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. 

COVID-19 coronavirus

Of 300-plus imaging-based AI models for COVID-19 diagnosis, zero suitable for clinical use

Numerous publications have touted the use of AI to pinpoint the novel coronavirus on X-ray and CT scans, but U.K. experts aren't impressed.

AI enhances brain MRI scans to better classify Alzheimer’s disease

Last year alone, total healthcare costs spent on AD treatment exceeded $305 billion, making improved detection an important clinical goal.

Thumbnail

New MR imaging reveals quality sleep is fundamental to recovering from brain injuries

Oregon Health & Science University researchers say perivascular MRI may also be useful for diagnosing dementia and other neurological conditions.

Thumbnail

‘Less is more’: Retinal imaging tweaks boost resolution by 33%

National Eye Institute researchers say their enhanced method will help better diagnose and treat degenerative eye diseases.

Thumbnail

AI provides automated second-reader support, catching radiologist misses in chest CT reports

Underreporting of findings on CT exams is relatively common, but a deep learning algorithm showed “superior diagnostic performance” in spotting two particular concerns. 

Thumbnail

Radiology advocates urge HHS to reject ‘extraordinarily concerning’ proposal weakening AI oversight

The ACR, Radiology Society of North America and Society for Imaging Informatics in Medicine all said the "midnight" plan would jeopardize patient care and go against the FDA's previous intentions. 

Thumbnail

Robots almost as good as clinicians at pleasing patients in the ER

Emergency-room patients are happy to receive care from a physician interacting remotely over a tablet computer mounted on a dog-like robot.

AI identifies FDA-approved drugs warranting novel testing against Alzheimer’s

Harvard researchers have used machine learning to find molecular features in existing drugs that may be effective in warding off or treating Alzheimer’s disease.