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.

A case report and review of literature: Tuberculous pericarditis with pericardial effusion as the only clinical manifestation

Tuberculosis is a main cause of pericardial disease in developing countries. However, in patients with atypical clinical presentation, it can lead to misdiagnosis, missed diagnosis, and delayed treatment. In this study, we report a case of a 61-year-old woman admitted to the cardiac intensive care unit with "weakness and loss of appetite" and a large pericardial effusion shown by echocardiography. After hospitalization, a pericardiocentesis was performed, and the pericardial fluid was hemorrhagic. However, the Xpert MTB/RIF and T-SPOT tests were negative, and repeated phlegm antacid smears and culture of pericardial fluid did not reveal antacid bacilli. The patient eventually underwent thoracoscopic pericardial biopsy, which revealed extensive inflammatory cells and significant granulomas. Combined with the fact that the patient's pericardial effusion was exudate, the patient was considered to be suspected of tuberculous pericarditis (TBP) and given empirical anti-tuberculosis treatment the patient's symptoms improved and the final diagnosis was TBP. In this case report, it is further shown that a negative laboratory test cannot exclude tuberculosis infection. In recurrent unexplained pericardial effusions, the pericardial biopsy is feasible. In countries with a high burden of tuberculosis, empirical antituberculosis therapy may be used to treat the pericardial effusion that excludes other possible factors.

Pediatric Lupus Presenting as Pulmonary Hypertension, Myocarditis, and Massive Pericardial Effusion in an 11-Year-Old Girl: A Case Report and Literature Review

Systemic lupus erythematosus (SLE) is an autoimmune disease that may cause vital organ damage. Although not rare for child-onset SLE to have cardiovascular or pulmonary involvement, myocarditis, and pulmonary hypertension are infrequent features and can be life-threatening. In this case report, we describe an 11-year-old girl with SLE who initially presented with fulminant myocarditis pulmonary hypertension, and massive pericardial effusion. Initial immunosuppressive therapy with methylprednisolone pulse therapy, and IVIG were administered, followed by cyclophosphamide, which was ultimately successful, with no residual pulmonary hypertension and no recurrence of myocarditis for over 3 years after the initial episode. Our case highlights the need for clinicians to be aware of systemic lupus erythematosus as a possible diagnostic entity in pediatric patients with severe myocarditis or pulmonary hypertension. Aggressive immunosuppressive therapy should be strongly considered in such cases, as it may lead to good short-term and long-term outcomes.