Color Doppler Echocardiography Research Articles

Automatic Segmentation and Evaluation of Mitral Regurgitation Using Doppler Echocardiographic Images

Background: Mitral Regurgitation (MR) is a common heart valve disease. Severe MR can lead to pulmonary hypertension, cardiac arrhythmia, and even death. Therefore, early diagnosis and assessment of MR severity are crucial. In this study, we propose a deep learning-based method for segmenting MR regions, aiming to improve the efficiency of MR severity classification and diagnosis. Methods: We enhanced the Efficient Multi-Scale Attention (EMA) module to capture multi-scale features more effectively, thereby improving its segmentation performance on MR regions, which vary widely in size. A total of 367 color Doppler echocardiography images were acquired, with 293 images used for model training and 74 images for testing. To fully validate the capability of the improved EMA module, we use ResUNet as the backbone, partially integrating the enhanced EMA module into the decoder’s upsampling process. The proposed model is then compared with classic models like Deeplabv3+ and PSPNet, as well as UNet, ResUNet, ResUNet with the original EMA module added, and UNet with the improved EMA module added. Results: The experimental results demonstrate that the model proposed in this study achieved the best performance for the segmentation of the MR region on the test dataset: Jaccard (84.37%), MPA (92.39%), Recall (90.91%), and Precision (91.9%). In addition, the classification of MR severity based on the segmentation mask generated by our proposed model also achieved acceptable performance: Accuracy (95.27%), Precision (88.52%), Recall (91.13%), and F1-score (90.30%). Conclusion: The model proposed in this study achieved accurate segmentation of MR regions, and based on its segmentation mask, automatic and accurate assessment of MR severity can be realized, potentially assisting radiologists and cardiologists in making decisions about MR.

Bio inspired technological performance in color Doppler ultrasonography and echocardiography for enhanced diagnostic precision in fetal congenital heart disease

The aim of this experiment is to investigate the bioinspired diagnostic performance of color Doppler ultrasound (CDUS) and two-dimensional (2D) echocardiography (ECG) for fetal congenital heart disease (FCHD). The research subjects were 33 expectant mothers with a diagnosis of FCHD at Xiangyang No. 1 People's Hospital between January 2017 and January 2021. The accuracy, sensitivity, and specificity of the two detection techniques were computed to ascertain and compare the diagnostic efficiency after CDUS and ECG examinations of all pregnant women. According to the findings, the prenatal CDUS detection rate was 92.61% higher than the 2D ECG detection rate (64.32%). The CDUS had an accuracy of 93.94%, sensitivity of 93.55%, and specificity of 100%, detecting 29 true positives, 0 false positives, 2 false negatives, and 2 true negatives. At 84.85% accuracy, 88.89% sensitivity, and 80% specificity, the 2D ECG identified 16 true positives, 3 false positives, 2 false positives, and 12 true negatives. There was a statistically significant (P < 0.05) difference between the accuracy, sensitivity, and specificity of 2D ECG and CDUS. In summary, CDUS was more effective than 2D ECG in diagnosing prenatal FCHD, and it also had a lower rate of missed and incorrect diagnoses.

'Color Doppler stripes’ make it difficult to diagnose the severity of valvular heart diseases: a report of two cases

BackgroundEchocardiography remains the reference-standard imaging technique for assessing valvular heart disease (VHD), but artifacts like the ‘color Doppler stripe’ can complicate diagnosis. This artifact is not widely recognized and can mimic severe VHD, leading to potential misdiagnoses. We present two cases where color Doppler stripes mimicked severe VHD, highlighting the need for awareness and accurate interpretation in echocardiographic assessments.Case presentationsCase 1: An 85-year-old patient was referred for mitral valve surgery due to suspected severe mitral regurgitation (MR). Upon evaluation, transthoracic echocardiography (TTE) showed mitral valve prolapse (P3) and a high-echoic, vibrating structure attached to the mitral valve, indicative of chordal rupture. Color Doppler echocardiography revealed strong systolic signals in the left atrium, mimicking severe MR. Transesophageal echocardiography (TEE) also detected the vibrating structure and color Doppler stripes in the left atrium, left ventricle, and outside the cardiac chambers. The PISA method on TEE indicated moderate MR and left ventriculography showed Sellers grade II MR. The artifact was identified as color Doppler stripes caused by the vibrating high-echoic structure from the ruptured chorda. Case 2: A 64-year-old patient with severe aortic stenosis, end-stage kidney disease requiring hemodialysis, and a history of coronary bypass grafting presented for routine follow-up. B-mode echocardiography showed a severely calcified tricuspid aortic valve with a vibrating calcified nodule and restricted opening, corresponding to severe aortic stenosis. During systole, color Doppler signals were observed around the aortic, pulmonary, and tricuspid valves, mimicking significant pulmonary stenosis and tricuspid regurgitation. However, pulmonary stenosis was ruled out as the pulmonary valve opening was normal. Mild tricuspid regurgitation was confirmed in the apical view.ConclusionsThese cases highlight the diagnostic challenges posed by color Doppler stripes. Recognizing and understanding this artifact are crucial for the accurate diagnosis and management of VHD, ensuring appropriate treatment and patient outcomes.

Novel 3-dimensional effective regurgitation orifice area quantification serves as a reliable tool to identify severe mitral valve regurgitation.

A precise quantification of mitral regurgitation (MR) severity is essential for treatment and outcome of patients with MR. 3D echocardiography facilitates estimation of MR but selection of patients with necessity of invasive treatment remains challenging. We investigate effective regurgitation orifice area (EROA) quantification by 3D compared to 2D echocardiography in patients with MR and highlight the improved discrimination of MR severity. We consecutively enrolled fifty patients with primary or secondary and at least moderate MR undergoing 2D and 3D colour Doppler echocardiography prior to transcatheter edge-to-edge repair (TEER). Improved accuracy of MR grading using 3D vena contracta area (VCA) as an estimate of EROA was compared to 2D proximal isovelocity surface area (PISA) quantification method and a multiparameter reference standard. Quantification of EROA remarkably varies between 2D and 3D echocardiography and the discrimination between moderate and severe MR was significantly (p = 0.001) different using 2D PISA or 3D VCA, respectively. 3D VCA correlated significantly (r = 0.501, p < 0.001) better with the pre-defined MR severity. We detected crucial differences in the correct identification of severe MR between 2D and 3D techniques, thus 2D PISA significantly (p < 0.0001) underestimates EROA due to clinical and morphological parameters. The assessment of 3D VCA resulted in improved diagnostic accuracy.

Complete atrioventricular canal in a dog—sounds like a final judgment but is it actually one? A case report

Congenital heart disease (CHD) is an important subset of all cardiovascular diseases in dogs. Among them, there are a number of other less commonly described congenital malformations. One of these is the atrioventricular canal, which involves a defect that has several phenotypes. This report details a case of a complete atrioventricular canal (cAVC) defect. Using Rastelli’s classification scheme, the diagnosis of a type-A cAVC defect was based on two-dimensional, contrast, and color Doppler echocardiography. Despite a severe defect that resulted in the atypical anatomy of the atrioventricular apparatus, as well as significant hemodynamic changes in the heart, the affected dog remained asymptomatic throughout the 48-month follow-up period. Due to its stable clinical condition, the decision was made not to begin pharmacological therapy. As this defect is rare in dogs, there are limited data in the literature on this condition. Therefore, in clinical practice, the management and monitoring of the patient may pose difficulties. Due to such limited data, it can be very difficult to provide a prognosis. For the above reasons, we hope that the following case will contribute valuable information for the monitoring of this kind of CHD.

High-Throughput Deep Learning Detection of Mitral Regurgitation.

Diagnosis of mitral regurgitation (MR) requires careful evaluation by echocardiography with Doppler imaging. This study presents the development and validation of a fully automated deep learning pipeline for identifying apical 4-chamber view videos with color Doppler echocardiography and detecting clinically significant (moderate or severe) MR from transthoracic echocardiograms. A total of 58 614 transthoracic echocardiograms (2 587 538 videos) from Cedars-Sinai Medical Center were used to develop and test an automated pipeline to identify apical 4-chamber view videos with color Doppler across the mitral valve and then assess MR severity. The model was tested internally on a test set of 1800 studies (80 833 videos) from Cedars-Sinai Medical Center and externally evaluated in a geographically distinct cohort of 915 studies (46 890 videos) from Stanford Healthcare. In the held-out Cedars-Sinai Medical Center test set, the view classifier demonstrated an area under the curve (AUC) of 0.998 (0.998-0.999) and correctly identified 3452 of 3539 echocardiography videos as having color Doppler information across the mitral valve (sensitivity of 0.975 [0.968-0.982] and specificity of 0.999 [0.999-0.999] compared with manually curated videos). In the external test cohort from Stanford Healthcare, the view classifier correctly identified 1051 of 1055 manually curated videos with color Doppler information across the mitral valve (sensitivity of 0.996 [0.990-1.000] and specificity of 0.999 [0.999-0.999]). In the Cedars-Sinai Medical Center test cohort, MR moderate or greater in severity was detected with an AUC of 0.916 (0.899-0.932) and severe MR was detected with an AUC of 0.934 (0.913-0.953). In the Stanford Healthcare test cohort, the model detected MR moderate or greater in severity with an AUC of 0.951 (0.924-0.973) and severe MR with an AUC of 0.969 (0.946-0.987). In this study, a novel automated pipeline for identifying clinically significant MR from full transthoracic echocardiography studies demonstrated excellent performance across large numbers of studies and across multiple institutions. Such an approach has the potential for automated screening and surveillance of MR.

Mid-term results of percutaneous transmitral commissurotomy (PTMC) in central iran

Objectives: Percutaneous Trans-Mitral Commissurotomy (PTMC) is an effective non-surgical treatment in patients with severe rheumatic mitral valve stenosis. This study aimed to evaluate the mid-term results of this procedure in central Iran. Methods: This retrospective study was performed on 101 patients with severe mitral valve stenosis who underwent successful PTMC from March 2011 to September 2018 in Afshar Hospital in Yazd. At follow-up, all patients underwent clinical examination, two-dimensional and color Doppler echocardiography, and events were recorded. Data were analyzed using SPSS software version 19. Results: The mean age of the patients was 44.79± 11.72 years, and 83.3% were female. The mean follow-up time was 38.98 23.33 months (6-94 months).25.8% had AF rhythm, and 12% had previous PTMC or OMVC or CMVC. After percutaneous Trans-Mitral Commissurotomy, 97% of patients were in NYHA functional class I, II and the mitral valve area (MVA) increased from 0.92 ± 0.18 to 1.66± 0.29 cm2 (p&lt;0.0001). Pulmonary artery systolic pressure decreased from 46.96± 18.56 mmHg to 38.43±14.02 mmHg (p&lt;0.0001). The Mean mitral valve gradient decreased from 12.37± 3.99 mmHg to 4.79± 2.38 mmHg (p&lt;0.0001). Restenosis rate and severe mitral regurgitation resulting in mitral valve replacement (MVR) were 10.9% and 2%, respectively. Two patients died because of intracranial hemorrhage (ICH). During the follow-up event, free survival was 82.2%. Multivariable analysis revealed that the predictors of shorter event-free survival were AF rhythm (HR; 4.5, 95%CI;1.59-12.9, P=0.005) and post PTMC higher NYHA functional class (HR;2.2, CI;1-4.8,p=0.049). Conclusions: Mid-term results of percutaneous transmitral commissurotomy (PTMC) in central Iran are the same as in other parts of the world. This procedure is an effective and low-risk treatment for severe mitral valve stenosis.

Boosting Cardiac Color Doppler Frame Rates with Deep Learning.

Color Doppler echocardiography enables visualization of blood flow within the heart. However, the limited frame rate impedes the quantitative assessment of blood velocity throughout the cardiac cycle, thereby compromising a comprehensive analysis of ventricular filling. Concurrently, deep learning is demonstrating promising outcomes in post-processing of echocardiographic data for various applications. This work explores the use of deep learning models for intracardiac Doppler velocity estimation from a reduced number of filtered I/Q signals. We used a supervised learning approach by simulating patient-based cardiac color Doppler acquisitions and proposed data augmentation strategies to enlarge the training dataset. We implemented architectures based on convolutional neural networks. In particular, we focused on comparing the U-Net model and the recent ConvNeXt models, alongside assessing real-valued versus complex-valued representations. We found that both models outperformed the state-of-the-art autocorrelator method, effectively mitigating aliasing and noise. We did not observe significant differences between the use of real and complex data. Finally, we validated the models on in vitro and in vivo experiments. All models produced quantitatively comparable results to the baseline and were more robust to noise. ConvNeXt emerged as the sole model to achieve high-quality results on in vivo aliased samples. These results demonstrate the interest of supervised deep learning methods for Doppler velocity estimation from a reduced number of acquisitions.

Quantitative flow ratio for the functional assessment of extracranial internal carotid artery stenosis.

In asymptomatic patients presenting with significant internal carotid artery (ICA) stenoses undergoing endovascular revascularization, a selective angiography before stenting (CAS) is required. Sometimes, angiographic findings could be discordant from non-invasive assessment and a tool able to evaluate functional relevance of the stenosis could be of value. We sought to evaluate the usefulness of quantitative flow ratio (QFR) as angiography-based tool for functional assessment of ICA stenoses. We prospectively enrolled 50 asymptomatic patients undergoing CAS. Peak systolic velocity (PSV, cm/s) assessed at color Doppler echocardiography was used to identify significant stenoses (PSV >125 cm/s). At angiography, assessment of ICA stenosis was obtained visually (%DS<inf>VISUAL</inf>) and according NASCET criteria (%DS<inf>NASCET</inf>). Stenoses were considered significant if >60%. After exclusion of 20 vessels, QFR, area stenosis (AS, %) and minimal lumen area (MLA, mm2) were obtained in the remaining 80 vessels. At linear regression analysis, QFR significantly correlated with PSV (r2=0.52, P<0.001) as well as with %DS<inf>NASCET</inf> (r2=0.68, P<0.001) and %DS<inf>VISUAL</inf> (r2=0.71, P<0.001). Using PSV as reference, QFR showed good accuracy to predict functionally significant stenosis (AUC=0.98, P<0.001) with a cut-off value of 0.93. As compared with %DS<inf>NASCET</inf> and %DS<inf>VISUAL</inf>, QFR showed a significantly higher accuracy (61% vs. 73% vs. 94%, respectively; P<0.05), sensitivity (43% vs. 61% vs. 93%, respectively; P<0.05) and negative predictive value (46% vs. 51% vs. 85%, respectively; P<0.05) for detecting hemodynamically significant ICA stenoses. This study suggest the potential benefit of adopting QFR for functional assessment of extracranial ICA stenoses. These data should be validated in larger studies.

Congenital Heart Defects in Pregnancies Conceived by Assisted Reproductive Technology: Comparing Functional and Structural Defects.

Introduction Congenital heart defects (CHD) are one of the most common congenital anomalies, and their association with assisted reproductive technology (ART) is controversial in different populations. The purpose of this study was to evaluate this association and to provide information about the necessity of specialized echocardiography during pregnancy with ART. Methods This retrospective study was performed on all pregnancies conceived by ART and referred for fetal echocardiography to the Rasoul Akram and Akbar Abadi hospitalsin Tehran, Iran. A total of 109 patients were enrolled in the study (56 in the ART group and 53 in the non-ART). Two-dimensional and color Doppler echocardiography were performed on all patients to identify heart problems and anomalies and medical records of the patients were reviewed. The outcome was considered the presence of functional and structural heart defects on echocardiography. Results The study groups were similar in terms of maternal age and GA.The ART group consisted of 31 singletons (55%) and 25 multiples (45%). All pregnancies in the non-ART group were singletons. Following in vitro fertilization (33%), ovulation induction (25%) was the next most used method. The findings of echocardiography were one atrial septal defect (ASD) in ART and one in non-ART, six ventricular septal defects (VSD) in ART and three in non-ART, and one ASD and VSD in the ART group. These structural abnormalities showed no difference in the two groups (P value = 0.58). There was no significant difference in rhythm between the two groups (P = 0.51). Echocardiographic indices of both groups did not differ statistically except in the TR-PG index (P value = 0.02). Conclusions The structural defects of the two groups were not different, and no heart dysfunction was observed in ART fetuses. There was no association between ART and CHD in our study. We concluded that echocardiography by pediatric cardiologists is not necessary for these fetuses.

Clinical characteristics of congenital heart defects in mild congenital anorectal malformation: single-centre experience

ObjectiveTo analyze the clinical characteristics and types of congenital heart defect (CHD) in mild congenital anorectal malformation (CARM), namely the rectoperineal and rectovestibular fistulas.MethodsThe retrospective study of 183 patients with mild CARM was conducted with assessments of demographic information, color Doppler echocardiography results, and follow-up data. We performed an analysis of the clinical characteristics of CHD, grouping them based on sex and type of mild CARM.ResultsOf the 183 patients, rectoperineal fistula occurred in 133 patients (72.7%), while the frequency of CHD was 79.8% (146/183). Ventricular septal defects (VSDs) occur more frequently in patients with rectoperineal fistula compared to those with rectovestibular fistula (1.5% vs. 10%), while the opposite trend was observed for patent ductus arteriosus (PDAs) (39.8% vs. 22.0%). Additionally, males presented higher frequency of PDA (42.7% vs. 26.4%) and self-healing (6 months: 87.2% vs. 42.6%; 12 months: 91.0% vs. 63.2%) than females. However, males had a lower rate of undergoing cardiac surgery (6.4% vs. 17.6%) and a younger median diagnosis age (1 day vs. 9 days).ConclusionOur study indicates that there is a necessity for meticulous cardiac assessment and follow-up in neonates diagnosed with mild CARM.

Abnormal aortic origin of coronary arteries

The anomalous aortic origin of the coronary arteries has an estimated prevalence of 0.02-5.7%. It can be associated with sudden death when it has an interarterial or intramural pathway or be damaged during interventions on the mitral, pulmonary and/or aortic annulus or percutaneous closure of an interatrial septal defect. To identify these patients by imaging techniques such as transthoracic color Doppler echocardiography (TTE), computed tomography (CT) multislice angiography or coronary angiography. The imaging techniques used for the detection of coronary anomalies were TTE, multislice coronary angiography or coronary angiography according to what is generally accepted. Fifteen patients were identified; in 12 of them the suspicion was due to TTE and in the remaining 3, CT multislice angiography was diagnostic. The circumflex artery was the coronary artery most involved, associated or not with another coronary anomaly (12/15 patients) and in the other three cases, the anomalous coronary artery had an interarterial course, with the right coronary arteries and the anterior descending coronary arteries being involved. The under diagnosis by TTE of coronary artery abnormalities may be due to the difficulty of visualization that is accentuated with age. Their detection is crucial because they can both, lead to sudden death associated with an intramural and/or interarterial pathway and complicate an interventional procedure on the interatrial septum or within the mitral, pulmonary and/or aortic rings.

Adult-type anomalous origin of the left coronary artery from the pulmonary artery and right coronary-right atrial fistula: a case report

BackgroundAnomalous origin of the left coronary artery from the pulmonary artery (ALCAPA) is a rare congenital cardiac anomaly, mortality rates in infancy reach approximately 90%, with only a small number of patients surviving into adulthood, therefore, most of the literature reports mainly focus on infantile type.Case presentationA 55-year-old female was admitted due to persistent repeated chest pain experienced and had worsened for unknown reasons. Color doppler echocardiography, coronary computed tomographic angiography, and coronary angiography confirmed the diagnosis of ALCAPA and concurrent right coronary artery-right atrial fistula. The symptoms of chest pain exhibited notable improvement subsequent to corrective surgery for the anomalous origin of the coronary artery.ConclusionsThis report shows an unique case of ALCAPA in an adult patient, characterizing the condition’s combination with a right coronary-right atrial fistula, and it is prone to misdiagnosis and misdiagnosis. We aim to provide valuable insights for clinical diagnosis and treatment of ALCAPA.

Assessing Intracardiac Vortices with High Frame-Rate Echocardiography-Derived Blood Speckle Imaging in Newborns.

The left ventricle (LV) has a unique pattern of hemodynamic filling. During diastole, a rotational body or ring of fluid known as a vortex is formed due to the chiral geometry of the heart. A vortex is reported to have a role in conserving the kinetic energy of blood flow entering into the LV. Recent studies have shown that LV vortices may have prognostic value in describing diastolic function at rest in neonatal, pediatric, and adult populations, and may help with earlier subclinical intervention. However, the visualization and characterization of the vortex remain minimally explored. A number of imaging modalities have been utilized for visualizing and describing intracardiac blood flow patterns and vortex rings. In this article, a technique known as blood speckle imaging (BSI) is of particular interest. BSI is derived from high-frame rate color Doppler echocardiography and provides several advantages over other modalities. Namely, BSI is an inexpensive and noninvasive bedside tool that does not rely on contrast agents or extensive mathematical assumptions. This work presents a detailed step-by-step application of the BSI methodology used in our laboratory. The clinical utility of BSI is still in its early stages, but has shown promise within the pediatric and neonatal populations for describing diastolic function in volume-overloaded hearts. A secondary aim of this study is thus to discuss recent and future clinical work with this imaging technology.

Pleiotropic effects of hyaluronic acid and silver sulfadiazine dressings in the treatment of acute and chronic skin lesions.

Hyaluronic acid (HA) is a natural unbranched polymer that belongs to a group of heteropolysaccharide glycosaminoglycans (GAGs) that are major components of the extracellular matrix (ECM), while silver sulfadiazine exerts antibacterial activity. In this study, we evaluated the efficacy and safety of dressings with hyaluronic acid and silver sulfadiazine in acute and chronic lesions, according to the wound bed preparation and TIME principles. Thirty-two patients with acute and chronic injuries participated in the study. After collecting their personal histories and making a differential diagnosis by evaluating their ankle/arm index, patients with a Winsor Index below 0.8 underwent lower extremity color Doppler echocardiography. The dressing protocol followed the principles of wound bed preparation, identifying the prevailing clinical sign by evaluating the lesion background, margins, and perilesional skin. A product containing low molecular weight hyaluronic acid (200 kDa) and silver sulfadiazine 1% was used for the dressing. In the acute lesion group, the protocol we applied resulted in all injuries being healed. Of the 20 treated wounds in the chronic lesion group, 10 healed at the end of 8 weeks of treatment and 8 saw an improvement with a reduction in the lesion area. Consisting of a combination of hyaluronic acid and silver sulfadiazine, the dressing is widely used in the management of acute and chronic skin wounds. In the present study, the healing rate of acute wounds was 100%; in chronic wounds, healing was reported in 50% of cases while in 40% of the remainder, we found a 40% reduction in the lesion area.

Automatic Segmentation and Assessment of Valvular Regurgitations with Color Doppler Echocardiography Images: A VABC-UNet-Based Framework.

This study investigated the automatic segmentation and classification of mitral regurgitation (MR) and tricuspid regurgitation (TR) using a deep learning-based method, aiming to improve the efficiency and accuracy of diagnosis of valvular regurgitations. A VABC-UNet model was proposed consisting of VGG16 encoder, U-Net decoder, batch normalization, attention block and deepened convolution layer based on the U-Net backbone. Then, a VABC-UNet-based assessment framework was established for automatic segmentation, classification, and evaluation of valvular regurgitations. A total of 315 color Doppler echocardiography images of MR and/or TR in an apical four-chamber view were collected, including 35 images in the test dataset and 280 images in the training dataset. In comparison with the classic U-Net and VGG16-UNet models, the segmentation performance of the VABC-UNet model was evaluated via four metrics: Dice, Jaccard, Precision, and Recall. According to the features of regurgitation jet and atrium, the regurgitation could automatically be classified into MR or TR, and evaluated to mild, moderate, moderate-severe, or severe grade by the framework. The results show that the VABC-UNet model has a superior performance in the segmentation of valvular regurgitation jets and atria to the other two models and consequently a higher accuracy of classification and evaluation. There were fewer pseudo- and over-segmentations by the VABC-UNet model and the values of the metrics significantly improved (p < 0.05). The proposed VABC-UNet-based framework achieves automatic segmentation, classification, and evaluation of MR and TR, having potential to assist radiologists in clinical decision making of the regurgitations in valvular heart diseases.

Značaj trikuspidalne regurgitacije i velicine desne pretkomore kod bolesnika sa umerenim i teskim stepenom hobp

Introduction: Chronic obstructive pulmonary disease (COPD) is one of the leading causes of death in the world. The Republic of Serbia, with over half a million sufferers (4.2% of the population), belongs to the group of countries with the most frequent incidence of this disease. Due to increased resistance in the airways and pulmonary circulation, pulmonary hypertension, cor pulmonale chronicum and right and left ventricular dysfunction develop over time. OBJECTIVE: To determine the frequency and significance of tricuspid regurgitation as well as the size of the right atrium in relation to the degree of COPD. Methodology: Characteristic changes of the tricuspid valvular apparatus are assessed by Color Doppler echocardiography in a two-dimensional view. This study included 70 patients with chronic obstructive pulmonary disease. The study included 48 patients out of the initial 70 (68.57%), who were selected as patients diagnosed with tricuspid regurgitation on echocardiographic examination. They were divided into four g holes according to the GOLD criteria and there were 12 subjects in each group. Results: Kruskal-Wallis showed that there is a significant difference for FEV1 among all groups (p=0.05), except for FEV1 values between the third and fourth groups. According to the Kruskal-Wallis test, there is a statistically significant difference for the frequency of TR in mild versus moderate and severe COPD. There were significant differences for TR between moderate and severe COPD disease (p&lt;0.05). By comparing the values of the right atrium, there is no statistical significance for the values of the right atrium among the groups of patients with COPD (p&gt;0.05). Conclusion: In order to timely detect and prevent the cardiac complications of COPD, all patients should undergo color doppler echocardiography in a certain period of time

Congenital heart disease in the resolving polyclinic of children’s cardiology at the Hospital del Niño “Dr. Ovidio Aliaga Uría” at 3.650 masl

Introduction: Congenital malformations are the leading cause of early neonatal mortality and the second leading cause of infant mortality. Among them, congenital heart diseases are the main cause of mortality in the early neonatal period. Material and methods: A prospective cross-sectional study was conducted at the "Dr. Ovidio Aliaga Uría" Children's Hospital in La Paz, Bolivia, at an altitude of 3,650 masl. A pediatric cardiology outpatient clinic was set up to examine 42 children, recording clinical data, physical examination, and color Doppler echocardiography. Results: The most frequent reason for referral was a heart murmur. In 52.38% (n=22) of the evaluated patients, congenital heart disease was present, with ventricular septal defects being the most common at 40.91% (n=9), followed by atrial septal defects at 18.18% (n=4), persistent foramen ovale at 13.64% (n=3), and patent ductus arteriosus at 9.09% (n=2) of patients. Discussion: There are very few studies in populations living at altitudes above 3,000 masl. Our study shows a high percentage of children with cardiac defects, which may be attributed to accurate diagnosis at referral or possibly a higher incidence of cardiac malformations in the studied population. Conclusion: the most common cardiac defect was ventricular septal defect, as described in populations living at sea level.

Phase Unwrapping of Color Doppler Echocardiography using Deep Learning.

Color Doppler echocardiography is a widely used non-invasive imaging modality that provides real-time information about the intracardiac blood flow. In an apical long-axis view of the left ventricle, color Doppler is subject to phase wrapping, or aliasing, especially during cardiac filling and ejection. When setting up quantitative methods based on color Doppler, it is necessary to correct this wrapping artifact. We developed an unfolded primal-dual network to unwrap (dealias) color Doppler echocardiographic images and compared its effectiveness against two state-of-the-art segmentation approaches based on nnU-Net and transformer models. We trained and evaluated the performance of each method on an in-house dataset and found that the nnU-Net-based method provided the best dealiased results, followed by the primal-dual approach and the transformer-based technique. Noteworthy, the primal-dual network, which had significantly fewer trainable parameters, performed competitively with respect to the other two methods, demonstrating the high potential of deep unfolding methods. Our results suggest that deep learning-based methods can effectively remove aliasing artifacts in color Doppler echocardiographic images, outperforming DeAN, a state-of-the-art semi-automatic technique. Overall, our results show that deep learning-based methods have the potential to effectively preprocess color Doppler images for downstream quantitative analysis.

Automated Identification of Patent Ductus Arteriosus Using a Computer Vision Model.

Patent ductus arteriosus (PDA) is a vascular defect common in preterm infants and often requires treatment to avoid associated long-term morbidities. Echocardiography is the primary tool used to diagnose and monitor PDA. We trained a deep learning model to identify PDA presence in relevant echocardiographic images. Echocardiography video clips (n = 2527) in preterm infants were reviewed by a pediatric cardiologist and those relevant to PDA diagnosis were selected and labeled (PDA present/absent/indeterminate). We trained a convolutional neural network to classify each echocardiography frame of a clip as belonging to clips with or without PDA. A novel attention mechanism that aggregated predictions for all frames in each clip to obtain a clip-level prediction by weighting relevant frames. In early model iterations, we discovered training with color Doppler echocardiography clips produced the best performing classifier. For model training and validation, 1145 such clips from 66 patients (661 PDA+ clips, 484 PDA- clips) were used. Our best classifier for clip level performance obtained sensitivity of 0.80 (0.83-0.90), specificity of 0.77 (0.62-0.92) and AUC of 0.86 (0.83-0.90). Study level performance obtained sensitivity of 0.83 (0.72-0.94), specificity of 0.89 (0.79-1.0) and AUC of 0.93 (0.89-0.98). Our novel deep learning model demonstrated strong performance in classifying echocardiography clips with and without PDA. Further model development and external validation are warranted. Ultimately, integration of such a classifier into auto detection software could streamline PDA imaging workflow. This work is the first step toward semi-automated, bedside detection of PDA in preterm infants.