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.

GPT-4 can detect radiology report errors at the same rate as members of the specialty
“This efficiency in detecting errors may hint at a future where AI can help optimize the workflow within radiology departments," a lead author of the study said.
Semiautonomous AI shows potential to reduce false positives, unnecessary procedures and medical expenses
Scientists developed the deep learning algorithm using a set of over 123,000 digital mammograms (including 6,100-plus cancer cases).
GE HealthCare finalizes acquisition of Cleveland-based provider of AI imaging-analysis software
The company plans to integrate MIM Software's radiology and nuclear medicine solutions into its advanced-visualization product line.
Large language models excel at simplifying radiology reports
Yale scientists sought to gauge how LLMs such as ChatGPT-3.5/4, Google’s Bard (now known as Gemini) and Microsoft Bing could improve readability.
Radiology AI company gains FDA clearance for new CT offerings focused on PE, stroke
The newly approved AI models are designed to improve the detection of pulmonary embolisms and strokes in patients who undergo CT scans.

Example of AI automated detection and highlighting of critical lung findings on a chest X-ray for a possible lung cancer nodule and fibrosis. Example shown by AI vendor Lunit.

VIDEO: Radiology AI trends at RSNA 2022

Sanjay Parekh, PhD, senior market analyst with Signify Research, discusses trends in radiology AI seen on the expo floor and in sessions at RSNA 2022.

December 12, 2022

Tablet projecting metaphorical medical hologram

AI-powered platform for heart failure detection gains FDA clearance

According to data submitted to the FDA, the platform has been linked to an accuracy of 90%, sensitivity of 87.8% and specificity of 83%.

December 8, 2022

AI is still one of the key technologies on the floor that many radiologists want to learn more about. A product rep discussing breast automated detection AI in the crowded Lunit booth at RSNA 2022.

9 technology trends and takeaways from RSNA 2022

Here are some interesting new technologies and key trends from the vast expo floor at the Radiological Society of North America 2022 meeting.

December 6, 2022

Jorge Soto, MD, chair of the RSNA Annual Meeting Program Planning Committee, chief of radiology, Boston Medical Center, and professor of medicine, Boston University School of Medicine, offers an overview of the trends, hot topics, and innovative research and technology at the Radiological Society of North America (RSNA) 2022 meeting.

VIDEO: Key takeaways from RSNA 2022

Jorge Soto, MD, chair of the RSNA Annual Meeting Program Planning Committee, chief of radiology, Boston Medical Center, offers an overview of the trends, hot topics, research and technology at the Radiological Society of North America (RSNA) 2022 meeting.

December 5, 2022

Dynamic lung air flow analysis just using X-ray without any contrast with new technology from 4D Medical.

PHOTO GALLERY: New technology and trends at RSNA 2022

Images from the Radiological Society of North America (RSNA) 2022 annual meeting Nov. 27- Dec. 1 in Chicago. The gallery includes new technologies and a look at sights around the world's largest radiology conference.

December 1, 2022

AI generates imitation lung X-rays replete with diagnosable pathologies

Stanford researchers have created synthetic yet highly realistic chest X-rays by customizing an open-source AI model called Stable Diffusion for rendering text as images.

December 1, 2022

probably benign abnormalities on mammogram

Google Health partners with iCAD in commercial AI imaging push

The deal is the first commercial partnership for Google Health to introduce its breast imaging AI into clinical practice.

December 1, 2022

RadNet and Google Health join forces to use AI for lung cancer screening

Aidence will license, develop, and validate Google Health’s existing AI research module, hoping to offer better differentiation between benign and malignant lung nodules at an early stage.

November 29, 2022

Around the web

Cardiovascular Business

Medicare drops AUC requirement for advanced imaging, ASNC celebrates

"This was an unneeded burden, which was solely adding to the administrative hassles of medicine," said American Society of Nuclear Cardiology President Larry Phillips.

Cardiovascular Business

Cardiology, radiology groups urge insurance provider to rethink imaging policy

SCAI and four other major healthcare organizations signed a joint letter in support of intravascular ultrasound.

Cardiovascular Business

Radiology AI company gains FDA clearance for new CT offerings focused on PE, stroke

The newly approved AI models are designed to improve the detection of pulmonary embolisms and strokes in patients who undergo CT scans.