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.

How generative AI for healthcare is similar to—and different from—its conventional older cousin
The National Academy of Medicine considers some pertinent ins and outs of GenAI.
RadNet to acquire breast imaging AI vendor iCAD for $103M
The acquisition will give Los Angeles-based RadNet an installed base of more than 1,500 healthcare provider locations, facilitating 8 million mammograms across 50 countries.
FDA clears AI-powered echocardiography software
HeartFocus guides users through the entire process, making it so that even novices can deliver high-quality echocardiograms every time.
American-made GPT-4 knows no borders, translates radiology reports into different languages
New research highlights the potential of GPT-4 to enhance radiologists’ communication of findings in clinical environments across the pond.
FDA takes first step toward ending animal testing as part of ‘3.0 modernization'
Monoclonal antibody therapies will be the first drugs permitted to take advantage of alternatives, including advanced lab simulations and artificial intelligence. A pilot framework to phase out the decades-long requirement for animal testing will be rolled out in the coming year, the FDA said.

ZEISS introduces machine learning capability for microscopy

First ZEISS ZEN Intellesis solution enables segmentation of correlative microscopy datasets.

MRI study finds prenatal exposure to certain antidepressants may alter brain development

Researchers from New York and California recently used MRI to determine prenatal exposure to commonly used antidepressants in pregnant women may be associated with impacted fetal brain development—particularly in areas crucial to emotions.

Rediscovering radiology’s ‘soul’ in the AI era

Despite radiology’s love-hate relationship with artificial intelligence (AI), advancements could afford the field an opportunity to “hit refresh” and reinvent itself, Emory University professor and radiologist Srini Tridandapani, PhD, MD, MSCR, wrote in Academic Radiology this month.

MRI of tumor surface regularity may aid surgery, predict survival in glioblastoma patients

A team of international researchers published a study in Radiology that found surface regularity taken from high-resolution contrast-enhanced pretreatment volumetric T1-weighted MRIs to be an accurate predictor of survival in patients with specific malignant brain or spine tumors.

Virtual world ‘Second Life’ could present new learning opportunities for radiology students

As online learning options for radiology continue to grow, some students are turning to Second Life—a virtual community developed by its own users and reigned by avatars—to complete their medical education, researchers in Malaga, Spain, have found.

Deep learning improves radiologist workflow, efficiency determining musculoskeletal MRI protocol

Deep learning and artificial intelligence (AI) are often associated with identifying nodules and classifying images, but a recent study found convolutional neural networks (CNNs) can be utilized in radiology workflows to determine musculoskeletal MRI protocols.

Microscopic imaging finds new organ—dubbed the 'highway of moving fluid'

Calling the discovery of a new organ in the human body surprising is a bit of an understatement, but that's what a study published in Scientific Reports claims.

AI digital pathology may help guide cancer therapies

A team of Stony Brook University-led researchers in New York created a method using deep learning digital pathology to map cancerous immune cell patters that may help guide new cancer therapies.

Artificial Intelligence

How generative AI for healthcare is similar to—and different from—its conventional older cousin

RadNet to acquire breast imaging AI vendor iCAD for $103M

FDA clears AI-powered echocardiography software

American-made GPT-4 knows no borders, translates radiology reports into different languages

FDA takes first step toward ending animal testing as part of ‘3.0 modernization'