FDA clears AI technology that evaluates echocardiograms
Software from Bay Labs incorporates deep learning and analytics into its analysis, says Charles Cadieu.
A medical technology company specializing in applying artificial intelligence to cardiovascular imaging has received clearance from the Food and Drug Administration for its fully automated video clip selection and calculation of left ventricular ejection fraction.
The software from San Francisco-based Bay Labs—which can be integrated into any DICOM PACS medical imaging environment—is expected to improve cardiovascular disease management and patient outcomes through earlier detection and monitoring, according to Charles Cadieu, co-founder and CEO of the company.
Ejection fraction (EF) is a measurement of the percentage of blood that the heart pumps out when it contracts. It is the most widely used metric of cardiac function from echocardiograms and is used as the basis for many clinical decisions.
Bay Labs received 510(k)clearance for its EchoMD AutoER software product, which eliminates the need to manually select views, choose the best video clips and manipulate them for quantification. These manual processes are often time consuming and variable.
In contrast, the EchoMD AutoEF automatically reviews all of the relevant digital video clips of cardiac cycles from a patient’s echocardiogram study, rates them according to image quality, and selects the best ones to calculate the EF. The algorithm learned clip selection and EF calculation after being trained on a dataset of over 4 million images representing 9,000 patients.
The technology, which Cadieu says is the first of its kind, also uses deep learning to produce automated estimates of EF and uses the entire image, not just the borders of the ventricle. It additionally provides to the clinician an estimate of confidence of the algorithm for that particular patient, he adds.
Also See: FDA clears AI-based system to detect diabetic retinopathy
“Left ventricular ejection fraction has been a mainstay of echocardiography for the last 50 years. Bay Labs’ use of artificial intelligence for image selection and automated EF measurement will allow clinicians across a wide range of experience to obtain accurate evaluation of ventricular function and aid in interpretation of the echocardiograms with greater efficiency,” says Neil J. Weissman, MD, chief scientific officer for MedStar Health in Washington and a professor of medicine at Georgetown University School of Medicine. Weissman was an unbiased adjudicator and reviewer of the technology, says Cadieu.
There are more than 10 million echocardiograms performed a year in the United States. Over 600,000 people in the country die from cardiovascular disease annually.
“We’re seeing a really good response form hospitals and health systems [about our software]. Each [echocardiogram] needs this measurement. It’s critical for understanding cardiac function and the system of the heart. This [technology] can have a dramatic impact,” says Cadieu.
This is Bay Lab’s first FDA clearance; other software products are in process.
“Our hope is that EchoMD AutoEF will assist cardiologists in their decision making and enhance the care they provide to their patients. We look forward to continuing to develop unique deep learning technologies that enable expanded access to high-quality echocardiography image acquisition and interpretation, with the goal to improve disease management and patient outcomes through earlier detection and monitoring,” he says.
The software from San Francisco-based Bay Labs—which can be integrated into any DICOM PACS medical imaging environment—is expected to improve cardiovascular disease management and patient outcomes through earlier detection and monitoring, according to Charles Cadieu, co-founder and CEO of the company.
Ejection fraction (EF) is a measurement of the percentage of blood that the heart pumps out when it contracts. It is the most widely used metric of cardiac function from echocardiograms and is used as the basis for many clinical decisions.
Bay Labs received 510(k)clearance for its EchoMD AutoER software product, which eliminates the need to manually select views, choose the best video clips and manipulate them for quantification. These manual processes are often time consuming and variable.
In contrast, the EchoMD AutoEF automatically reviews all of the relevant digital video clips of cardiac cycles from a patient’s echocardiogram study, rates them according to image quality, and selects the best ones to calculate the EF. The algorithm learned clip selection and EF calculation after being trained on a dataset of over 4 million images representing 9,000 patients.
The technology, which Cadieu says is the first of its kind, also uses deep learning to produce automated estimates of EF and uses the entire image, not just the borders of the ventricle. It additionally provides to the clinician an estimate of confidence of the algorithm for that particular patient, he adds.
Also See: FDA clears AI-based system to detect diabetic retinopathy
“Left ventricular ejection fraction has been a mainstay of echocardiography for the last 50 years. Bay Labs’ use of artificial intelligence for image selection and automated EF measurement will allow clinicians across a wide range of experience to obtain accurate evaluation of ventricular function and aid in interpretation of the echocardiograms with greater efficiency,” says Neil J. Weissman, MD, chief scientific officer for MedStar Health in Washington and a professor of medicine at Georgetown University School of Medicine. Weissman was an unbiased adjudicator and reviewer of the technology, says Cadieu. There are more than 10 million echocardiograms performed a year in the United States. Over 600,000 people in the country die from cardiovascular disease annually.
“We’re seeing a really good response form hospitals and health systems [about our software]. Each [echocardiogram] needs this measurement. It’s critical for understanding cardiac function and the system of the heart. This [technology] can have a dramatic impact,” says Cadieu.
This is Bay Lab’s first FDA clearance; other software products are in process.
“Our hope is that EchoMD AutoEF will assist cardiologists in their decision making and enhance the care they provide to their patients. We look forward to continuing to develop unique deep learning technologies that enable expanded access to high-quality echocardiography image acquisition and interpretation, with the goal to improve disease management and patient outcomes through earlier detection and monitoring,” he says.
More for you
Loading data for hdm_tax_topic #better-outcomes...