AI-Enabled Lung Assessment Tool for Handheld Ultrasound Gets FDA Nod
The artificial intelligence (AI) powered Auto B-line Counter, which reportedly produces a B-line count from a six-second ultrasound clip, may facilitate more expedient and consistent assessment of abnormal lung function.
The Food and Drug Administration (FDA) has granted 510(k) clearance for the Auto B-line Counter (Butterfly Network), a handheld ultrasound tool that may help accelerate assessment of suspected lung function abnormality in patients with conditions ranging from chronic obstructive pulmonary disease (COPD) to COVID-19.
In contrast to traditional manual processes for counting B-lines from lung ultrasound scans, the Auto B-line Counter utilizes deep learning technology that can provide a B-line count from a six-second ultrasound clip, according to the Butterfly Network, the manufacturer of the modality.
Incorporating an instant percent counting technique, Butterfly Network said the algorithm for the Auto B-line Counter accounts for discrete B-lines as well as confluent B-lines by the percentage of occupied rib space.
“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,” noted Jonathan Rothberg, Ph.D., the founder and interim chief executive officer of Butterfly Network.
The Reading Room: Artificial Intelligence: What RSNA 2020 Offered, and What 2021 Could Bring
December 5th 2020Nina Kottler, M.D., chief medical officer of AI at Radiology Partners, discusses, during RSNA 2020, what new developments the annual meeting provided about these technologies, sessions to access, and what to expect in the coming year.
AI-Initiated Recalls After Screening Mammography Demonstrate Higher PPV for Breast Cancer
March 18th 2025While recalls initiated by one of two reviewing radiologists after screening mammography were nearly 10 percent higher than recalls initiated by an AI software, the AI-initiated recalls had an 85 percent higher positive predictive value for breast cancer, according to a new study.
