Data security has become a serious issue in the U.S., not only for big tech companies like Facebook, but for vendors and institutions looking to use patient imaging information to develop AI platforms.

“Medical M.R.I.s can do great characterization of samples, but not at this small scale," said A. Duke Shereen, director of the MRI Core Facility at the Advanced Science Research Center in New York, to the New York Times.

Teenagers with large amounts of white matter depicted on brain scans are more likely to up their alcohol intake over the next five years, reported authors of a new study published July 2 in eLife.

The American College of Radiology (ACR) has expanded its ACR AI-LAB pilot program geared toward helping radiologists develop AI models without the use of coding language.

PET brain imaging using a new brain imaging paradigm yields preliminary evidence that tobacco smokers may have reduced neuroimmune function compared with non-smokers.

A convolutional neural network (CNN) approach can accurately identify and sub-classify suspected tuberculosis (TB) on chest radiographs, according to research presented at the Society for Imaging Informatics in Medicine (SIIM) annual meeting.

In order to properly train and validate algorithms, developers need high volumes of quality-labeled data. But such datasets are not easy to obtain.

Predictions of heart attacks and deaths based on coronary computed tomography angiography (CCTA) are more accurate when made using an artificial intelligence (AI) algorithm than with the Coronary Artery Disease Reporting and Data System (CAD-RADS) or other risk assessment methods.