Upon training a machine learning model to analyze ultrasound images of the neck, researchers tested their algorithm and have found it correctly flagged likely cancerous nodules of the thyroid gland at a 97% clip.

The study yielded a malignancy rate of 8.4% for the women who presented for routine pelvic ultrasound without prior suspicion for adnexal lesions.

Testing AI’s ability to detect carotid artery disease on ultrasound, U.K. researchers have found their algorithm achieved 90% accuracy, along with 87% sensitivity and 82% specificity, at the task.

The comprehensive approach may be warranted for patients whose musculoskeletal injuries include fractures of the costal cartilage. 

Artificial intelligence vendor DiA has emerged as a key third-party provider of AI to larger imaging vendors.

Two European studies illustrate opportunities and challenges presented by the growing appeal of point-of-care ultrasound to primary care practices.  

The new technique is still in the development stage, but early research suggests it could provide clinicians with a new treatment option for breaking down arterial plaque. 

Using point-of-care ultrasound in emergency settings does not lead to overutilization of follow-up imaging with cross-sectional CT, MRI or additional ultrasounds.