-mixed asphalt mixture (HMA). This paper analyzed whether the Kramers-Kronig (K-K) relation and thermorheologically simple properties applied to the PU mixture. Based on the results, the PU mixture exhibited thermorheologically simple properties within the test conditions. The time-temperature superposition principle (TTSP) was applicable for the PU mixture to construct a dynamic modulus master curve using the standard logistic sigmoidal (SLS) model, the generalized logistic sigmoidal (GLS) model, and the Havriliak-Negami (HN) model. The Hilbert integral transformed SLS and GLS models for the phase angle can accurately fit the measured phase angle data with newly fitted shift factors and predict the phase angle within the viscoelastic range. The core-core and black space diagrams both displayed single continuous smooth curves, which can be utilized to characterize the viscoelastic property of the PU mixture. The K-K relation is applicable for the PU mixture to obtain the phase angle master curve model, storage modulus, and loss modulus from the complex modulus test results with the test temperatures and loading frequencies. The phase angle of the PU mixture at extremely high or low test temperatures cannot be derived from the dynamic modulus data.

Leveraging Senescent Cancer Cell Membrane to Potentiate Cancer Immunotherapy Through Biomimetic Nanovaccine.

Senescent cancer cells are endowed with high immunogenic potential that has been leveraged to elicit antitumor immunity and potentially complement anticancer therapies. However, the efficacy of live senescent cancer cell-based vaccination is limited by interference from immunosuppressive senescence-associated secretory phenotype and pro-tumorigenic capacity of senescent cells. Here, a senescent cancer cell-based nanovaccine with strong immunogenicity and favorable potential for immunotherapy is reported. The biomimetic nanovaccine integrating a senescent cancer cell membrane-coated nanoadjuvant outperforms living senescent cancer cells in enhancing dendritic cells (DCs) internalization, improving lymph node targeting, and enhancing immune responses. In contrast to nanovaccines generated from immunogenic cell death-induced tumor cells, senescent nanovaccines facilitate DC maturation, eliciting superior antitumor protection and improving therapeutic outcomes in melanoma-challenged mice with fewer side effects when combined with αPD-1. The study suggests a versatile biomanufacturing approach to maximize immunogenic potential and minimize adverse effects of senescent cancer cell-based vaccination and advances the design of biomimetic nanovaccines for cancer immunotherapy.

Parallel Dual-Branch Fusion Network for Epileptic Seizure Prediction.

Epilepsy is a prevalent chronic disorder of the central nervous system. The timely and accurate seizure prediction using the scalp Electroencephalography (EEG) signal can make patients adopt reasonable preventive measures before seizures occur and thus reduce harm to patients. In recent years, deep learning-based methods have made significant progress in solving the problem of epileptic seizure prediction. However, most current methods mainly focus on modeling short- or long-term dependence in EEG, while neglecting to consider both. In this study, we propose a Parallel Dual-Branch Fusion Network (PDBFusNet) which aims to combine the complementary advantages of Convolutional Neural Network (CNN) and Transformer. Specifically, the features of the EEG signal are first extracted using Mel Frequency Cepstral Coefficients (MFCC). Then, the extracted features are delivered into the parallel dual-branches to simultaneously capture the short- and long-term dependencies of EEG signal. Further, regarding the Transformer branch, a novel feature fusion module is developed to enhance the ability of utilizing time, frequency, and channel information. To evaluate our proposal, we perform sufficient experiments on the public epileptic EEG dataset CHB-MIT, where the accuracy, sensitivity, specificity and precision are 95.76%, 95.81%, 95.71% and 95.71%, respectively. PDBFusNet shows superior performance compared to state-of-the-art competitors, which confirms the effectiveness of our proposal.

Imaging and blood flow characteristics of cerebrovascular fenestration malformation and its relationship with the occurrence of ischemic cerebrovascular disease.

OBJECTIVE: To explore the imaging and transcranial Doppler cerebral blood flow characteristics of cerebrovascular fenestration malformation and its relationship with the occurrence of ischemic cerebrovascular disease. METHODS: A retrospective analysis was conducted on the imaging data of 194 patients with cerebrovascular fenestration malformation who visited the Heyuan People's Hospital from July 2021 to July 2023. The location and morphology of the fenestration malformation blood vessels as well as the presence of other cerebrovascular diseases were analyzed. Transcranial Doppler cerebral blood flow detection data of patients with cerebral infarction and those with basilar artery fenestration malformation were also analyzed. RESULTS: A total of 194 patients with cerebral vascular fenestration malformation were found. Among the artery fenestration malformation, basilar artery fenestration was the most common, accounting for 46.08% (94/194). 61 patients (31.44%) had other vascular malformations, 97 patients (50%) had cerebral infarction, of which 30 were cerebral infarction in the fenestrated artery supply area. 28 patients with cerebral infarction in the fenestrated artery supply area received standardized antiplatelet, lipid-lowering and plaque-stabilizing medication treatment. During the follow-up period, these patients did not experience any symptoms of cerebral infarction or transient ischemic attack again. There were no differences in peak systolic flow velocity and end diastolic flow velocity, pulsatility index and resistance index between the ischemic stroke group and the no ischemic stroke group in patients with basal artery fenestration malformation (P > 0.05). CONCLUSION: Cerebrovascular fenestration malformation is most common in the basilar artery. Cerebrovascular fenestration malformation may also be associated with other cerebrovascular malformations. Standardized antiplatelet and statin lipid-lowering and plaque-stabilizing drugs are suitable for patients with cerebral infarction complicated with fenestration malformation. The relationship between cerebral blood flow changes in basilar artery fenestration malformation and the occurrence of ischemic stroke may not be significant.

Size control of ropivacaine nano/micro-particles by soft-coating with peptide nanosheets for long-acting analgesia.

Rationale: To meet the need of long-acting analgesia in postoperative pain management, slow-releasing formulations of local anesthetics (LAs) have been extensively investigated. However, challenges still remain in obtaining such formulations in a facile and cost-effective way, and a mechanism for controlling the release rate to achieve an optimal duration is still missing. Methods: In this study, nanosheets formed by a self-assembling peptide were used to encapsulate ropivacaine in a soft-coating manner. By adjusting the ratio between the peptide and ropivacaine, ropivacaine particles with different size were prepared. Releasing profile of particles with different size were studied in vitro and in vivo. The influence of particle size and ropivacaine concentration on effective duration and toxicity were evaluated in rat models. Results: Our results showed that drug release rate became slower as the particle size increased, with particles of medium size (2.96 ± 0.04 µm) exhibiting a moderate release rate and generating an optimal anesthetic duration. Based on this size, formulations at different ropivacaine concentrations generated anesthetic effect with different durations in rat sciatic nerve block model, with the 6% formulation generated anesthetic duration of over 35 h. Long-acting analgesia up to 48 h of this formulation was also confirmed in a rat total knee arthroplasty model. Conclusion: This study provided a facile strategy to prepare LA particles of different size and revealed the relationship between particle size, release rate and anesthetic duration, which provided both technical and theoretical supports for developing long-acting LA formulations with promising clinical application.

Identification of crosstalk genes relating to ECM-receptor interaction genes in MASH and DN using bioinformatics and machine learning.

This study aimed to identify genes shared by metabolic dysfunction-associated fatty liver disease (MASH) and diabetic nephropathy (DN) and the effect of extracellular matrix (ECM) receptor interaction genes on them. Datasets with MASH and DN were downloaded from the Gene Expression Omnibus (GEO) database. Pearson's coefficients assessed the correlation between ECM-receptor interaction genes and cross talk genes. The coexpression network of co-expression pairs (CP) genes was integrated with its protein-protein interaction (PPI) network, and machine learning was employed to identify essential disease-representing genes. Finally, immuno-penetration analysis was performed on the MASH and DN gene datasets using the CIBERSORT algorithm to evaluate the plausibility of these genes in diseases. We found 19 key CP genes. Fos proto-oncogene (FOS), belonging to the IL-17 signalling pathway, showed greater centrality PPI network; Hyaluronan Mediated Motility Receptor (HMMR), belonging to ECM-receptor interaction genes, showed most critical in the co-expression network map of 19 CP genes; Forkhead Box C1 (FOXC1), like FOS, showed a high ability to predict disease in XGBoost analysis. Further immune infiltration showed a clear positive correlation between FOS/FOXC1 and mast cells that secrete IL-17 during inflammation. Combining the results of previous studies, we suggest a FOS/FOXC1/HMMR regulatory axis in MASH and DN may be associated with mast cells in the acting IL-17 signalling pathway. Extracellular HMMR may regulate the IL-17 pathway represented by FOS through the Mitogen-Activated Protein Kinase 1 (ERK) or PI3K-Akt-mTOR pathway. HMMR may serve as a signalling carrier between MASH and DN and could be targeted for therapeutic development.

Painful diabetic neuropathy: The role of ion channels.

Painful diabetic neuropathy (PDN) is a common chronic complication of diabetes that causes neuropathic pain and negatively affects the quality of life. The management of PDN is far from satisfactory. At present, interventions are primarily focused on symptomatic treatment. Ion channel disorders are a major cause of PDN, and a complete understanding of their roles and mechanisms may provide better options for the clinical treatment of PDN. Therefore, this review summarizes the important role of ion channels in PDN and the current drug development targeting these ion channels.

A novel approach for intelligent diagnosis and grading of diabetic retinopathy.

Diabetic retinopathy (DR) is a severe ocular complication of diabetes that can lead to vision damage and even blindness. Currently, traditional deep convolutional neural networks (CNNs) used for DR grading tasks face two primary challenges: (1) insensitivity to minority classes due to imbalanced data distribution, and (2) neglecting the relationship between the left and right eyes by utilizing the fundus image of only one eye for training without differentiating between them. To tackle these challenges, we proposed the DRGCNN (DR Grading CNN) model. To solve the problem caused by imbalanced data distribution, our model adopts a more balanced strategy by allocating an equal number of channels to feature maps representing various DR categories. Furthermore, we introduce a CAM-EfficientNetV2-M encoder dedicated to encoding input retinal fundus images for feature vector generation. The number of parameters of our encoder is 52.88 M, which is less than RegNet_y_16gf (80.57 M) and EfficientNetB7 (63.79 M), but the corresponding kappa value is higher. Additionally, in order to take advantage of the binocular relationship, we input fundus retinal images from both eyes of the patient into the network for features fusion during the training phase. We achieved a kappa value of 86.62% on the EyePACS dataset and 86.16% on the Messidor-2 dataset. Experimental results on these representative datasets for diabetic retinopathy (DR) demonstrate the exceptional performance of our DRGCNN model, establishing it as a highly competitive intelligent classification model in the field of DR. The code is available for use at https://github.com/Fat-Hai/DRGCNN.

Disulfideptosis-associated lncRNAs reveal features of prognostic, immune escape, tumor mutation, and tumor malignant progression in renal clear cell carcinoma.

PURPOSE: Investigating the role of lncRNAs associated with the latest cell death mode (Disulfideptosis) in renal clear cell carcinoma, as well as their correlation with tumor prognosis, immune escape, immune checkpoints, tumor mutational burden, and malignant tumor progression. Searching for potential biomarkers and targets for renal clear cell carcinoma. METHODS: Downloaded the expression profile data and clinical data of 533 cases of renal clear cell carcinoma from the TCGA database, and randomly divided them into a test set (267 cases) and a validation set (266 cases). Based on previous research, 13 genes associated with Disulfideptosis were obtained. Using R software, lncRNAs with a differential expression that is related to the prognosis of renal clear cell carcinoma and associated with Disulfideptosis were screened out. After univariate Cox regression analysis, Lasso regression analysis, and multivariate Cox regression analysis, lncRNAs with independent predictive ability were obtained. A predictive risk model was established based on the risk scores. Verification was carried out between the obtained high-risk and low-risk groups and their subgroups (including Age, Gender, tumor mutational burden (TMB), tumor grading, and staging). Subsequently, a nomogram was established, and a calibration curve was generated for verification. Performed GO (Gene Ontology) and KEGG (Kyoto Encyclopedia of Genes and Genomes) functional enrichment analyses. Downloaded the values of Tumor Immune Dysfunction and Exclusion (TIDE) for all samples and calculated the difference between the high and low-risk groups. Selected human renal tumor cell lines (786-O, OS-RC-2, A-498, ACHN) and human renal cortex proximal tubule epithelial cell line (HK-2). The RNA expression levels of the above lncRNAs in each cell line were analyzed using RT-qPCR (Real-time Quantitative PCR Detecting System). Used siRNA (small interfering RNA) to knock down FAM225B in 786-O and OS-RC-2 cell lines, and then performed in vitro cell experiments to validate the functional characteristics of FAM225B. RESULTS: Our constructed predictive model includes 5 lncRNAs with an independent predictive ability (FAM225B, ZNF503-AS1, SPINT1-AS1, WWC2-AS2, LINC01338), which can effectively distinguish between patients in high and low-risk groups and their subgroups. The 1, 3, and 5-year AUC (Area Under the ROC Curve) values of the established nomogram are 0.756, 0.752, and 0.781, respectively. The 5-year AUC value is higher compared to other clinical characteristics (Age: 0.598, Gender: 0.488, Grade: 0.680, Stage: 0.717). After the knockdown of FAM225B, the proliferation, migration, and invasion abilities of renal cancer cell lines OS-RC-2 and 786-O all decreased. CONCLUSION: We have constructed and validated a prognostic model based on Disulfideptosis-associated lncRNAs. This model can effectively predict the high or low risk of patient prognosis and can distinguish the tumor cell mutational burden and immune escape capabilities among high-risk and low-risk patients. This predictive model can serve as an independent prognostic factor for renal clear cell carcinoma, providing a new direction for personalized treatment of patients with renal clear cell carcinoma.

Deep Survival Analysis With Latent Clustering and Contrastive Learning.

Survival analysis is employed to analyze the time before the event of interest occurs, which is broadly applied in many fields. The existence of censored data with incomplete supervision information about survival outcomes is one key challenge in survival analysis tasks. Although some progress has been made on this issue recently, the present methods generally treat the instances as separate ones while ignoring their potential correlations, thus rendering unsatisfactory performance. In this study, we propose a novel Deep Survival Analysis model with latent Clustering and Contrastive learning (DSACC). Specifically, we jointly optimize representation learning, latent clustering and survival prediction in a unified framework. In this way, the clusters distribution structure in latent representation space is revealed, and meanwhile the structure of the clusters is well incorporated to improve the ability of survival prediction. Besides, by virtue of the learned clusters, we further propose a contrastive loss function, where the uncensored data in each cluster are set as anchors, and the censored data are treated as positive/negative sample pairs according to whether they belong to the same cluster or not. This design enables the censored data to make full use of the supervision information of the uncensored samples. Through extensive experiments on four popular clinical datasets, we demonstrate that our proposed DSACC achieves advanced performance in terms of both C-index (0.6722, 0.6793, 0.6350, and 0.7943) and Integrated Brier Score (IBS) (0.1616, 0.1826, 0.2028, and 0.1120).

Topical Tacrolimus and Mycophenolic Acid Therapy Synergizes with Low Dose Systemic Immunosuppression to Sustain Vascularized Composite Allograft Survival.

AIM: The goal of this study was to evaluate whether topical administration of tacrolimus (TAC) and mycophenolic acid (MPA) at the transplant site enables vascularized composite allograft (VCA) survival with significant minimization of the dose and adverse effects of systemic TAC (STAC) immunosuppression. MATERIALS AND METHODS: Lewis (Lew) rats received orthotopic hind limb allotransplants from fully mismatched Brown Norway (BN) donors. Group 1 (Controls) received no treatment. Other groups were treated with STAC at a dose of 1 mg/kg/day for 7 days. On post-operative day (POD) 8, the STAC dose was dropped to 0.1 mg/kg/day for Group 2 and maintained at 1 mg/kg for Group 3. Group 4 received topical application of TAC and MPA on the transplanted (Tx) limb starting POD 8 without STAC. Group 5 received topical TAC and MPA on the contralateral non-Tx limb and Group 6 received topical TAC and MPA on the Tx limb starting POD 8 along with low dose STAC (0.1 mg/kg/day). Treatment was continued until the study end point was reached, defined as either grade 3 rejection or allograft survival exceeding 100 days. .We conducted sequential LC-MS/MS measurements to assess TAC and MPA concentrations in both blood/plasma and allograft tissues. Additionally, we evaluated markers indicative of organ toxicity associated with STAC immunosuppression. RESULTS: Compared to controls, topical therapy with TAC+MPA significantly prolonged allograft survival beyond 100 daysat very low dose STAC (0.1 mg/kg/day) (Group 6). The histopathological assessment of the grafts was consistent with the clinical outcomes. .Drug levels in blood/plasma remained low or undetectable, while allograft tissues showed higher drug concentrations compared to contralateral limb tissues (P<0.05). . Urinary creatinine clearance remained within the normal range at 2.5 mL/min. CONCLUSION: Combination therapy with topical TAC and MPA synergizes with a very low dose, corticosteroid- free-STAC regimen and facilitates rejection-free, prolonged VCA survival without morbidity.

POZ/BTB and AT hook containing zinc finger 1 (PATZ1) suppresses differentiation and regulates metabolism in human embryonic stem cells.

Human embryonic stem cells (hESCs) can proliferate infinitely (self-renewal) and give rise to almost all types of somatic cells (pluripotency). Hence, understanding the molecular mechanism of pluripotency regulation is important for applications of hESCs in regenerative medicine. Here we report that PATZ1 is a key factor that regulates pluripotency and metabolism in hESCs. We found that depletion of PATZ1 is associated with rapid downregulation of master pluripotency genes and prominent deceleration of cell growth. We also revealed that PATZ1 regulates hESC pluripotency though binding the regulatory regions of OCT4 and NANOG. In addition, we demonstrated PATZ1 is a key node in the OCT4/NANOG transcriptional network. We further revealed that PATZ1 is essential for cell growth in hESCs. Importantly, we discovered that depletion of PATZ1 drives hESCs to exploit glycolysis which energetically compensates for the mitochondrial dysfunction. Overall, our study establishes the fundamental role of PATZ1 in regulating pluripotency in hESCs. Moreover, PATZ1 is essential for maintaining a steady metabolic homeostasis to refine the stemness of hESCs.

Conserved mechanisms of self-renewal and pluripotency in mouse and human ESCs regulated by simulated microgravity using a 3D clinostat.

Embryonic stem cells (ESCs) exhibit unique attributes of boundless self-renewal and pluripotency, making them invaluable for fundamental investigations and clinical endeavors. Previous examinations of microgravity effects on ESC self-renewal and differentiation have predominantly maintained a descriptive nature, constrained by limited experimental opportunities and techniques. In this investigation, we present compelling evidence derived from murine and human ESCs, demonstrating that simulated microgravity (SMG)-induced stress significantly impacts self-renewal and pluripotency through a previously unidentified conserved mechanism. Specifically, SMG induces the upregulation of heat shock protein genes, subsequently enhancing the expression of core pluripotency factors and activating the Wnt and/or LIF/STAT3 signaling pathways, thereby fostering ESC self-renewal. Notably, heightened Wnt pathway activity, facilitated by Tbx3 upregulation, prompts mesoendodermal differentiation in both murine and human ESCs under SMG conditions. Recognizing potential disparities between terrestrial SMG simulations and authentic microgravity, forthcoming space flight experiments are imperative to validate the impact of reduced gravity on ESC self-renewal and differentiation mechanisms.

Diagnostic performance of coronary computed tomography angiography stenosis score for coronary stenosis.

BACKGROUND: Coronary computed tomography angiography stenosis score (CCTA-SS) is a proposed diagnosis score that considers the plaque characteristics, myocardial function, and the diameter reduction rate of the lesions. This study aimed to evaluate the diagnostic performance of the CCTA-SS in seeking coronary artery disease (CAD). METHODS: The 228 patients with suspected CAD who underwent CCTA and invasive coronary angiography (ICA) procedures were under examination. The diagnostic performance was evaluated with the receiver operating curve (ROC) for CCTA-SS in detecting CAD (defined as a diameter reduction of ≥ 50%) and severe CAD (defined as a diameter reduction of ≥ 70%). RESULTS: The area under ROC (AUC) of CCTA-SS was 0.909 (95% CI: 0.864-0.943), which was significantly higher than that of CCTA (AUC: 0.826; 95% CI: 0.771-0.873; P = 0.0352) in diagnosing of CAD with a threshold of 50%. The optimal cutoff point of CCTA-SS was 51% with a sensitivity of 90.66%, specificity of 95.65%, positive predictive value of 98.80%, negative predictive value of 72.13%, and accuracy of 91.67%, whereas the optimal cutoff point of CCTA was 55%, and the corresponding values were 87.36%, 93.48%, 98.15%, 65.15%, and 88.60%, respectively. With a threshold of 70%, the performance of CCTA-SS with an AUC of 0.927 (95% CI: 0.885-0.957) was significantly higher than that of CCTA with an AUC of 0.521 (95% CI: 0.454-0.587) (P < 0.0001). CONCLUSIONS: CCTA-SS significantly improved the diagnostic accuracy of coronary stenosis, including CAD and severe CAD, compared with CCTA.