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. 

Industry first: FDA clears device for detecting stroke on noncontrast CT

RapidAI said it aims to give smaller facilities access to tools often only available at comprehensive stroke centers. 

April 19, 2023

10-year imaging study examines long-term side effects of smoking cigarettes

The findings support the notion that it is never too late to quit smoking, as the benefits of doing so are clear, experts involved in the study suggested.

April 12, 2023
Example of data generated by an automated artificial intelligence (AI) brain CT assessment tool from Annalise.ai at RSNA 2022. What does brain imaging look like?

AI company racks up 7 new FDA clearances for image triage and notification solutions

The Australia-based company made the announcement on April 12 in a release that described the timing of these AI-assisted solutions as “increasingly important” amid growing workloads and staffing shortages. 

April 12, 2023
Example of the four types of breast tissue density. The density of fibroglandular tissue inside the breast impacts the ability to easily see cancers. Cancers are very easy to spot in fatty breasts, but are almost impossible to find in extremely dense breasts. These examples show craniocaudal mammogram findings characterized as almost entirely fatty (far left), scattered areas of fibroglandular density (second from left), heterogeneously dense (second from right), and extremely dense (far right). RSNA

Experts developed a deep learning model that can estimate breast density

When tested, the model achieved a performance comparable to that of human experts.

April 10, 2023
The European Society of radiology European Congress of Radiology (ECR) 2023 meeting. Image courtesy of ECR

Key trends in radiology at the European Congress of Radiology 2023 meeting

Bhvita Jani, research manager at the healthcare market analysis firm Signify Research, shares noteworthy happenings from the ECR expo floor.

April 7, 2023
pulmonary embolism on CT pulmonary angiography

AI work list prioritization tool significantly decreases PE turnaround times

The FDA-approved tool works by reprioritizing CTPA exams to the top of a radiologist’s work list when the scan is positive for PE.

April 5, 2023
A team of cardiologists from Cleveland Clinic and Stanford University recently tested ChatGPT, the popular artificial intelligence (AI) model, to see if it could accurately answer questions about preventive cardiology and cardiovascular disease. The model performed well, only missing a handful of questions, and the researchers concluded that ChatGPT showed considerable potential. Cleveland Clinic cardiologist Ashish Sarraju, MD, was the lead author of that study. #ChartGPTChat GPT

ChatGPT offers 'pretty amazing' recommendations on breast cancer screening, but oversight remains critical

A team of experts with the University of Maryland School of Medicine recently presented ChatGPT with a set of questions relative to breast cancer screening recommendations to determine whether the program could reliably offer appropriate guidance.

April 4, 2023
Chest X-ray. Using an explainable artificial intelligence (AI) model, researchers were recently able to accomplish highly accurate labeling on large datasets of publicly available chest radiograph X-rays.. 

Radiologists develop point-of-care AI for chest X-rays

Radiologists used an AI tool-building platform to create their model(s), which allows clinicians the opportunity to develop AI models without any prior training in data sciences or computer programming. 

April 3, 2023

Around the web

Automated AI-generated measurements combined with annotated CT images can improve treatment planning and help referring physicians and patients better understand their disease, explained Sarah Jane Rinehart, MD, director of cardiac imaging with Charleston Area Medical Center.

Two advanced algorithms—one for CAC scores and another for segmenting cardiac chamber volumes—outperformed radiologists when assessing low-dose chest CT scans. 

"Gen AI can help tackle repetitive tasks and provide insights into massive datasets, saving valuable time," Thomas Kurian, CEO of Google Cloud, said Tuesday. 

Trimed Popup
Trimed Popup