Automatic computation of Left Ventricular Performance from ultrasound
Heart failure poses a significant global public health challenge, and early detection and treatment are vital for preventing disease progression and alleviating the burden on healthcare systems. Echocardiography, a non-invasive and patient-friendly imaging technique, is widely utilized as the primary method for evaluating cardiac structure and function in diagnosing heart failure. However, the interpretation of echocardiograms often requires specialized expertise, leading to limited accessibility.
Recent advancements in deep learning have opened up possibilities for automating the analysis of medical images. While previous attempts at automating echocardiogram interpretation have primarily focused on identifying specific views or quantifying systolic function, they have not included external validation in patients with abnormal findings. This approach overlooks the fact that more than half of heart failure patients exhibit mid-range or preserved ejection fraction (HFpEF), making the assessment of diastolic function essential across various cardiac disease states. Diagnosing HFpEF is particularly challenging and relies on identifying structural and functional changes associated with elevated left ventricular filling pressure, in addition to clinical evaluation.
Therefore, there is a critical need for a fully automated workflow that can comprehensively assess both systolic and diastolic function parameters in echocardiograms. Such a workflow would address the current gap in automated analysis and provide a more holistic evaluation of cardiac function in heart failure patients. By leveraging deep learning techniques, this automated approach has the potential to improve accessibility, expedite diagnosis, and support more effective management strategies for heart failure patients.
AINIGMA Technologies have created an automated deep learning workflow to classify, segment, and annotate two-dimensional (2D) videos and Doppler modalities in echocardiograms. This workflow aims to replace the time-consuming and error-prone manual interpretation of echocardiograms, which is currently used to assess cardiac systolic and diastolic function for heart failure diagnosis and management.
Technologies we use:
