Artificial Intelligence

Artificial intelligence (AI) is becoming a crucial component of healthcare to help augment physicians and make them more efficient. In medical imaging, it is helping radiologists more efficiently manage PACS worklists, enable structured reporting, auto detect injuries and diseases, and to pull in relevant prior exams and patient data. In cardiology, AI is helping automate tasks and measurements on imaging and in reporting systems, guides novice echo users to improve imaging and accuracy, and can risk stratify patients. AI includes deep learning algorithms, machine learning, computer-aided detection (CAD) systems, and convolutional neural networks. 

Tomo on par with diagnostic mammo for recall workup

Digital breast tomosynthesis (DBT) provided sensitivity and specificity on par with diagnostic mammography for the evaluation of noncalcified findings recalled from screening mammography, suggesting tomosynthesis can replace the conventional diagnostic approach. The study was published in the February issue of the American Journal of Roentgenology.

CDS prototype for breast MR does not curb unnecessary biopsies

Diagnostic performance and false-positive biopsy recommendations did not improve among radiologists using a prototype clinical decision support (CDS) system designed for dynamic contrast-enhanced breast MRI studies, according to a study published in this month's American Journal of Roentgenology. 

Imaging informatics + genomics promise lung cancer treatment potential

An approach that combines digital imaging with genomic sequencing to match lung cancer patients with treatments could result in improved survival rates, according to researchers at Ohio State University, Columbus, and University of Kentucky, Lexington.

PCPs say no to rads giving results to patients

Most primary care physicians (PCPs) are satisfied with radiology reporting and recommendations, according to results of a survey published Feb. 1 in the Journal of American College of Radiology. However, the survey offered a few surprises, including a universal objection to radiologists delivering results to patients.

UVA taps M*Modal for speech understanding

The University of Virginia (UVA) Health System will deploy M*Modal Fluency Direct and M*Modal Catalyst for Quality to speech-enable its EHR systems.

Structured reporting success balances uniformity + individuality

For a department to successfully implement common structured reporting, it must overcome organizational challenges that require at least as much attention as the technical challenges, according to an article published online Jan. 17 in Radiology.

GSI to acquire NDS Surgical Imaging

GSI Group has acquired San Jose, Calif.-based NDS Surgical Imaging (NDSsi) for $82.5 million in cash, subject to customary closing adjustments.

Smartphone flop: Melanoma assessment apps may mislead patients

The diagnostic performance of smartphone applications designed to assess melanoma risk is generally poor and highly variable, according to a study published online Jan. 16 in JAMA Dermatology.

Around the web

Harvard’s David A. Rosman, MD, MBA, explains how moving imaging outside of hospitals could save billions of dollars for U.S. healthcare.

Back in September, the FDA approved GE HealthCare’s new PET radiotracer, flurpiridaz F-18, for patients with known or suspected CAD. It is seen by many in the industry as a major step forward in patient care. 

After three years of intermittent shortages of nuclear imaging tracer technetium-99m pyrophosphate, there are no signs of the shortage abating.