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. 

neuroblastoma prognosis

18F-FDG PET/CT radiomics nomogram provides detailed insight into neuroblastoma

Better risk stratification can improve clinical decision making and better outcomes, experts involved in the study explained in EJR.

Left, coronary CT angiography of a vessel showing plaque heavy calcium burden. Right, image showing color code of various types of plaque morphology showing the complexity of these lesions. The right image was processed using the FDA cleared, AI-enabled plaque assessment from Elucid.

Cardiac CT soft plaque assessment may offer paradigm shift for coronary disease screening

New artificial intelligence software that can evaluate coronary CT scans to automatically assess soft plaques were by far the biggest technology advance discussed at the Society of Cardiovascular Computed Tomography (SCCT) 2022 meeting. 

5 reasons radiologists should feel confident about learning—and teaching—AI

For years radiology educators have been reassuring prospects, recruits and trainees that artificial intelligence can only—and will only—assist or augment radiologists. And still a nervous concern continues to come up. 

True or false? ‘AI does not influence radiologists’ performance’

A healthcare AI startup in Silicon Valley is partnering with a top-tier medical school—and hopefully a few good radiologists—to test a hypothesis that’s increasingly crucial to radiology.

enteric tube placement on radiographs

Algorithm spots enteric tube misplacement on x-ray with great accuracy

The model was externally validated using more than 1,500 radiographs with real-world incidence of critically misplaced tubes. 

Thumbnail

Content-based AI system decreases read times by 31% while increasing accuracy

Using CBIRS decreased interpretation times despite the radiologists who utilized them having to review the additional information the system provided.

Medtronic CathWorks FFRangio FFR fractional flow reserve x-rays

Medtronic invests $75M in AI-powered FFR specialists, opening door to a future acquisition

The FFRangio System, which uses AI to obtain fractional flow reserve (FFR) measurements from routine X-rays, is at the center of this new partnership

Thumbnail

Commercial PE-detecting algorithm identifies incidental clots on CT

Experts involved in the study, which analyzed more than 3,000 CT scans, suggested that there could be a future role for the algorithm to assist radiologists in busy settings.