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

AI predicts death or heart attack, topping expert physicians

A machine learning algorithm trained to read imaging scans was more accurate at predicting heart attacks or death than expertly trained physicians, according to a study presented at the International Conference on Nuclear Cardiology and Cardiac CT (ICNC) in Lisbon, Portugal, on May 12.

Thumbnail

Tech-savvy healthcare consumer? There’s a robot doctor in your future

There’s probably a lot of overlap between computer “power users” and individuals who are comfortable with machines replacing humans in the workplace.

Thumbnail

AI-powered triage solution for pneumothorax gains FDA clearance

Zebra Medical Vision has received FDA clearance for its new artificial intelligence (AI) solution that scans chest x-rays for signs of pneumothorax and alerts imaging providers when necessary.

Clinicians should consider whole-body MRI to save time, costs when staging cancer patients

Whole-body MRI (WB-MRI) staged colorectal and lung cancer patients with accuracy similar to standard staging pathways, but WB-MRI saved valuable time and costs associated with screening, according to results of two new trials published May 9.

Thumbnail

Elevated tau levels found in former athletes with history of concussions

Tau levels found in concussed former athletes may help predict who will ultimately suffer from long-term effects of blows to the brain, according to a new study published in Neurology.

Thumbnail

NVIDIA, King’s College London partner on AI platform for radiology workflows

NVIDIA and King’s College London have announced a new partnership focused on developing a new artificial intelligence (AI) platform to improve radiology workflows.

Thumbnail

4D CT can reliably assess ankle ligament injuries

Four-dimensional (4D) CT can reliably evaluate ligament injuries in the ankle and may be used to test the ankle in-motion to spot asymptomatic problems, according to results of a May 8 study published in Clinical Radiology.

Thumbnail

A new, improved way to predict breast cancer risk with AI

A new deep learning model leveraging data from screening mammograms can predict a patient’s breast cancer risk with significant accuracy, according to a new study published in Radiology.