Artificial Intelligence

A team at Geisinger Health System in Pennsylvania created a machine learning platform able to read CT scans that reduced the time to detect internal bleeding by 96 percent.
A recent editorial in STAT argued that as artificial intelligence (AI) continues to proliferate, the need for human providers will not decrease—rather, their knowledge will become more valuable in decision-making.
Harvard Medical School researchers in collaboration with 3D bioprinting firm Aether recently introduced a 3D printing software that uses artificial intelligence (AI) to reproduce medical images of organs as 3D models.
Artificial intelligence (AI) continues to change the way radiologists work. The major shift predicted by many isn’t happening as quickly as expected—but AI is reaching areas some didn’t anticipate.
Facebook's most recent data scandal had lawmakers grilling founder and CEO Mark Zuckerberg in a Senate hearing April 11 and presents bioethics lessons for healthcare leaders who are creating AI models for clinical decision making
W. Art Chaovalitwongse, PhD, from the University of Arkansas, discusses using radiomics versus deep learning-based features to predict clinical outcomes from medical imaging data.
Recent research found a machine learning algorithm outperformed coronary CT angiography and quantitative coronary angiography in identifying heart blockages.
Primary care physicians may now be able to identify moderate to severe levels of retinopathy in adult patients with diabetes using a recently FDA-approved artificial intelligence (AI) imaging device.
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.
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.
Ohio State University researchers have developed an artificial intelligence (AI) algorithm able to analyze a single brain CT scan in just six seconds, according to an article published online March 28 by the Lantern.
Eight members of the Association of University Radiologists Radiology Research Alliance Task Force on Deep Learning describe a radiologist-friendly overview examining past, present and future applications and how the field might benefit from embracing deep learning.
New artificial intelligence research from Google, presented at MIT Technology Review's EmTech Digital 2018 conference in San Francisco, may point to reducing the number of radiologist-annotated images required to train a deep learning algorithm for medical imaging applications.
A group of U.S. researchers created a natural language processing (NLP) system which outperformed traditional rule-based methods in identifying lumbar spine findings, according to a study published online in Academic Radiology.
Jensen Huang, CEO of Nvidia, a California-based technology company, recently revealed plans to construct a medical imaging supercomputer affectionately named Clara.
A study published in the journal Digital Medicine found a trained artificial intelligence (AI) platform classified echocardiogram views with 98 percent accuracy—outperforming board-certified cardiologists.
As deep learning in medical imaging continues to advance, two leading experts argue in an editorial in the Harvard Business Review that it will only result in positive impacts on the field—rather than replace imaging professionals with computers.
A recent study published in Radiology has demonstrated that deep-learning bone age assessment models analyzing hand radiographs produced results as accurate as a radiologist.
Researchers from Massachusetts General Hospital (MGH) have developed a machine learning and artificial intelligence (AI)-based technique that may generate higher quality images without having to collect additional data.
Artificial Intelligence (AI) is perhaps the hottest topic across healthcare right now—especially in radiology. A recent Forbes article suggests the profession may be in a good spot to embrace the coming change.
A group of Chinese scientists and clinicians developed a learning artificial intelligence (AI) platform able to diagnose prostate cancer with the same accuracy as a human pathologist, according to a European Association of Urology press release.