Some 81% of the models—70 of 86 DL algorithms reported in 83 separate studies—diminished at least somewhat in diagnostic accuracy compared with their accuracy on internal datasets.

Competing to classify thyroid nodules on ultrasound images as either malignant or benign, three deep learning models have essentially drawn a tie with four radiologists.

Mayo Clinic researchers have demonstrated a deep learning model that can automatically segment kidneys and measure total kidney volumes using only 3D ultrasound images.

Deep learning has bested experienced neurosurgeons at predicting poor outcomes, including mortality, among patients admitted comatose with severe traumatic brain injuries.

Physicians may not be aware of such devices' intended use, with potential for misdiagnosis resulting in patient injury or death, the agency announced. 

Now valued at $1.2B, the San Francisco startup was co-founded by a neurosurgeon and offers a suite of solutions for diagnosing diseases from medical images. 

This marks the ninth 510(k) clearance for the company, which has offices in Israel and New York, and second in the past 10 days. 

Only 10% of such scans reveal positive findings for TBI, raising concerns about overuse and radiation exposure among children, experts wrote in JACR.