Follow-up recommendations in radiology reports commonly contain little standardization. Machine learning and deep learning methods are each effective for deciphering reports and may provide the foundation for real-time recommendation extraction, according to a recent study in the Journal of the American College of Radiology.

Radiology has continuously been on the forefront of adopting new technologies. But at one institution, it took a bit of training and exposure to existing interactive multimedia reporting features before radiologists were willing to adopt it into clinical practice.

Long wait times can negatively impact patient satisfaction, which then harms the patient-centered, value-based care imaging departments seek to provide. But collecting the necessary data for improvements can be difficult, according to the authors of a case study published in the Journal of Digital Imaging.

Radiology has the highest use of telemedicine for patient interactions than any other medical specialty, according to results from a nationally representative survey published in the December issue of Health Affairs by the American Medical Association (AMA).

Using data from the Human Connectome Project, researchers were able to reassess inconsistent findings from neuroimaging studies of Alzheimer’s patients, according to a study published online Dec. 14 in the journal BRAIN.

A deep learning algorithm developed by researchers at the Mayo Clinic in Rochester, Minnesota, segmented abdominal CT images to determine body composition similarly to, and at times, better than trained radiologists.