Object:To explore the feasibility of using artificial intelligence for quality control of echocardiographic images.Methods:Retrospectively，5 000 two-dimensional echocardiographic video images within the period from 2021 to 2023 were randomly retrieved from the echocardiography database of Nanjing Drum Tower Hospital，Affiliated Hospital of Medical School，Nanjing University. Among these selected images，1 559 of them were apical views. The physician team formulated the scoring rules，which specifically included four scoring criteria：gain，scaling ratio，cardiac axis angle，and structure. Subsequently，the data were labeled with view classification and image quality scores. The labeled data were further partitioned into the training set（ n = 643），the validation set（ n = 276），and the test set（ n = 640）. The training and validation sets were utilized for constructing the models for view classification and quality assessment，while the test set was employed to verify the models' effectiveness. The view classification module was implemented using the SlowFast model，and the quality assessment module involved algorithms such as ResNet，Video Swin Transformer，SSD，and U-Net. Results:The average accuracy，precision，recall rate and F1 score of the classification model in identifying each apical view were 0.987 1，0.983 0，0.987 1 and 0.984 9 respectively，and the inference time was（333.4 ± 105.4）ms. The average accuracies of the quality assessment module in terms of gain，scaling ratio，cardiac axis angle and display of main structures were 0.915 1，0.928 2，0.938 7 and 0.965 6 respectively，and the overall scoring accuracy was 0.912 7.Conclusions:The echocardiogram quality control system developed in this research can effectively classify and evaluate the quality of two-dimensional images of the apical views in echocardiograms. Moreover，it guarantees the objectivity，timeliness and high-efficiency of quality control，which has reference value for the establishment of the echocardiogram quality control system.

Object:To explore the feasibility of using artificial intelligence for quality control of echocardiographic images.Methods:Retrospectively，5 000 two-dimensional echocardiographic video images within the period from 2021 to 2023 were randomly retrieved from the echocardiography database of Nanjing Drum Tower Hospital，Affiliated Hospital of Medical School，Nanjing University. Among these selected images，1 559 of them were apical views. The physician team formulated the scoring rules，which specifically included four scoring criteria：gain，scaling ratio，cardiac axis angle，and structure. Subsequently，the data were labeled with view classification and image quality scores. The labeled data were further partitioned into the training set（ n = 643），the validation set（ n = 276），and the test set（ n = 640）. The training and validation sets were utilized for constructing the models for view classification and quality assessment，while the test set was employed to verify the models' effectiveness. The view classification module was implemented using the SlowFast model，and the quality assessment module involved algorithms such as ResNet，Video Swin Transformer，SSD，and U-Net. Results:The average accuracy，precision，recall rate and F1 score of the classification model in identifying each apical view were 0.987 1，0.983 0，0.987 1 and 0.984 9 respectively，and the inference time was（333.4 ± 105.4）ms. The average accuracies of the quality assessment module in terms of gain，scaling ratio，cardiac axis angle and display of main structures were 0.915 1，0.928 2，0.938 7 and 0.965 6 respectively，and the overall scoring accuracy was 0.912 7.Conclusions:The echocardiogram quality control system developed in this research can effectively classify and evaluate the quality of two-dimensional images of the apical views in echocardiograms. Moreover，it guarantees the objectivity，timeliness and high-efficiency of quality control，which has reference value for the establishment of the echocardiogram quality control system.

Objective To explore the value of deep learning(DL)models semi-automatic training system for automatic optimization of clinical image quality control of transthoracic echocardiography(TTE).Methods Totally 1 250 TTE videos from 402 patients were retrospectively collected,including 490 apical four chamber(A4C),310 parasternal long axis view of left ventricle(PLAX)and 450 parasternal short axis view of great vessel(PSAXGv).The videos were divided into development set(245 A4C,155 PLAX,225 PSAXGV),semi-automated training set(98 A4C,62 PLAX,90 PSAXGV)and test set(147 A4C,93 PLAX,135 PSAXGV)at the ratio of 5:2:3.Based on development set and semi-automatic training set,DL model of quality control was semi-automatically iteratively optimized,and a semi-automatic training system was constructed,then the efficacy of DL models for recognizing TTE views and assessing imaging quality of TTE were verified in test set.Results After optimization,the overall accuracy,precision,recall,and F1 score of DL models for recognizing TTE views in test set improved from 97.33％,97.26％,97.26％and 97.26％to 99.73％,99.65％,99.77％and 99.71％,respectively,while the overall accuracy for assessing A4C,PLAX and PSAXGV TTE as standard views in test set improved from 89.12％,83.87％and 90.37％to 93.20％,90.32％and 93.33％,respectively.Conclusion The developed DL models semi-automatic training system could improve the efficiency of clinical imaging quality control of TTE and increase iteration speed.

Objective:To develop and validate a MRI-based radiomics nomogram combining with radiomics signature and clinical factors for the preoperative differentiation of benign parotid gland tumors (BPGT) and malignant parotid gland tumors (MPGT).Methods:From January 2015 to May 2020, 86 patients with parotid tumors confirmed by surgical pathology in the Affiliated Hospital of Qingdao University were enrolled as training sets, and 35 patients in the University of Hong Kong-Shenzhen Hospital from January 2013 to January 2020 were enrolled as independent external validation sets. The logistic regression was used to establish a clinical-factors model based on demographics and MRI findings. Radiomics features were extracted from preoperative T 1WI and fat-saturated T 2WI (fs-T 2WI), a radiomics signature model was constructed, and a radiomics score (Rad-Score) was calculated. A combined diagnostic model and nomogram combining with the Rad-score and independent clinical factors was constructed using multivariate logistic regression analysis. The receiver operating characteristic (ROC) analysis was used to evaluate the performance of each model and DeLong test was used for comparison of area under the ROC curve (AUC). Results:The logistic regression results showed that deep lobe involvement (OR=3.285, P=0.040) and surrounding tissue invasion (OR=15.919, P=0.013) were independent factors for MPGT and constructed the clinical-factors model. A total of 19 features were extracted from the joint T 1WI and fs-T 2WI to build the radiomics signature model. The combined diagnostic model and nomogram incorporating deep lobe involvement, surrounding tissue invasion and Rad-score were established. The AUCs of the clinical-factors model, radiomics signature model and combined diagnostic model for differentiating BPGT from MPGT for the training and validation sets were 0.758, 0.951, 0.953 and 0.752, 0.941 and 0.964 respectively. The AUCs of the radiomics signature model and the combined diagnostic model were significantly higher than those of the clinical-factors model for both training and validation sets (training set: Z=3.95, 4.31, both P<0.001; validation set: Z=2.16, 2.67, P=0.031, 0.008). There was no statistical difference in AUCs between the radiomics signature model and combined diagnostic model (training set: Z=0.39, P=0.697; validation set: Z=1.10, P=0.273). Conclusions:The MRI-based radiomics signature model and radiomics nomogram incorporating deep lobe involvement, surrounding tissue invasion, and Rad-score showed favorable predictive efficacy for differentiating BPGT from MPGT.

Objective: To investigate factors affecting X-ray structure of the spine in patients with ankylosing spondylitis (AS). Methods: A total of 206 AS patients were recruited. Clinical and laboratory parameters in AS patients were recorded in detail. Disease activity index [Bath ankylosing spondylitis disease activity index (BASDAI), ankylosing spondylitis disease activity score (ASDAScrp)], X-ray structural damage index-modified stoke ankylosing spondylitis spine score (mSASSS) and grading results of radiographic examination of sacroiliac joint were calculated. Statistical analysis using Statistical Package form Soci-science(SPSS) 17.0 Chi-square test, rank test, Logistics regression analysis and other statistical methods were used. Differences of mSASSS levels, spine involvement (mSASSS>0) and rates of bone bridge formation were compared between different groups. Results: Incidences of spine involvement (100%) and bone bridge formation(65.2%) in AS patients ≥40 years old were significantly higher than those in AS patients <40 years old (90.6%、31.9%)(χ²=4.651, P=0.031; χ²=16.647, P<0.01), and the level of mSASSS was also higher (Z=5.575, P<0.01). In AS patients with BMI ≥24 kg/m², disease duration ≥5 years (49.2%, 50.4%), rates of bone bridge formation was significantly higher than those in AS with BMI <24 kg/m², but the disease duration (34.5%, 19.7%)(χ²=4.014, P=0.045; χ²=18.173, P=0.03), and mSASSS values were significantly higher (Z=2.281, P=0.023, Z=4.828, P<0.01). Bone bridge formation rate in smoking patients (50.6%) was significantly higher than that in non-smoking patients (31.0%) (χ²=7.346, P=0.007) and mSASSS value was significantly higher (Z=2.045, P=0.041). Bone bridge formation rates in AS with high-ESR and high-CRP(48.6%, 49.0%) were significantly higher than those in patients with normal-ESR and normal-CRP(25.6%, 28.9%)(χ²=10.784, P=0.001; χ²=8.102, P=0.004) and mSASSS value was clearly higher(Z=2.379, P<0.01; Z=3.112, P<0.01). Bone bridge formation rate in AS with BASDAI≥4 or ASDAScrp≥2.1 groups (52.8%, 46.4%) were significantly higher than that in AS with BASDAI<4 or ASDAScrp<2.1 groups (34.2%, 30.7%) (χ²=5.681, P=0.017; χ²=4.646, P=0.031) and mSASSS values were significantly higher (Z=3.887, P<0.01; Z=3.895, P=0.004). Rates of bone bridge formation among different X-ray grading of sacroiliac joint (10.8%, 35.6%, 60.3%) and MRI findings (33.3%, 50.0%, 15.4%) differed with each other (χ²=25.714, P<0.01; χ²=6.855, P=0.032). Logistics regression analysis showed that BMI [OR(95%CI)=1.145(1.037, 1.265), P<0.01], disease duration [OR(95%CI)=1.144(1.055, 1.239), P<0.01], smoking [OR(95%CI)=2.832(1.343, 5.969), P<0.01] and sacroiliac joint X-ray staging [OR(95%CI)=2.584(1.337, 4.997), P<0.01] were risk factors for the bone bridge formation in spine of AS. Conclusion Spinal involvement in AS is related to disease activity. Bone bridge formation correlateswith disease duration, BMI and disease-status, especially with smoking.

Objective To explore the prevalence and reference value of disease features of patients with spondyloarthritis. Methods Spondyioarthritis features and laboratory indexes and radiographic indexes of 505 patients with spondyloarthritis (SpA) including 353 patients with ankylosing spondylitis (AS), 62 patients with non-radiographic axial spondyloarthritis (nr-axSpA) and 90 patients with peripheral spondyloarthritis (pSpA) were recorded. One-way analysis of variance, Kruskal-Wallis test, x2-test, Logistic regression were used for statistical analysis. Results Sex ratio ( x2=20.673, P<0.01), age ( x2=22.258, P<0.01), disease duration ( x2=76.052, P<0.01) were different among AS, nr-axSpA and pSpA. Besides, Bath ankylosing spondylitis disease activity index (BASDAI), ankylosing spondylitis disease activity score (ASDAScrp), erythrocyte sedimentation rate (ESR), C-reactionprotein (CRP) and Bath ankylosing spondylitis functional index (BASFI)were different among SpA subgroups ( x2/F=13.196-40.028, P<0.01). Prevalence of inflammatory back pain, peripheral arthritis, preceding infection, positive human lymphocyte antigen (HLA)-B27 and elevated CRP were different among SpA subgroups ( x2=11.416, 32.657, P<0.01). Prevalence of dactylitis in SpA with positive HLA-B27 was lower than that in SpA with negative HLA-B27 ( x2=5.414, P=0.02). Prevalence of enthesitis and dactylitis in SpA patients with peripheral arthritis was higher than that in SpA without peripheral arthritis involvement ( x2=7.177, 14.428, P<0.01). Prevalence of good response to Non-steroid anti-inflammatory drugs. (NSAIDs) in patients with anterior uveitis involvement was higher than SpA without anterior uveitis involvement ( x2=4.578, P=0.032). SpA patients were stratified by total number of SpA features into 4 subgroups (n≤1, n=2, n=3, n≥4). Prevalence of inflammatory back pain, positive HLA-B27, good response to NSAIDs were the top three in all subgroups. Inflammatory back pain and HLA-B27 (+) were risk factors for axSpA (OR=3.254, 3.323, P<0.01). Peripheral arthritis, dactylitis, and preceding infection were risk factors for pSpA (OR=3.759, 4.134, 17.044, P<0.01). Conclusion Inflammatory back pain, HLA-B27 (+) and good response to NSAIDs should be emphasized for the diagnosis of SpA. Inflammatory back pain and HLA-B27(+) always means axSpA. Peripheral arthritis, dactylitis and preceding infection always indicates pSpA.

Science of cardiac electrophysiology (EP), a most complicated professional branch of car-diovascular medicine, is composed of theoretical knowledge of EP, anatomical knowledge, catheter manipu-lation skills, and antiarrhythmic drug therapy. Longer growth period is involved in clinical cardiac EP physicians due to abstract and complicated electrophysiology knowledge. Starting with simple operation and case to stimulate students' interest in learning, this study focuses on the four teaching modules such as the theory of electrophysiology, the knowledge of anatomy, the skill of the operation of the catheter and the use of antiarrhythmic drugs. It also guides and trains students' simplified habit of thinking and independent thinking and induction learning ability, which improves the cardiac electrophysiologic doctors' efficiency of clinical practice.

Follicular dendritic cell sarcoma is a rare low-grade malignant tumor. At present, only twenty ca ses was discovered all over the world. This paper reports a case treated in our hospital, explores the clinical manifestations, pathological diagnosis and treatment to provide certain help to clinical doctor in diagnosis and treatment to reduce the misdiagnosis of the disease.
Dendritic Cell Sarcoma, Follicular ; diagnosis ; therapy ; Female ; Humans ; Middle Aged ; Palatal Neoplasms ; diagnosis ; therapy

Objective To investigate the effects of constant magnetic field (CMF) on proliferation, apopto-sis and nitric oxide (NO) secretion of rat bone marrow-derived endothelial progenitor cells (EPCs) intervened by C-reactive protein (CRP). Methods EPCs were isolated from rat bone marrow by density gradient centrifugation and cultured on fibronectin-coated dishes. The cells were divided into five groups, i. e., control group, CRP (12 μg/ml) group, CRP plus CMF (0.1, 0. 5, 1.0 mT) groups. Samples were collected 24 hours after incubation. Cell proliferation was measured by MTT chromatometry. Apoptosis rate was detected by flow-cytometry. NO content of culture medium was measured by nitrate reductase method. Results As compared with control group, cell prolifer-ation in CRP group reduced significantly (0. 265±0. 008 vs 0. 316±0. 011, P < 0.05), NO secretion also de-creased significantly [(22.7±4.5) μmol/L vs (37.6±3.8) μmol/L, P < 0.05], cell apoptosis rate elevated sig-nificantly [(10.8±0. 8) % vs (4.2±0.5)% ,P < 0.05]. Cell proliferation in CRP plus 0. 5 mT or 1.0 mT CMF group (0. 295±0. 009,0. 302±0. 010) were much more than those in CRP group (P<0.05), NO secretion contents [(28.3±4.9) μmol/L, (29.2±5.6) μmol/L]were also much more than those in CRP group (P < 0.05) , apopto-sis rate [(7.4±0.5)% ,(6.9±0.6)%]was significantly lower than that in CRP group (P <0.05). Conclusion CMF at intensity of 0.5 mT and 1.0 mT can antagonize the effects of CR, promote proliferation of EPCs and secretion of NO and inhibit apoptosis rate of EPCs.

BACKGROUND: Angiotensin Ⅱ has been found to induce atrial electrical remodeling, which can be blocked or inhibited by allicin.OBJECTIVE: To study the effects of allicin on angiotensin Ⅱ-induced calcium channel current and intracellular free calcium concentration in human atrial myocytes.DESIGN: A randomized controlled study based on human atrial myocytes freshly isolated.SETTING: Cardiology department of a military medical university of Chinese PLA.METHODS: This study was carried out from June 2003 to June 2004 in the Laboratory of Cardiology Department, Xijing Hospital, the Fourth Military Medical University of Chinese PLA. Ten patients with congenital heart disease who underwent extracorporeal circulation surgery were included in the study. Among them, there were 6 males and 4 females with the average age of 15 ± 6 years. Tissue samples were taken from their right auricle and sent to the lab, where the atrial myocytes were freshly isolated. There were four co-administration of angiotensin Ⅱ (0. 1 μmol/L)and allicin(50 μmol/L).The conventional whole-cell configuration of the patch-clamp technique was used to detect membrane electric current of Ca2 + in L type. Confocal microscope was used with Fluo-3/AM as calcium indicator to detect changes of intracellular free calcium concentration immediately and 15 minutes after drug intervention, respectively.MAIN OUTCOME MEASURES: The peak density of electric current of Ca2 + in L type and alteration of fluoresence intensity of intracellular free calcium concentration.electric current of Ca2 + in L type in human atrial myocytes was significantly increased by angiotensin Ⅱ of 0. 1 μmol/L[( - 12. 77 ± 1. 61) vs ( -5.78affect electric current of Ca2+ in L type in human atrial myocytes group, the peak density of electric current of Ca2 + in L type was significantly lower than that in angiotensin Ⅱ group[ ( - 8.75 ± 0.97) pA/pF, P ＜ 0. 05 ].in angiotensin Ⅱ group was significantly higher than that in control and allicin groups[(2 610.1±112.6, (299.2±27.3)%; 653.9±42.5, 0;simultaneously with angiotensin Ⅱ, the alteration of intracellular fluoresence intensity was much lower than that in angiotensin Ⅱ group[ ( 1284.9 ± 85.2,(96.5±8.4)%;P ＜0.05].CONCLUSION: Allicin antagonizes angiotensin Ⅱ-induced increase in the peak density of electric current of Ca2+ in L type and intracellular calcium overload, which may relieve atrial electrical remodeling.