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. 

Thumbnail

4D CT could supplement wrist radiographs in evaluating radioulnar deviation

For patients with wrist movement abnormalities, four-dimensional CT imaging during radioulnar deviation could improve diagnosis of suspected scapholunate ligament tears and injuries, according to research published online Sept. 25 in Radiology.

Thumbnail

Sloan Kettering’s deal with digital pathology startup draws backlash

An agreement between artificial intelligence (AI) startup Paige.AI and Memorial Sloan Kettering Cancer Center in New York is drawing backlash over the company’s exclusive rights to the cancer center’s 25 million pathology slide images, the New York Times reported.

Thumbnail

CT technique offers microscopic view of Egyptian remains

Swedish researchers have used a novel CT imaging technique to study the soft tissue of an ancient Egyptian mummy’s hand at microscopic levels, according to a Sept. 25 study published in Radiology.

Thumbnail

Unused MRI information offers insights into brain conditions

MRI scans produce mounds of unused data. Now, researchers at Washington University School of Medicine in St. Louis have created a new method of utilizing that information to determine how many and where cells have been lost due to injury or disease.

Thumbnail

fMRI, AI demonstrates how the brain connects episodic memories to solve problems

The process of episodic memory—the ability to combine memories to solve problems—may be enabled by the brain’s capacity to store, activate and connect specific memories in the hippocampus, according to new theoretical research published online Sept. 19 in Neuron.

Thumbnail

Simulation reveals how breast tissue of varying density may react to MRI

Novel computer simulations of the female body developed by researchers from Purdue University in West Lafayette, Indiana, may help predict how more than 20 different breast tissue ratios will respond to MRI varying in radiofrequency.

Thumbnail

Photoacoustic imaging technique may improve wearable imaging devices, medical diagnostics

Chinese researchers developed a flexible photoacoustic imaging technique by modifying fiber optic sensors and combining laser light and ultrasound to image biological tissue, detailed in a release from The Optical Society.

Thumbnail

Deep learning beats radiologists at fibrotic lung disease classification

A deep-learning algorithm beat thoracic radiologists at classifying fibrotic lung disease, according to research published Sept. 15 in The Lancet Respiratory Medicine.

Around the web

RBMA President Peter Moffatt discusses declining reimbursement rates, recruiting challenges and the role of artificial intelligence in transforming the industry.

Deepak Bhatt, MD, director of the Mount Sinai Fuster Heart Hospital and principal investigator of the TRANSFORM trial, explains an emerging technique for cardiac screening: combining coronary CT angiography with artificial intelligence for plaque analysis to create an approach similar to mammography.

A total of 16 cardiology practices from 12 states settled with the DOJ to resolve allegations they overbilled Medicare for imaging agents used to diagnose cardiovascular disease.