Quantitative assessment of pericardial effusion volume by two-dimensional echocardiography

Development and validation of a deep learning pipeline to measure pericardial effusion in echocardiography

Objectives

The aim of this study was to develop a deep-learning pipeline for the measurement of pericardial effusion (PE) based on raw echocardiography clips, as current methods for PE measurement can be operator-dependent and present challenges in certain situations.

Methods

The proposed pipeline consisted of three distinct steps: moving window view selection (MWVS), automated segmentation, and width calculation from a segmented mask. The MWVS model utilized the ResNet architecture to classify each frame of the extracted raw echocardiography files into selected view types. The automated segmentation step then generated a mask for the PE area from the extracted echocardiography clip, and a computer vision technique was used to calculate the largest width of the PE from the segmented mask. The pipeline was applied to a total of 995 echocardiographic examinations.

Results

The proposed deep-learning pipeline exhibited high performance, as evidenced by intraclass correlation coefficient (ICC) values of 0.867 for internal validation and 0.801 for external validation. The pipeline demonstrated a high level of accuracy in detecting PE, with an area under the receiving operating characteristic curve (AUC) of 0.926 (95% CI: 0.902-0.951) for internal validation and 0.842 (95% CI: 0.794-0.889) for external validation.

Conclusion

The machine-learning pipeline developed in this study can automatically calculate the width of PE from raw ultrasound clips. The novel concepts of moving window view selection for image quality control and computer vision techniques for maximal PE width calculation seem useful in the field of ultrasound. This pipeline could potentially provide a standardized and objective approach to the measurement of PE, reducing operator-dependency and improving accuracy.

Circulating lipid and lipoprotein profiles and their correlation to cardiac function and cardiovascular outcomes in patients with acute myocardial infarction

Recent studies showed that lipoproteins represent major risk factors, both positive and negative, for atherosclerotic cardiovascular disease. The aim of the present study was to describe the relationship between plasma lipid profile and cardiac function and cardiovascular outcomes in patients with acute myocardial infarction (AMI) after percutaneous coronary intervention (PCI). Two independent groups of subjects including a total of 797 patients diagnosed of AMI undergoing PCI admitted to the First Affiliated Hospital of Xi’an Jiaotong University were included in the present study. We performed a cross-sectional study for the correlation between plasma lipid profile and cardiac function based on the first group, including 503 patients with AMI. We further validated the correlation and did the follow-up of 2.4 years of major cardiovascular outcomes on the second group, including 294 patients with AMI. Our results showed that apolipoprotein A-I (ApoA-I) level was significantly reduced, and the high-density lipoprotein cholesterol (HDL-C):ApoA-I ratio was increased in the patients with lower LVEF or higher N-terminal pro-B-type natriuretic peptide levels compared with the control; there was a positive correlation between cardiac function and ApoA-I, and a negative correlation between cardiac function and the HDL-C:ApoA-I ratio. Meanwhile, multivariate Cox analysis showed that ApoA-I was independent predictors of major adverse cardiovascular events (MACEs). Kaplan-Meier survival analysis showed the ApoA-I levels exhibited a significant effect on predicting the incidence of MACEs. In sum, plasma ApoA-I level is positively associated with the cardiac function of patients with AMI after PCI, and ApoA-I is an independent indicator to predict the incidence of MACEs.

Transient Marked Myocardial Thickening after Reperfused Myocardial Infarction Causing Refractory Heart Failure

•

Modest LV wall thickening is a common phenomenon after reperfusion therapy.

•

Wall thickening may be due to myocardial interstitial edema and/or hemorrhage.

•

Marked left ventricular wall thickening can reduce SV.

•

MI is difficult to treat when SV is decreased during the acute phase.

The Biplane Modified Simpson's Method Accurately Estimates Pericardial Effusion Volume: A Comparison with Pericardiocentesis

BACKGROUND

Pericardial effusion (PE) volume is often assessed semiqualitatively by echocardiography and categorized into minimal, small, moderate, or large. Several methods of echocardiographic quantification have been proposed, but their application is limited either by complexity or inaccuracy. We evaluated the accuracy of PE volume quantification by two-dimensional transthoracic echocardiogram (2DTTE) and commercially available volume quantification software in patients undergoing pericardiocentesis.

METHODS

In a retrospective case series, immediate preprocedure echocardiograms of 33 patients for pericardiocentesis were analyzed. 2DTTE using the Simpson's method was adopted for volume measurement in the apical two- and four-chamber views. Pericardial fluid volume was calculated by taking the difference between volumes obtained by tracing the epicardial border of the heart and the pericardium. Postprocedure echocardiograms were performed to verify adequate pericardiocentesis.

RESULTS

The mean pericardiocentesis fluid volume was 725.1 ± 299.5 mL (range, 250-1420 mL). The average volume estimated echocardiographically by the Simpson's method was 657.5 ± 276.9 mL (range, 205.7-1193.2 mL). There was strong direct linear correlation between echocardiographic and pericardiocentesis-derived volumes (P < 0.001, r = +0.823). Echocardiography underestimated PE volume by a mean of 9.3%.

CONCLUSION

Two-dimensional transthoracic echocardiography using biplane Simpson's method of disks can simply and accurately estimate PE volume.