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. 

Thumbnail

AI shows promise as a second reader for breast cancer detection

A commercial artificial intelligence system correctly identified nearly 88% of screen-detected cancers and 45% of interval cancers, according to a major study published in Radiology

rib fracture broken ribs

AI assists radiologists in detecting fractures, improves workflow

Research published recently in Radiology found comparable sensitivity and specificity between artificial intelligence and clinicians for fracture detection. 

radiology reporting EHR health record CDS AUC

Scaling structured radiology reporting template use across multiple health systems to build a data registry

Pennsylvania imaging experts offered several key lessons learned, including the need to engage rads and continuously monitor data accuracy. 

Thumbnail

Misuse of public imaging data is producing 'overly optimistic' results in machine learning research

 "This research aims to raise a red flag regarding naive off-label usage of open-access data in the development of machine-learning algorithms," experts involved in the study said.

Thumbnail

Radiology groups urge Congress to address scarcity of AI solutions in pediatric care

The Society for Pediatric Radiology and ACR want lawmakers to draft healthcare policies that encourage innovation in artificial intelligence to address this gap. 

Private equity makes ‘strategic growth investment’ in heart CT, MR firm Circle Cardiovascular Imaging

Financial terms were not disclosed, but the two said the funds will fuel future expansion of its AI-based products, used for reading, reporting and processing images.

Thumbnail

Hospital explores using AI to autonomously order imaging exams in the emergency department

Machine learning could streamline care for 22% of visits while making results available earlier by 165 minutes per affected patient, experts wrote in JAMA

chest pain lung pulmonary embolism

Image quality is not an issue for AI model that detects pulmonary embolisms on CT

CTPA is the standard of care for diagnosing PE, but suboptimal scans make it difficult to reach a diagnosis. A new Clinical Imaging study tests the effectiveness of AI when image quality is lacking.