Deep learning-based differentiation of ventricular septal defect from tetralogy of Fallot in fetal echocardiography images.

BACKGROUND: Congenital heart disease (CHD) seriously affects children's health and quality of life, and early detection of CHD can reduce its impact on children's health. Tetralogy of Fallot (TOF) and ventricular septal defect (VSD) are two types of CHD that have similarities in echocardiography. However, TOF has worse diagnosis and higher morality than VSD. Accurate differentiation between VSD and TOF is highly important for administrative property treatment and improving affected factors' diagnoses. OBJECTIVE: TOF and VSD were differentiated using convolutional neural network (CNN) models that classified fetal echocardiography images. METHODS: We collected 105 fetal echocardiography images of TOF and 96 images of VSD. Four CNN models, namely, VGG19, ResNet50, NTS-Net, and the weakly supervised data augmentation network (WSDAN), were used to differentiate the two congenital heart diseases. The performance of these four models was compared based on sensitivity, accuracy, specificity, and AUC. RESULTS: VGG19 and ResNet50 performed similarly, with AUCs of 0.799 and 0.802, respectively. A superior performance was observed with NTS-Net and WSDAN specific for fine-grained image categorization tasks, with AUCs of 0.823 and 0.873, respectively. WSDAN had the best performance among all models tested. CONCLUSIONS: WSDAN exhibited the best performance in differentiating between TOF and VSD and is worthy of further clinical popularization.

Anemia in Heart Failure: A Perspective from 20-Year Bibliometric Analysis.

Background & Objective: Anemia in patients with heart failure (HF) is a growing concern. However, there has no bibliometric analysis in this area up to now. The aim of this study is to explore the status and trends in the field of anemia in HF through the bibliometric analysis, and to provide an outlook on future research. Methods: We retrieved publications from the Web of Science Core Collection database, and the following data analysis and visualization tools were utilized to perform data processing, statistical computing and graphics generation: VOSviewer (v.1.6.18), CiteSpace (v.6.2 R5), Scimago Graphica (v.1.0.36), Biblimatrix and Microsoft Excel. Results: We identified a total of 3490 publications from 2004 to 2023. The publications in the field of anemia in HF are growing steadily. The United States, the United Kingdom, and Italy were the leading countries in this area. Stefan D Anker, as the most influential author, held the most total citations and publications. Harvard University was the most productive institution in this area. The European Journal of Heart Failure had published the most papers. Through the analysis of co-citations, 14 major clusters based on cluster labels were identified. Keyword analysis showed that mortality, outcome, prevalence, and risk were the most frequent keywords, and the potential research hotspots in the future will be intravenous iron and iron deficiency. Conclusion: This study provides a comprehensive analysis of countries, authors, institutions, journals, co-cited references, and keywords in the field of anemia in HF through bibliometric analysis and data visualization. The status, hotspots and future trends in this field offer a reference for in-depth research. Further studies are necessary in the future to broaden the spectrum of research in this field, to evaluate comprehensive approaches to treating anemia in patients with HF, and to find rational targets for the management of anemia.

Deep learning-based anatomical position recognition for gastroscopic examination.

BACKGROUND: The gastroscopic examination is a preferred method for the detection of upper gastrointestinal lesions. However, gastroscopic examination has high requirements for doctors, especially for the strict position and quantity of the archived images. These requirements are challenging for the education and training of junior doctors. OBJECTIVE: The purpose of this study is to use deep learning to develop automatic position recognition technology for gastroscopic examination. METHODS: A total of 17182 gastroscopic images in eight anatomical position categories are collected. Convolutional neural network model MogaNet is used to identify all the anatomical positions of the stomach for gastroscopic examination The performance of four models is evaluated by sensitivity, precision, and F1 score. RESULTS: The average sensitivity of the method proposed is 0.963, which is 0.074, 0.066 and 0.065 higher than ResNet, GoogleNet and SqueezeNet, respectively. The average precision of the method proposed is 0.964, which is 0.072, 0.067 and 0.068 higher than ResNet, GoogleNet, and SqueezeNet, respectively. And the average F1-Score of the method proposed is 0.964, which is 0.074, 0.067 and 0.067 higher than ResNet, GoogleNet, and SqueezeNet, respectively. The results of the t-test show that the method proposed is significantly different from other methods (p< 0.05). CONCLUSION: The method proposed exhibits the best performance for anatomical positions recognition. And the method proposed can help junior doctors meet the requirements of completeness of gastroscopic examination and the number and position of archived images quickly.

Design and Implementation of a Four-Unit Array Piezoelectric Bionic MEMS Vector Hydrophone.

High-performance vector hydrophones have been gaining attention for underwater target-monitoring applications. Nevertheless, there exists the mutual constraint between sensitivity and bandwidth of a single hydrophone. To solve this problem, a four-unit array piezoelectric bionic MEMS vector hydrophone (FPVH) was developed in this paper, which has a cross-beam and a bionic fish-lateral-line-nerve-cell-cilia unit array structure. Simulation analysis and optimization in the design of the bionic microstructure have been performed by COMSOL 6.1 software to determine the structure dimensions and the lead zirconate titanate (PZT) thin film distribution. The FPVH was manufactured using MEMS technology and tested in a standing wave bucket. The results indicate that the FPVH has a sensitivity of up to -167.93 dB@1000 Hz (0 dB = 1 V/µPa), which is 12 dB higher than that of the one-unit piezoelectric MEMS vector hydrophone (OPVH). Additionally, the working bandwidth of the FPVH reaches 20 Hz~1200 Hz, exhibiting a good cosine curve with an 8-shape. This work paves a new way for the development of multi-unit piezoelectric vector hydrophones for underwater acoustic detectors.

The impact of the time factors on the exercise-based cardiac rehabilitation outcomes of the patients with acute myocardial infarction after percutaneous coronary intervention: a systematic review and meta-analysis.

BACKGROUND AND OBJECTIVE: Cardiac rehabilitation (CR) has been demonstrated to improve outcomes in patients with acute myocardial infarction (AMI) after percutaneous coronary intervention (PCI). However, the optimal CR initiation time and duration remain to be determined. This study aimed to explore the impact of the time factors on the CR outcomes in AMI patients who received PCI by the method of meta-regression analysis. METHODS: We searched five databases (PubMed, Embase, Cochrane Library, Web of Science and Google scholar) up to October 31, 2023. Meta-regression analysis was utilized to explore the impact of the time factors on the effect sizes. Subgroups with more than 3 studies were used for meta-regression analysis. RESULTS: Our analysis included 16 studies and a total of 1810 patients. The meta-regression analysis revealed that the initiation time and duration of CR had no significant impact on the occurrence of arrhythmia, coronary artery restenosis and angina pectoris. The initiation time and duration of CR also had no significant impact on the changes in left ventricular ejection fraction (LVEF, starting time: estimate = 0.160, p = 0.130; intervention time: estimate = 0.017, p = 0.149), left ventricular end-diastolic volume (LVEDV, starting time: estimate = - 0.191, p = 0.732; intervention time: estimate = - 0.033, p = 0.160), left ventricular end-systolic volume (LVESV, starting time: estimate = - 0.301, p = 0.464; intervention time: estimate = 0.015, p = 0.368) and 6-minute walk test (6MWT, starting time: estimate = - 0.108, p = 0.467; intervention time: estimate = 0.019, p = 0.116). CONCLUSION: Implementation of CR following PCI in patients with AMI is beneficial. However, in AMI patients, there is no significant difference in the improvement of CR outcomes based on different CR starting times within 1 month after PCI or different durations of the CR programs. It indicates that it is feasible for patients with AMI to commence CR within 1 month after PCI and continue long-term CR, but the time factors which impact CR are intricate and further clinical research is still needed to determine the optimal initiation time and duration of CR.

Molecular targets and mechanisms of Guanxinning tablet in treating atherosclerosis: Network pharmacology and molecular docking analysis.

BACKGROUND: Guanxinning tablet (GXNT), a Chinese patent medicine, is composed of salvia miltiorrhiza bunge and ligusticum striatum DC, which may play the role of endothelial protection through many pathways. We aimed to explore the molecular mechanisms of GXNT against atherosclerosis (AS) through network pharmacology and molecular docking verification. METHODS: The active ingredients and their potential targets of GXNT were obtained in traditional Chinese medicine systems pharmacology database and analysis platform and bioinformatics analysis tool for molecular mechanism of traditional Chinese medicine databases. DrugBank, TTD, DisGeNET, OMIM, and GeneCards databases were used to screen the targets of AS. The intersection targets gene ontology and Kyoto encyclopedia of genes and genomes enrichment analysis were performed in DAVID database. GXNT-AS protein-protein interaction network, ingredient-target network and herb-target-pathway network were constructed by Cytoscape. Finally, we used AutoDock for molecular docking. RESULTS: We screened 65 active ingredients of GXNT and 70 GXNT-AS intersection targets. The key targets of protein-protein interaction network were AKT1, JUN, STAT3, TNF, TP53, IL6, EGFR, MAPK14, RELA, and CASP3. The Kyoto encyclopedia of genes and genomes pathway enrichment analysis showed that pathways in cancer, lipid and atherosclerosis, and PI3K-Akt signaling pathway were the main pathways. The ingredient-target network showed that the key ingredients were luteolin, tanshinone IIA, myricanone, dihydrotanshinlactone, dan-shexinkum d, 2-isopropyl-8-methylphenanthrene-3,4-dione, miltionone I, deoxyneocryptotanshinone, Isotanshinone II and 4-methylenemiltirone. The results of molecular docking showed that tanshinone IIA, dihydrotanshinlactone, dan-shexinkum d, 2-isopropyl-8-methylphenanthrene-3,4-dione, miltionone I, deoxyneocryptotanshinone, Isotanshinone II and 4-methylenemiltirone all had good binding interactions with AKT1, EGFR and MAPK14. CONCLUSION: The results of network pharmacology and molecular docking showed that the multiple ingredients within GXNT may confer protective effects on the vascular endothelium against AS through multitarget and multichannel mechanisms. AKT1, EGFR and MAPK14 were the core potential targets of GXNT against AS.

High-Sensitivity Piezoelectric MEMS Accelerometer for Vector Hydrophones.

In response to the growing demand for high-sensitivity accelerometers in vector hydrophones, a piezoelectric MEMS accelerometer (PMA) was proposed, which has a four-cantilever beam integrated inertial mass unit structure, with the advantages of being lightweight and highly sensitive. A theoretical energy harvesting model was established for the piezoelectric cantilever beam, and the geometric dimensions and structure of the microdevice were optimized to meet the vibration pickup conditions. The sol-gel and annealing technology was employed to prepare high-quality PZT thin films on silicon substrate, and accelerometer microdevices were manufactured by using MEMS technology. Furthermore, the MEMS accelerometer was packaged for testing on a vibration measuring platform. Test results show that the PMA has a resonant frequency of 2300 Hz. In addition, there is a good linear relationship between the input acceleration and the output voltage, with V = 8.412a - 0.212. The PMA not only has high sensitivity, but also has outstanding anti-interference ability. The accelerometer structure was integrated into a vector hydrophone for testing in a calibration system. The results show that the piezoelectric vector hydrophone (PVH) has a sensitivity of -178.99 dB@1000 Hz (0 dB = 1 V/µPa) and a bandwidth of 20~1100 Hz. Meanwhile, it exhibits a good "8" shape directivity and consistency of each channel. These results demonstrate that the piezoelectric MEMS accelerometer has excellent capabilities suitable for use in vector hydrophones.

Evaluation of deep learning methods for early gastric cancer detection using gastroscopic images.

BACKGROUND: A timely diagnosis of early gastric cancer (EGC) can greatly reduce the death rate of patients. However, the manual detection of EGC is a costly and low-accuracy task. The artificial intelligence (AI) method based on deep learning is considered as a potential method to detect EGC. AI methods have outperformed endoscopists in EGC detection, especially with the use of the different region convolutional neural network (RCNN) models recently reported. However, no studies compared the performances of different RCNN series models. OBJECTIVE: This study aimed to compare the performances of different RCNN series models for EGC. METHODS: Three typical RCNN models were used to detect gastric cancer using 3659 gastroscopic images, including 1434 images of EGC: Faster RCNN, Cascade RCNN, and Mask RCNN. RESULTS: The models were evaluated in terms of specificity, accuracy, precision, recall, and AP. Fast RCNN, Cascade RCNN, and Mask RCNN had similar accuracy (0.935, 0.938, and 0.935). The specificity of Cascade RCNN was 0.946, which was slightly higher than 0.908 for Faster RCNN and 0.908 for Mask RCNN. CONCLUSION: Faster RCNN and Mask RCNN place more emphasis on positive detection, and Cascade RCNN places more emphasis on negative detection. These methods based on deep learning were conducive to helping in early cancer diagnosis using endoscopic images.

Deep learning for differentiating benign from malignant tumors on breast-specific gamma image.

BACKGROUND: Breast diseases are a significant health threat for women. With the fast-growing BSGI data, it is becoming increasingly critical for physicians to accurately diagnose benign as well as malignant breast tumors. OBJECTIVE: The purpose of this study is to diagnose benign and malignant breast tumors utilizing the deep learning model, with the input of breast-specific gamma imaging (BSGI). METHODS: A benchmark dataset including 144 patients with benign tumors and 87 patients with malignant tumors was collected and divided into a training dataset and a test dataset according to the ratio of 8:2. The convolutional neural network ResNet18 was employed to develop a new deep learning model. The model proposed was compared with neural network and autoencoder models. Accuracy, specificity, sensitivity and ROC were used to evaluate the performance of different models. RESULTS: The accuracy, specificity and sensitivity of the model proposed are 99.1%, 98.8% and 99.3% respectively, which achieves the best performance among all methods. Additionally, the Grad-CAM method is used to analyze the interpretability of the diagnostic results based on the deep learning model. CONCLUSION: This study demonstrates that the proposed deep learning method could help physicians diagnose benign and malignant breast tumors quickly as well as reliably.

Emerging trends and hotspots evolution in cardiotoxicity: A bibliometric and knowledge-Map analysis From 2010 to 2022.

Background: There is growing emphasis on the cardiotoxicity research over the past 12 years. To look for the hotspots evolution and to explore the emerging trends in the field of cardiotoxicity, publications related to cardiotoxicity were acquired from the Web of Science Core Collection on August 2, 2022. Methods: We used the CiteSpace 5.8 R3 and VOSviewer 1.6.18 to perform bibliometric and knowledge-map analysis. Results: A total of 8,074 studies by 39,071 authors from 6,530 institutions in 124 countries or regions were published in different academic journals. The most productive country was absolutely the United States, and the University of Texas MD Anderson Cancer Center was the institution with the largest output. Zhang, Yun published the most articles, and the author who had the most frequent co-citations was Moslehi, Javid. New England Journal of Medicine was the most frequently cited journals in this field. Mechanisms of cardiotoxicity have received the most attention and was the main research directions in the field. The disease of cardiotoxicity together with the related risk factors are potential research hotspots. Immune checkpoint inhibitor and myocarditis are two recently discussed and rapidly expanding research topic in the areas of cardiotoxicity. Conclusions: This bibliometric analysis provided a thorough analysis of the cardiotoxicity, which would provide crucial sources of information and concepts for academics studying this area. As a rapidly expanding field in cardiology, the related field of cardiotoxicity will continue to be a focus of research.

Gas-Sensing Properties and Mechanisms of 3D Networks Composed of ZnO Tetrapod Micro-Nano Structures at Room Temperature.

Metal oxide semiconductors (MOSs) hold great promise for electronic devices such as gas sensors. The utilization of ZnO as a conductometric gas sensor material can be traced back to its early stages; however, its application has primarily been limited to high-temperature environments. A gas sensor based on highly porous and interconnected 3D networks of ZnO tetrapod (ZnO-T) micro-nano structures was fabricated via an easy chemical vapor deposition (CVD) method. Homemade instruments were utilized to evaluate the gas-sensing of the sample at room temperature. It exhibited good gas-sensing at room temperature, particularly with a response of up to 338.80% toward 1600 ppm ethanol, while also demonstrating remarkable repeatability, stability, and selectivity. Moreover, the unique gas-sensing properties of ZnO-T at room temperature can be reasonably explained by considering the effect of van der Waals forces in physical adsorption and the synergistic effect of carrier concentration and mobility. The aforementioned statement presents an opportunity for the advancement of gas sensors utilizing ZnO at room temperature.

Bioresorbable scaffolds vs. drug-eluting stents for patients with myocardial infarction: A systematic review and meta-analysis of randomized clinical trials.

Objective: To compare the efficacy and safety of bioresorbable scaffolds (BRS) with drug-eluting stents (DES) in patients with myocardial infarction undergoing percutaneous coronary interventions (PCI). Methods: We performed a systematic review and meta-analysis of randomized controlled trials (RCTs) comparing BRS with DES on clinical outcomes with at least 12 months follow-up. Electronic databases of PubMed, CENTRAL, EMBASE, and Web of Science from inception to 1 March 2022 were systematically searched to identify relevant studies. The primary outcome of this study was the device-oriented composite endpoint (DOCE) consisting of cardiac death, target-vessel myocardial infarction, and target lesion revascularization. Secondary outcomes were a composite of major adverse cardiac events (MACE, all-cause death, target-vessel myocardial infarction, or target vessel revascularization) and the patient-oriented composite endpoint (POCE, defined as a composite of all-cause death, myocardial infarction, or revascularization). The safety outcomes were definite/probable device thrombosis and adverse events. Results: Four randomized clinical trials including 803 participants with a mean age of 60.5 ± 10.8 years were included in this analysis. Patients treated with BRS had a higher risk of the DOCE (RR 1.62, 95% CI: 1.02-2.57, P = 0.04) and MACE (RR 1.77, 95% CI: 1.02-3.08, P = 0.04) compared with patients treated with DES. No significant difference on the POCE (RR 1.33, 95% CI: 0.89-1.98, P = 0.16) and the definite/probable device thrombosis (RR 1.31, 95% CI: 0.46-3.77, P = 0.61) were observed between BRS and DES. No treatment-related serious adverse events were reported. Conclusion: BRS was associated with a higher risk of DOCE and MACE compared with DES in patients undergoing PCI for myocardial infarction. Although this seems less effective in preventing DOCE, BRS appears as safe as DES. Systematic review registration: [https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=321501], identifier [CRD 42022321501].

Fatigue Fracture Analysis on 2524 Aluminum Alloy with the Influence of Creep-Aging Forming Processes.

The different creep-aging forming processes of 2524 aluminum alloy were taken as the research object, and the effects of creep-aging temperature and creep stress on the fatigue-crack propagation properties of the alloy were studied. The research results showed the following under the same sintering time of 9 h, at creep-aging temperatures of 100 °C, 130 °C, 160 °C, and 180 °C, respectively, with an increase in creep-aging temperature: the fatigue-crack propagation rate was promoted, the spacing of fatigue striations increased, and the sizes of dimples decreased while the number was enlarged; this proves that the fatigue property of the alloy was weakened. Compared with the specimens with creep deformation radii of 1000 mm and 1500 mm, the creep deformation stress was the smallest when the forming radius was 1800 mm, with a higher threshold value of fatigue-crack growth in the near-threshold region of fatigue-crack propagation (ΔK ≤ 8 MPa·m1/2). Under the same fatigue cycle, the specimens under the action of larger creep stress endured a longer fatigue stable-propagation time and a faster fracture speed. Comparing the effect of creep-aging temperature and creep stress, the creep-aging temperature plays a dominant role in the fatigue-crack propagation of creep-aged 2524 aluminum alloy.

Elastography ultrasound with machine learning improves the diagnostic performance of traditional ultrasound in predicting kidney fibrosis.

BACKGROUND: Noninvasively predicting kidney tubulointerstitial fibrosis is important because it's closely correlated with the development and prognosis of chronic kidney disease (CKD). Most studies of shear wave elastography (SWE) in CKD were limited to non-linear statistical dependencies and didn't fully consider variables' interactions. Therefore, support vector machine (SVM) of machine learning was used to assess the prediction value of SWE and traditional ultrasound techniques in kidney fibrosis. METHODS: We consecutively recruited 117 CKD patients with kidney biopsy. SWE, B-mode, color Doppler flow imaging ultrasound and hematological exams were performed on the day of kidney biopsy. Kidney tubulointerstitial fibrosis was graded by semi-quantification of Masson staining. The diagnostic performances were accessed by ROC analysis. RESULTS: Tubulointerstitial fibrosis area was significantly correlated with eGFR among CKD patients (R = 0.450, P < 0.001). AUC of SWE, combined with B-mode and blood flow ultrasound by SVM, was 0.8303 (sensitivity, 77.19%; specificity, 71.67%) for diagnosing tubulointerstitial fibrosis (>10%), higher than either traditional ultrasound, or SWE (AUC, 0.6735 [sensitivity, 67.74%; specificity, 65.45%]; 0.5391 [sensitivity, 55.56%; specificity, 53.33%] respectively. Delong test, p < 0.05); For diagnosing different grades of tubulointerstitial fibrosis, SWE combined with traditional ultrasound by SVM, had AUCs of 0.6429 for mild tubulointerstitial fibrosis (11%-25%), and 0.9431 for moderate to severe tubulointerstitial fibrosis (>50%), higher than other methods (Delong test, p < 0.05). CONCLUSION: SWE with SVM modeling could improve the diagnostic performance of traditional kidney ultrasound in predicting different kidney tubulointerstitial fibrosis grades among CKD patients.

Effect of Pressure and Temperature on Densification in Electric Field-Assisted Sintering of Inconel 718 Superalloy.

Electric field-assisted sintering has ubiquitous merits over conventional sintering technology for the fabrication of difficult-to-deform materials. To investigate the effect of sintering pressure and temperature on the densification of Inconel 718 superalloy, a numerical simulation model was established based on the Fleck-Kuhn-McMeeking (FKM) and Gurson-Tvergaard-Needleman (GTN) models, which covers a wide range of porosity. At a sintering pressure below 50 MPa or a sintering temperature below 950 °C, the average porosity of the sintered superalloy is over 0.17 with low densification. Under a pressure above 110 MPa and a temperature above 1250 °C, the sintered superalloy quickly completes densification and enters the plastic yield stage, making it difficult to control the sintering process. When the pressure is above 70 MPa while the temperature exceeds 1150 °C, the average porosity is 0.11, with little fall when the pressure or temperature rises. The experimental results indicated that the relative density of the sintered superalloy under 70 MPa and 1150 °C is 94.46%, and the proportion of the grain size below 10 µm is 73%. In addition, the yield strength of the sintered sample is 512 MPa, the compressive strength comes to 1260 MPa when the strain is over 0.8, and the microhardness is 395 Hv, demonstrating a better mechanical property than the conventional superalloy.

Diagnosis of Renal Diseases Based on Machine Learning Methods Using Ultrasound Images.

BACKGROUND: The incidence rate of renal disease is high, which can cause end-stage renal disease. Ultrasound is a commonly used imaging method, including conventional ultrasound, color ultrasound, elastography, etc. Machine learning is a potential method which has been widely used in clinical practices. OBJECTIVE: To compare the diagnostic performance of different ultrasonic image measurement parameters for kidney diseases, and to compare different machine learning methods with the human- reading method. METHODS: Ninety-four patients with pathologically diagnosed renal diseases and 109 normal controls were included in this study. The patients were examined by conventional ultrasound, color ultrasound and shear wave elasticity, respectively. Ultrasonic data were analyzed by Support vector machine (SVM), random forest (RF), K-nearest neighbor (KNN) and artificial neural network (ANN), respectively, and compared with the human-reading method. RESULTS: Only ultrasound elastography data have a diagnostic value for renal diseases. The accuracy of SVM, RF, KNN and ANN methods is 80.98%, 80.32%, 78.03% and 79.67%, respectively, while the accuracy of human-reading is 78.33%. In the data of machine learning ultrasound elastography, the elastic hardness parameters of the renal cortex are most important. CONCLUSION: Ultrasound elastography is of the highest diagnostic value in machine learning for nephropathy, the diagnostic efficiency of the machine learning method is slightly higher than that of the human-reading method, and the diagnostic ability of the SVM method is higher than other methods.

The efficacy and safety of acupuncture for patients with post-percutaneous coronary intervention depression: A protocol for systematic review and meta analysis.

BACKGROUND: Percutaneous coronary intervention (PCI) has been increasingly applied as an effective revascularization strategy in patients with coronary artery disease (CAD). However, recent studies had indicated a higher incidence of depression on post-PCI patients. Acupuncture therapy is effective for depression. However, the treatment effect of depression on post-PCI patients is still not clear. Therefore, this systematic review and meta-analysis protocol is planned to evaluate the efficacy and safety of acupuncture for depression in post-PCI patients. METHODS: Six English databases (PubMed, Web of science, Medline, EMBASE, Springer Cochrane Library and WHO International Clinical Trials Registry Platform) and 4 Chinese databases (Wan fang Database, Chinese Scientific Journal Database, China National Knowledge Infrastructure Database (CNKI) and Chinese Biomedical Literature Database) will be searched normatively according to the rule of each database from the inception to August 1, 2020. Two reviewers will independently conduct article selection, data collection, and risk of bias evaluation. Any disagreement will be resolved by discussion with the third reviewer. Either the fixed-effects or random-effects model will be used for data synthesis based on the heterogeneity test. The change in the scores on the Hamilton depression scale (HAMD) and the Self-rating depression scale (SDS) will be used as the main outcome measure. All-cause mortality, cardiac mortality, Major Adverse Cardiovascular Events (MACEs), rehospitalisation rate and Quality of Life Scale (SF-36) as the secondary outcome. Treatment Emergent Symptom Scale (TESS), General physical examination (temperature, pulse, respiration, blood pressure), Routine examination of blood, urine and stool, Electrocardiogram, Liver and kidney function examination as the security indexs. RevMan5.3.5 will be used for meta-analysis. RESULTS: This study will provide high-quality evidence to assess the efficacy and safety of acupuncture for depression in post-PCI patients. CONCLUSION: This systematic review will explore whether acupuncture is an effective and safe intervention for depression in post-PCI patients.

Full three-dimensional segmentation and quantification of tumor vessels for photoacoustic images.

Quantitative analysis of tumor vessels is of great significance for tumor staging and diagnosis. Photoacoustic imaging (PAI) has been proven to be an effective way to visualize comprehensive tumor vascular networks in three-dimensional (3D) volume, while previous studies only quantified the vessels projected in one plane. In this study, tumor vessels were segmented and quantified in a full 3D framework. It had been verified in the phantom experiments that the 3D quantification results have better accuracy than 2D. Furthermore, in vivo vessel images were quantified by 2D and 3D quantification methods respectively. And the difference between these two results is significant. In this study, complete vessel segmentation and quantification method within a 3D framework was implemented, which showed obvious advantage in the analysis accuracy of 3D photoacoustic images, and potentially improve tumor study and diagnosis.

Detection of Thyroid Nodules with Ultrasound Images Based on Deep Learning.

BACKGROUND: Thyroid nodules are a common clinical entity with high incidence. Ultrasound is often employed to detect and evaluate thyroid nodules. The development of an efficient automated method to detect thyroid nodules using ultrasound has the potential to reduce both physician workload and operator-dependence. OBJECTIVES: To study the method of automatic detection of thyroid nodules based on deep learning using ultrasound, and to obtain the detection method with higher accuracy and better performance. METHODS: A total of 1200 ultrasound images of thyroid nodules and 800 ultrasound thyroid images without nodule are collected. An improved faster R-CNN based detection method of thyroid nodule is proposed. Instead of using VGG16 as the backbone, ResNet is employed as the backbone for faster R-CNN. SVM, CNN and Faster-RCNN methods are used for thyroid nodule detection test. Precision, sensitivity, specificity and F1-score indicators are used to evaluate the detection performance of different methods. RESULTS: The method based on deep learning is superior to that based on SVM. Faster R-CNN method and the improved method are better than CNN method. Compared with VGG16 as the backbone, RestNet101 backbone based faster R-CNN method achieves better thyroid detection effect. From the accuracy index, the proposed method is 0.084, 0.032 and 0.019 higher than SVM, CNN and faster R-CNN, respectively. Similar results can be seen in precision, sensitivity, specificity and F1-Score indicators. CONCLUSION: The proposed method of deep learning achieves the best performance values with the highest true positive and true negative detection compared to other methods and performs best in the detection of thyroid nodules.

Thyroid Diagnosis from SPECT Images Using Convolutional Neural Network with Optimization.

Thyroid disease has now become the second largest disease in the endocrine field; SPECT imaging is particularly important for the clinical diagnosis of thyroid diseases. However, there is little research on the application of SPECT images in the computer-aided diagnosis of thyroid diseases based on machine learning methods. A convolutional neural network with optimization-based computer-aided diagnosis of thyroid diseases using SPECT images is developed. Three categories of diseases are considered, and they are Graves' disease, Hashimoto disease, and subacute thyroiditis. A modified DenseNet architecture of convolutional neural network is employed, and the training method is improved. The architecture is modified by adding the trainable weight parameters to each skip connection in DenseNet. And the training method is improved by optimizing the learning rate with flower pollination algorithm for network training. Experimental results demonstrate that the proposed method of convolutional neural network is efficient for the diagnosis of thyroid diseases with SPECT images, and it has superior performance than other CNN methods.