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.

Commercially available AI increases breast cancer detection by nearly 20%
Results from the world’s largest prospective artificial intelligence study revealed the system could significantly benefit breast cancer screening programs.
Clinicians want AI to show its work
Providers are more likely to trust AI when they understand how it arrives at its conclusions.
ACR Assess-AI national data registry tracks performance of clinical algorithms
Christoph Wald, MD, vice chair of the ACR Board of Chancellors, explains how the new Assess-AI National Radiology Data Registry is designed to help monitor accuracy and other metrics for radiology artificial intelligence.
New cardiac prevention paradigm explored in TRANSFORM trial using AI and CCTA
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.
PHOTO GALLERY: Medical imaging technology at RSNA 2024
Take a virtual tour around the Radiological Society of North America (RSNA) meeting to see the sights and new technologies displayed across the vast exhibit hall floors.

Chest x-ray AI similar, but quicker than radiologists at detecting diseases

A deep learning algorithm showed capability in screening chest x-rays for diseases similar to the interpretations of trained radiologists, but did so in a matter of seconds, according to Stanford University researchers.

November 21, 2018

AI may help radiologists interpret screening mammography without added reading time

Breast radiologists had slightly higher diagnostic performances when using artificial intelligence (AI) with no additional reading time required, according to a study published Nov. 20 in Radiology.

November 21, 2018

3D MRI comparable to 2D for diagnosing meniscal knee injuries

Three-dimensional (3D) MRI is similar to 2D for diagnosing meniscus knee injuries, but may be able to cut down on image acquisition time, reported authors of a Nov. 20 study published in Radiology.

November 20, 2018

3D images from total-body scanner to be presented at RSNA 2018

Images from the world’s first whole-body MRI scanner are set to be presented at this year’s 2018 RSNA Annual Meeting in Chicago, according to a University of California, Davis statement.

November 20, 2018

Predictive model may reduce overtreatment of ground glass nodules

A model based on radiomic features extracted from CT scans can help predict which ground glass nodule (GGN) cases require surgery and may reduce overtreatment, according to researchers at the Affiliated Suzhou Hospital of Nanjing Medical University in Suzhou, China.

November 20, 2018

Philips launches IntelliSpace Discovery* Research platform at RSNA to support the development and deployment of Artificial Intelligence assets in radiology

Royal Philips

November 20, 2018

Machine learning method helps radiologists diagnose uterine cancer

A machine learning algorithm based on perfusion-weighted MRI accurately differentiated between benign and malignant tumors in the uterus, according to researchers at Tehran University of Medical Sciences (TUMS) in Iran.

November 19, 2018

Radiomics, AI fall short of radiologists in breast lesion classification on MRI

Radiologists outperformed a convolutional neural network (CNN) and radiomic analysis (RA) at classifying contrast-enhancing lesions on multiparametric breast MRI, according to a Nov. 13 study published in Radiology. With more training, however, CNNs may soon close that gap.

November 15, 2018

Around the web

Radiology Business

The biggest obstacles facing radiology business managers in 2025

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

Cardiovascular Business

New cardiac prevention paradigm explored in TRANSFORM trial using AI and CCTA

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.

Cardiovascular Business

Cardiology practices pay $17.7M to settle fraud allegations brought on by whistleblowers

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.