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.

Popular LLMs confidently fail at answering image-based board questions
Updated large language models have been trained to process both text- and image-based questions, potentially making them more effective in radiology settings.
Nvidia rolls out AI models designed to behave like radiologists interpreting images
The global artifical intelligence leader collaborated with the NIH, Children’s Hospital of Philadelphia, and VinBrain to create the new chain-of-thought dataset.
Mallinckrodt Institute of Radiology to open center for advancing AI-based imaging tools
The Center for Computational and AI-enabled Imaging Sciences will bring together talent from WashU’s respected medical and engineering programs.
Healthcare AI today: Docs and clerks, talk therapy renewed, Dr. AI vs. Dr. Google, more
Not long ago, physicians and grocery clerks had a key duty in common: ‘connective labor.’ Today barcode reading machines sweep you through the checkout. And AI can handle most of your health questions.
Healthcare AI today: Rusty clinical skills, AI growing up so fast, AI for the malnourished
Clinicians who come to rely on AI for decision support risk the dulling of their skills. The concern is not new. But now comes a pointed call to researchers: Inquire about the particulars of the peril.

‘Minutes matter’: Deep learning quickly spots stroke-causing blockages on CTA scans

Brown University researchers built their model from scratch and credited a new multiphase approach to its enhanced detection capabilities.

Physician/AI aficionado dissects Medicare’s first agreement to pay for use of AI

Early this month CMS agreed to reimburse hospitals for using the first AI software to qualify for Medicare’s NTAP mechanism. Healthcare AI watchers have been unpacking the intricacies of the development ever since.

Dozens of radiologists pitch in as French artificial intelligence firm raises nearly $9M

Paris-based Gleamer will use the funds to target U.S. FDA clearance for its BoneView AI solution that's already live in 50 hospitals.

AI matches radiologists at spotting lung cancer; S&P negative on imaging firm, plus more vendor news

Also, Philips inks seven-year deal with 1,006-bed hospital, RBMA taps help in Medicare cut fight, and FDA clears new radiology solutions.

Machine-learning algorithm detects osteoarthritis prior to development

A machine-learning algorithm can predict the onset of osteoarthritis on MRI scans taken years before symptoms begin.

FDA’s new digital-health ‘center of excellence’ shows the shape it will take

The FDA has an eye trained on healthcare AI as it establishes a major operation to help advance the state of the art across digital health.

Drones deliver AEDs in times of need

In some instances, the drone helped get an AED on the scene nearly three minutes faster than normal.

RapidAI raises $25M; Sectra signs top health systems; conference shelved, plus more radiology vendor news

Also, MITA warns FDA about inappropriate cleaning of imaging systems and Fujifilm partners with the CHEST Foundation.

Artificial Intelligence

Popular LLMs confidently fail at answering image-based board questions

Nvidia rolls out AI models designed to behave like radiologists interpreting images

Mallinckrodt Institute of Radiology to open center for advancing AI-based imaging tools

Healthcare AI today: Docs and clerks, talk therapy renewed, Dr. AI vs. Dr. Google, more

Healthcare AI today: Rusty clinical skills, AI growing up so fast, AI for the malnourished