FDA OKs Butterfly Network’s AI-Enabled Auto B-Line Counter

Butterfly Network, the digital health firm transforming care with its handheld, whole-body ultrasound, has earned U.S. Food and Drug Administration (FDA) 510(k) clearance for an artificial intelligence (AI)-enabled Auto B-line Counter, which may simplify how clinicians evaluate adults with suspected diminished lung function.
 
The Auto B-line Counter uses deep learning tech to generate a B-line count from a six second ultrasound clip—a change from manual, subjective counting processes. B-lines on an ultrasound scan show up as bright, vertical lines that indicate wetness in the lungs and are associated with pulmonary air-space disease, pneumonia, and COVID-19.
 
“Our goal at Butterfly is to give healthcare practitioners, and eventually consumers, a real time full color, annotated, window into the human body. Applying AI to make ultrasound easier to use is core to Butterfly, and will enable powerful ultrasound to be in the palm of more clinician’s hands, across specialities, to monitor, assess, and prescribe treatments in a more informed way,” Dr. Jonathan Rothberg, Butterfly Network’s founder and interim CEO, told the press. “Our AI-enabled Auto B-line Counter empowers providers to assess lung conditions faster and with more confidence—and in turn, will aid in earlier detection, diagnosis, and treatment of cardiovascular diseases, a leading cause of death globally, taking nearly 18 million lives each year.”
 
The Auto B-line Counter algorithm uses an instant percent counting method that assigns numbers to confluent B-lines by the percentage of rib space occupied and counts discrete B-lines. Using the tech, trained providers can place the probe and receive a reliable number count on their screen.