Echo-CV is a novel, fully-automated system for analyzing images obtained from an echocardiogram that can be deployed on the web.
Echocardiography is one of the most widely used diagnostic tests in cardiology. It is routinely used in the diagnosis of heart diseases including Atherosclerosis, Amyloidosis, Aneurysm, Cardiomyopathy, Congenital heart disease, Heart failure, Left ventricular hypertrophy, Pericarditis and Valvular heart disease. It can provide a wealth of information to the physicians including the size and shape of the heart, pumping capacity, location and extent of any tissue damage, cardiac function tests including the cardiac output, ejection fraction and diastolic function.
Traditionally, echocardiograms are interpreted by cardiologists. Automated echocardiogram interpretation system has the potential to transform clinical practice in multiple ways including enabling low-cost serial assessment of cardiac function by non-experts in primary care and rural settings for targeted disease detection. It can significantly streamline the process to facilitate quantification of cardiac function in clinical trial settings as well as in hospitals. This technology fulfills an unmet need of the cardiac disease diagnosis industry, physicians and patients alike.
ADVANTAGES OF THE TECHNOLOGY:
Researchers at University of California, San Francisco have developed a software platform for automated analysis of echocardiograms that require no user intervention and thus can be deployed on high-performance computing cluster or web application. The echo video is preprocessed by automatically extracting metadata, convolutional neural networks are used for identifying views as well as image segmentation to calculate various structural and functional parameters for focused disease diagnosis.
To develop & commercialize the technology for expanding cardiac disease diagnosis using the automated echocardiogram interpretation platform.
Proof of Concept
Proof of Principle
|Patent Cooperation Treaty||Published Application||WO2019178404||09/19/2019||2018-046|