The generated report included indication, findings laid out numerically, TNM stage, impression and follow-up recommendations.

The findings contradict prior research that utilized the same software, experts involved in the research noted. This could be due to out-of-distribution data for the DL software, which could impair its performance. 

Cardiology has the second largest number of FDA-cleared AI algorithms, and many of them are for cardiac ultrasound. Echocardiography expert Patricia A. Pellikka, MD, discusses this trend and how AI is helping improve echo.

The use of synthetic images could reduce the amount of gadolinium-based contrast agents needed for breast MRI examinations, according to new data published this week in Radiology. 

The continued emergence of natural language processing has caught the eye of experts in the field, with some suggesting its use could streamline the process of integrating structured reporting across the specialty. 

A new meta-analysis suggests that when it comes to hip fractures, AI algorithms do not always live up to their hype. 

The tool’s sensitivity was recorded as 99.1% for abnormal radiographs and 99.8% for critical radiographs—better than two board-certified radiologists who also interpreted the exams. 

When put to the test, the new model was able to predict Alzheimer’s risk with 90.2% accuracy.