Assessment of Coronary Flow Velocity Reserve by Noninvasive Transthoracic Doppler Echocardiography in Patients with Angiographically Normal Coronary Arteries

Summary： The measurement of coronary flow velocity reserve （CFVR） by transthoracic Doppler echocardiography （TTDE） with invasive intracoronary Doppler flow wire technique （ICD） was validated and the pathological factors which influence CFVR in patients with angiographically normal coronary arteries were analyzed. CFVR was determined successfully in left anterior descending artery （LAD） in 37 of 40 patients with angiographically normal coronary arteries （men 22, women 15, age 20-75 years, mean age 54±12 years）. Coronary flow velocity was measured in the distal LAD by TTDE with contrast enhancement at baseline and during intravenous adenosine infusion of 110 μg/ kg per min within 48 h after ICD technique. Average peak velocity at baseline （APVb）, average peak velocity during hyperemia （APVh） and CFVR determined from TTDE were correlated closely with those from ICD measurements （APVb： y= 0. 64x＋ 5. 04, r=0. 86, P〈0. 001; APVh： y=0. 63x＋14. 36, r=0.82, P〈0.001; CFVR： y=0.65xq-0.92, r=0.88, P〈0.001）. For CFVR measurements, the mean differences between TTDE and ICD methods were 0. 12±0.39. CFVR in patients with history of hypertension was significantly lower than that in patients without history of hypertension （P〈0.05）. Intravascular ultrasound （IVUS） was performed in 34 patients. Plaque formation was found in LAD by IVUS in 17 （50%） patients. No significant difference in CFVR was found between the patients without plaque formation （3. 11±0. 49） and those with plaque formation （2. 76±0.53, P=0. 056）. It is suggested that TTDE with contrast enhancement provides reliable measurement of APV and CFVR in the distal I.AD. The early stage of atherosclerosis could be detected by IVUS, which may be normal in angiography. CFVR is impaired in patients with history of hypertension compared with that in patients without history of hypertension.

Non-invasive Assessment of Coronary Flow Velocity Reserve: A New Method Using Transthoracic Doppler Echocardiography

Summary: Transthoracic Doppler echocardiography (TTDE) allows noninvasive flow measurement in the distal left anterior descending artery (LAD). The feasibility of detecting coronary flow by contrast-enhanced TTDE with second harmonic technique was assessed, the coronary flow velocity reserve (CFVR) was evaluated in comparison to intracoronary Doppler flow (ICD) analysis and the CFVR after PTCA in LAD was investigated. In 77 (96 %) of 80 patients, CFVR was successfully determined with intravenous adenosine infusion. Doppler signal quality was evaluated in the first 46 patients by use of intravenous Levovist infusion and second harmonic technique. The Doppler flow was not visible in 1 patient only. CFVR determined from TTDE (2.77±0.65) was correlated closely with those from ICD (2.88±0.78) measurements (y=0.73x+0.67, r=0.87, P<0.001). In conclusion, TTDE is a feasible method and provides reliable data on CFVR which can be used for follow-up after PTCA.

Value of Acceleration Flow in the Left Anterior Descending Coronary Artery for the Detection of Coronary Artery Stenosis by Transthoracic Coronary Color Doppler Echocardiography

Summary： Whether the localized flow acceleration occurs in the resting stenotie left anterior descending coronary artery was explored and its value for detection of coronary stenosis estimated. Blood flow in the left anterior descending coronary arteries in 45 patients was detected by transthoratio color Doppler echocardiograph and multipoint pulse Doppler spectrums were recorded in the same segment. The ratio of the maximal peak diastolic velocity to the minimal peak diastolic velocity was calculated. The ratio ≥1.5 was the cutoff value for the presence of localized acceleration flow. There were 23 patients with localized acceleration flow examined by eehoeardiography. Twenty of them were found to have luminal diameter stenosis （60%-98%） in the left anterior descending coronary arteries by coronary angiography and 3 patients were normal. There were 22 patients without localized acceleration flow examined by eehoeardiography. Eighteen of them had no or %60 stenosis. Four patients had serious stenosis （≥95%） or occluded segments in the left anterior descending coronary arteries on coronary angiography. The ratio of the maximal peak diastolic velocity to the minimal peak diastolic velocity was significantly higher in patients with left anterior descending coronary artery stenosis than that in those without stenosis （1.9±0.3 vs 1.3±0.2, P〈0.01） and it correlated significantly with left anterior descending coronary artery stenosis （r=0.77, P〈0.01）. The specificity by using the ratio≥1. 5 for stenosis detection was 85.7% （18/ 21）, and the sensitivity was 83.3% （20/24）. This study demonstrated that local blood flow velocity was increased in the resting stenotie left anterior descending coronary artery. Transthoraeie color Doppler eehoeardiography is a reliable noninvasive method to detect localized acceleration flow in the left anterior descending coronary artery stenosis and it is useful in the noninvasive diagnosis of stenosis in the left anterior descending coronary artery.

Effects of sevoflurane on left ventricular function by speckletracking echocardiography in coronary bypass patients: A randomized trial

The present study aimed to dynamically observe the segmental and global myocardial movements of the left ventricle during coronary artery bypass grafting by transesophageal speckle-tracking echocardiography,and to assess the effect of sevoflurane on cardiac function.Sixty-four patients scheduled for the off-pump coronary artery bypass grafting were randomly divided into a sevoflurane-based anesthesia(AS)group and a propofolbased total intravenous anesthesia(AA)group.The AS group demonstrated a higher absolute value of left ventricular global longitudinal strain than that of the AA group at both T1(after harvesting all grafts and before coronary anastomosis)and T_(2)(30 min after completing all coronary anastomoses)(P<0.05).Moreover,strain improvement in the segment with the highest preoperative strain was significantly reduced in the AS group,compared with the AA group at both T1 and T_(2)(P<0.01).The flow of the left internal mammary artery-left anterior descending artery graft was superior,and the postoperative concentration of troponin T decreased rapidly in the AS group,compared with the AA group(P<0.05).Compared with total intravenous anesthesia,sevoflurane resulted in a significantly higher global longitudinal strain,stroke volume,and cardiac output.Sevoflurane also led to an amelioration in the condition of the arterial graft.Furthermore,sevoflurane significantly reduced strain improvement in the segmental myocardium with a high preoperative strain value.The findings need to be replicated in larger studies.

Evaluation of global cardiac systolic performance and diastolic filling in central hypovolumia by lower body negative pressure with Doppler echocardiography

Objective ：To overall evaluate the change of global cardiac systolic performance and diastolic filling in hypovoleamia by LBNP, Methods：10 healthy male subjects were placed in a standard LBNP chamber. Baseline haemodynamic and echocardiographic measurements were made after a period of least 10 min resting supine within the chamber. Pressure was then decreased to -10,-20 and -30 mmHg, with each pressure maintained for 15 rain. The indices of four transvalvular and SVC flow were measured using Doppler echocardiography. Results ：The results showed that S wave, Re wave ,and VTI of SVC progressively decreased with increasing LBNP. At -30 mmHg stage, S wave decreased by 35.4 % （change of 0.21±0.03 m/s, P 〈 0.001）. This reduction in pre-load Was associated with a progressive decrease in SV（by 21.5 ± 4.5 ml at -30 mmHg,P 〈 0.001 ）, decrease in CO（by 1.2 ± 0.2 L min^-1 at -30 mmHg LBNP,P 〈 0.001 ）. The diastolic filling of mitral and tricuspid flow also reduced significantly. At -30 mmHg stage, the E wave of MVF and TVF decreased 31% and 32% respectively （change of 0.23 ± 0.05 m/s,P 〈 0.001 and 0.18 ± 0.01 m/s,P 〈 0.001）. VTI of MVF and TVF decreased 27% and 27.7% respectively（change of 5.55 ± 1.41cm,P 〈 0.01 and 4.25 ± 0.44 cm,P 〈 0.01）. A wave of both sides did not change significantly. Conclusion：Doppler indices changes in different LBNP stage can roughly reflect the degree of hypovoleamia caused by blood volume redistribution. The indices of Doppler echocardiography are more sensitive than traditional physiological indexes in evaluating cardiovascular responses of LBNP. Echocardiography techniques overall can evaluate the global cardiac function including systolic performance and diastolic filling.

Validation of methods for effective orifice area measurement of prosthetic valves by two-dimensional and Doppler echocardiography following transcatheter self-expanding aortic valve implantation

Background The effective orifice area(EOA)is utilized to characterize the hemodynamic performance of the transcatheter heart valve(THV).However,there is no consensus on EOA measurement of self-expanding THV.We aimed to compare two echocardiographic methods for EOA measurement following transcatheter self-expanding aortic valve implantation.Methods EOA was calculated according to the continuity equation.Two methods were constructed.In Method 1 and Method 2,the left ventricular outflow tract diameter(LVOTd)was measured at the entry of the prosthesis(from trailing-to-leading edge)and proximal to the prosthetic valve leaflets(from trailing-toleading edge),respectively.The velocity-time integral(VTI)of the LVOT(VTILVOT)was recorded by pulsed-wave Doppler(PW)from apical windows.The region of the PW sampling should match that of the LVOTd measurement with precise localization.The mean transvalvular pressure gradient(MG)and VTI of THV was measured by Continuous wave Doppler.Results A total of 113 consecutive patients were recruited.The mean age was 77.2±5.5 years,and 72 patients(63.7%)were male.EOA1 with the use of Method 1 was larger than EOA2(1.56±0.39 cm2 vs.1.48±0.41 cm2,P=0.001).MG correlated better with the indexed EOA1(EOAI1)(r=-0.701,P<0.001)than EOAI2(r=-0.645,P<0.001).According to EOAI(EOAI≤0.65 cm2/m2,respectively),the proportion of sever prosthesis-patient mismatch with the use of EOA1 was lower than EOA2(12.4%vs.21.2%,P<0.05).Compared with EOA2,EOA1 had lower interobserver and intra-observer variability(intra:0.5%±17%vs.3.8%±22%,P<0.001;inter:1.0%±9%vs.3.5%±11%,P<0.001).Conclusions For transcatheter self-expanding valve EOA measurement,LVOTd should be measured in the entry of the prosthesis stent(from trailing-to-leading edge),and VTILVOT should match that of the LVOTd measurement with precise localization.

Remote sensing of air pollution incorporating integrated-path differential-absorption and coherent-Doppler lidar

An innovative complex lidar system deployed on an airborne rotorcraft platform for remote sensing of atmospheric pollution is proposed and demonstrated.The system incorporates integrated-path differential absorption lidar(DIAL) and coherent-doppler lidar(CDL) techniques using a dual tunable TEA CO_(2)laser in the 9—11 μm band and a 1.55 μm fiber laser.By combining the principles of differential absorption detection and pulsed coherent detection,the system enables agile and remote sensing of atmospheric pollution.Extensive static tests validate the system’s real-time detection capabilities,including the measurement of concentration-path-length product(CL),front distance,and path wind speed of air pollution plumes over long distances exceeding 4 km.Flight experiments is conducted with the helicopter.Scanning of the pollutant concentration and the wind field is carried out in an approximately 1 km slant range over scanning angle ranges from 45°to 65°,with a radial resolution of 30 m and10 s.The test results demonstrate the system’s ability to spatially map atmospheric pollution plumes and predict their motion and dispersion patterns,thereby ensuring the protection of public safety.

Venous Doppler flow patterns,venous congestion,heart disease and renal dysfunction:A complex liaison

The World Journal of Cardiology published an article written by Kuwahara et al that we take the pleasure to comment on.We focused our attention on venous congestion.In intensive care settings,it is now widely accepted that venous congestion is an important clinical feature worthy of investigation.Evaluating venous Doppler profile abnormalities at multiple sites could suggest adequate treatment and monitor its efficacy.Renal dysfunction could trigger or worsen fluid overload in heart disease,and cardio-renal syndrome is a well-characterized spectrum of disorders describing the complex interactions between heart and kidney diseases.Fluid overload and venous congestion,including renal venous hypertension,are major determinants of acute and chronic renal dysfunction arising in heart disease.Organ congestion from venous hypertension could be involved in the development of organ injury in several clinical situations,such as critical diseases,congestive heart failure,and chronic kidney disease.Ultrasonography and abnormal Doppler flow patterns diagnose clinically significant systemic venous congestion.Cardiologists and nephrologists might use this valuable,noninvasive,bedside diagnostic tool to establish fluid status and guide clinical choices.

Z-Score in Fetal Echocardiography–Is there Still Room for New Studies?

Congenital heart disease(CHD)is the most common type of birth defect,representing a significant cause of peri-natal morbidity and mortality.Early diagnosis of such anomalies is crucial for improving outcomes.Current pro-tocols recommend a qualitative assessment of cardiac structures using two-dimensional ultrasound(2DUS)and color Doppler imaging.In cases of suspected abnormalities,quantitative assessments through cardiac structure measurements and reference curves can aid in accurate diagnosis.Similar to centiles widely employed in obste-trics,Z-scores provide more precise quantification of various cardiac structures,particularly at the extremes of the curve.While the development of reference curves and Z-scores has progressed over the past two decades,a lack of standardization in measurements and statistical methodology for their determination is evident.Establishing reference curves requires adherence to specific recommendations to improve their accuracy.The purpose of this study is to provide a narrative review of the major studies that have generated reference values for cardiac struc-tures using 2DUS and Z-scores,to evaluate their methodology,and to provide a summary of the results.

Clinical Versus Doppler Based Assessment in Determining Amputation Level in Diabetic Foot Gangrene;A Prospective Cross-Sectional Study at Atbuth, Bauchi

Background: Amputation is defined as the surgical removal of a limb or part of a limb through the bone. If the amputation is done above or below the knee, they are termed major while minor amputations involve the partial removal of foot including forefoot resections, ray amputation of the digits or parts of the digits. Significant number of patients with diabetic foot ulcers end with amputations. In the past the amputation level was decided by clinical assessment alone, such as physical examination using color, temperature, peripheral pulses and wound bleeding during surgical procedure. The use of Doppler ultrasound to measure arterial blood pressure at the proposed amputation site has been advocated as a predictor of amputation success. An optimal choice of the level of amputation can reduce amputation complications. Methodology: A Prospective comparative randomized cross-sectional study carried out between 1st January 2022 and 1st January 2024 in ATBUTH, Bauchi amongst patients with diabetic foot Wagener stage IV and V scheduled for amputation. Outcome measures of wound break down, flap necrosis and re-amputation were assessed amongst the clinical based level assessment group and the doppler based level assessment group. Results: A total of 171 patients were recruited into the study. Males 103 and 68 are females, giving a male to female ratio of 1.5:1. mean age 47 years. There were 84 patients in the clinical based level assessment group and 87 patients in the doppler based level assessment. Conclusion: Diabetes mellitus foot disease is a significant risk factor for non-traumatic lower limb amputation and doppler level assessment is superior to clinical level in determining amputation level among diabetic patients scheduled for amputation. P-value 0.003.

Observation of Doppler shift f_(D) modulated by the internal kink mode using conventional reflectometry in the EAST tokamak

In this paper we present a new experimental observation using a conventional reflectometry technique,poloidal correlation reflectometry(PCR),in the Experimental Advanced Superconducting Tokamak(EAST).The turbulence spectrum detected by the PCR system exhibits an asymmetry and induced Doppler shift f_(D)during the internal kink mode(IKM)rotation phase.This Doppler shift f_(D)is the target measurement of Doppler reflectometry,but captured by conventional reflectometry.Results show that the Doppler shift f_(D)is modulated by the periodic changes in the effective angle between the probing wave and cutoff layer normal,but not by plasma turbulence.The fishbone mode and saturated long-lived mode are typical IKMs,and this modulation phenomenon is observed in both cases.Moreover,the value of the Doppler shift f_(D)is positively correlated with the amplitude of the IKM,even when the latter is small.However,the positive and negative frequency components of the Doppler shift f_(D)can be asymmetric,which is related to the plasma configuration.A simulated analysis is performed by ray tracing to verify these observations.These results establish a clear link between f_(D)and IKM rotation,and are helpful for studying the characteristics of IKM and related physical phenomena.

Comparison and Verification of Coherent Doppler Wind Lidar and Radiosonde Data in the Beijing Urban Area

As a new type of wind field detection equipment, coherent Doppler wind lidar(CDWL) still needs more relevant observation experiments to compare and verify whether it can achieve the accuracy and precision of traditional observation equipment in urban areas. In this experiment, a self-developed CDWL provided four months of observations in the southern Beijing area. After the data acquisition time and height match, the wind profile data obtained based on a Doppler beam swinging(DBS) five-beam inversion algorithm were compared with radiosonde data released from the same location. The standard deviation(SD) of wind speed is 0.8 m s^(–1), and the coefficient of determination R~2 is 0.95. The SD of the wind direction is 17.7° with an R~2 of 0.96. Below the height of the roughness sublayer(about 400 m), the error in wind speed and wind direction is significantly greater than the error above the height of the boundary layer(about 1500 m). For the case of wind speeds less than 4 m s^(–1), the error of wind direction is more significant and is affected by the distribution of surrounding buildings. Averaging at different height levels using suitable time windows can effectively reduce the effects of turbulence and thus reduce the error caused by the different measurement methods of the two devices.

Decoupling of temporal/spatial broadening effects in Doppler wind LiDAR by 2D spectral analysis

Pulse echo accumulation is commonly employed in coherent Doppler wind LiDAR(light detection and ranging)under the assumption of steady wind.Here,the measured spectral data are analyzed in the time dimension and frequency dimension to cope with the temporal wind shear and achieve the optimal accumulation time.A hardware-efficient algorithm combining the interpolation and cross-correlation is used to enhance the wind retrieval accuracy by reducing the frequency sampling interval and then reduce the spectral width calculation error.Moreover,the temporal broadening effect and spatial broadening effect are decoupled according to the strategy we developed.

Observation of Low-Level Jets in the Eastern Tropical Indian Ocean Based on Shipborne Coherent Doppler Lidar

In contrast to the Pacific and Atlantic Oceans,the Indian Ocean has lacked in-situ observations of wind profiles over open sea areas for decades.In 2021,a shipborne coherent Doppler lidar(CDL)was used to observe in-situ wind profiles in the eastern tropical Indian Ocean.This equipment successfully captured low-level jets(LLJs)in the region,and their characteristics were thoroughly analyzed.Results reveal that the observed wind speed of LLJs in the eastern Indian Ocean ranges from 6 m s^(-1) to 10 m s^(-1) during the boreal winter and spring seasons,showing a height range of 0.6 to 1 km and two peak times at 0800 and 2000 UTC.This wind shear is weaker than that in land or offshore areas,ranging from 0 s^(-1) to 0.006 s^(-1).Moreover,the accuracy of the CDL data is compared to that of ERA5 data in the study area.The results indicate that the zonal wind from ERA5 data significantly deviated from the CDL measurement data,and the overall ERA5 data are substantially weaker than the in-situ observations.Notably,ERA5 underestimates northwestward LLJs.

Abnormal Umbilical Doppler: Incidence and Neonatal Outcomes among Hypertensive Disorders in Pregnancy at KCMC: A Hospital-Based Prospective Cohort Study

Hypertensive disorders of pregnancy (HDP) are the most common maternal and perinatal health challenges. Globally, the incidence of HDP increased from 16.30 million to 18.08 million, with a total increase of about 10.9% from 1990 to 2019. Umbilical Doppler study in hypertensive disorders of pregnancy helps to predict neonatal outcomes and prevent neonatal and maternal morbidity and mortality. Objective: This study aims to determine the incidence of abnormal umbilical Doppler among hypertensive pregnant women, to identify the adverse neonatal outcomes associated with abnormal umbilical Doppler, and also to detect the diagnostic predictive values of umbilical Doppler to neonatal outcomes at KCMC. Material and methods: A hospital-based prospective cohort study included women with hypertensive disorders of pregnancy from the gestational age of 28 weeks and above, followed up to delivery during the study period from August 2022 to March 2023. Multivariate logistic regression analysis was used to determine the association between AUD and neonatal outcomes. Results: Out of 112 women with HDP, the incidence of abnormal umbilical Doppler was 38 (33.93%). Abnormal umbilical Doppler was associated with neonates with low birth weight aOR (95% of CI) of 4.52 (1.59 - 12.83) p = 0.005 and neonatal ICU admission 9.71 (2.90 - 32.43) p Conclusion: The incidence of abnormal umbilical Doppler is high in hypertensive disorders of pregnancy which is associated with an increase in neonatal low birth weight and neonatal ICU admissions, the sensitivity of abnormal umbilical Doppler in prediction of low birth weight and neonatal ICU admission is significant hence the routine use of umbilical Doppler assessment among hypertensive pregnant women is crucial.

Opto-mechanical-thermal integration analysis of Doppler asymmetric spatial heterodyne interferometer

In order to improve the detection accuracy of Doppler asymmetric spatial heterodyne(DASH)interferometer in harsh temperatures,an opto-mechanical-thermal integration analysis is carried out.Firstly,the correlation between the interference phase and temperature is established according to the working principle and the phase algorithm of the interferometer.Secondly,the optical mechanical thermal analysis model and thermal deformation data acquisition model are designed.The deformation data of the interference module and the imaging optical system at different temperatures are given by temperature load simulation analysis,and the phase error caused by thermal deformation is obtained by fitting.Finally,based on the wind speed error caused by thermal deformation of each component,a reasonable temperature control scheme is proposed.The results show that the interference module occupies the main cause,the temperature must be controlled within(20±0.05)℃,and the temperature control should be carried out for the temperature sensitive parts,and the wind speed error caused by the part is 3.8 m/s.The thermal drift between the magnification of the imaging optical system and the thermal drift of the relative position between the imaging optical system and the detector should occupy the secondary cause,which should be controlled within(20±2)℃,and the wind speed error caused by the part is 3.05 m/s.In summary,the wind measurement error caused by interference module,imaging optical system,and the relative position between the imaging optical system and the detector can be controlled within 6.85 m/s.The analysis and temperature control schemes presented in this paper can provide theoretical basis for DASH interferometer engineering applications.

Deep learning models semi-automatic training system for quality control of transthoracic echocardiography

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 1250 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(PSAX GV).The videos were divided into development set(245 A4C,155 PLAX,225 PSAX GV),semi-automated training set(98 A4C,62 PLAX,90 PSAX GV)and test set(147 A4C,93 PLAX,135 PSAX GV)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 PSAX GV 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.

BILL Strategy:Points to Consider During the Performance and Interpretation of Critical Care Echocardiography

The growing utilization of critical care echocardiography(CCE) by clinicians necessitates a meticulous review of clinical conditions in critically ill patients, both before and during the examination. The reviewing process of clinical conditions minimizes the risk of overlooking or misinterpreting crucial findings. This article proposes a comprehensive strategy, namely BILL strategy, to integrate into the CCE protocol, where "B" represents baseline respiratory and hemodynamic support, "I" signifies information gleaned from invasive monitoring, including central venous pressure and thermodilution-derived cardiac output, the first "L" denotes laboratory results such as central venous oxygen saturation, troponin, and brain natriuretic peptide, and the second "L" refers to lung ultrasound data. Combining the BILL strategy with CCE can enhance comprehensive understanding of critical conditions, potentially leading to improved diagnostic accuracy and patient outcomes.

Status of clinical applications of artificial intelligence in echocardiography

Artificial intelligence(AI)technology has been increasingly used in medical field with its rapid developments.Echocardiography is one of the best imaging methods for clinical diagnosis of heart diseases,and combining with AI could further improve its diagnostic efficiency.Though the applications of AI in echocardiography remained at a relatively early stage,a variety of automated quantitative and analytical techniques were rapidly emerging and initially entered clinical practice.The status of clinical applications of AI in echocardiography were reviewed in this article.

Intelligent diagnosis of atrial septal defect in children using echocardiography with deep learning

Background Atrial septal defect(ASD)is one of the most common congenital heart diseases.The diagnosis of ASD via transthoracic echocardiography is subjective and time-consuming.Methods The objective of this study was to evaluate the feasibility and accuracy of automatic detection of ASD in children based on color Doppler echocardiographic static images using end-to-end convolutional neural networks.The proposed depthwise separable convolution model identifies ASDs with static color Doppler images in a standard view.Among the standard views,we selected two echocardiographic views,i.e.,the subcostal sagittal view of the atrium septum and the low parasternal four-chamber view.The developed ASD detection system was validated using a training set consisting of 396 echocardiographic images corresponding to 198 cases.Additionally,an independent test dataset of 112 images corresponding to 56 cases was used,including 101 cases with ASDs and 153 cases with normal hearts.Results The average area under the receiver operating characteristic curve,recall,precision,specificity,F1-score,and accuracy of the proposed ASD detection model were 91.99,80.00,82.22,87.50,79.57,and 83.04,respectively.Conclusions The proposed model can accurately and automatically identify ASD,providing a strong foundation for the intelligent diagnosis of congenital heart diseases.