Deep learning performs superresolution MSK MRI
April 11, 2018 -- A deep-learning algorithm can transform low-resolution, thick-slice knee MR images into high-resolution, thin-slice images -- potentially yielding faster image acquisition, lower costs, and fewer motion artifacts in musculoskeletal MRI, according to research published online in Magnetic Resonance in Medicine.  Discuss
Nvidia aims to bring imaging AI to the people with Clara
April 10, 2018 -- While artificial intelligence (AI) is poised to reshape radiology, older imaging systems may be left behind, unable to handle the massive computational workload required to run AI algorithms. But graphics processing unit developer Nvidia hopes to solve this problem with its Clara virtual supercomputing platform.  Discuss
Education is needed to harness power of AI in radiology
April 6, 2018 -- Artificial intelligence (AI) can enhance the business and operational side of radiology, but radiologists and practice managers should understand the technology before they consider adopting it, according to a talk on April 5 at the Radiology Business Management Association's Paradigm annual conference in San Diego.  Discuss
CADx volumetry predicts lung cancer recurrence on CT
April 5, 2018 -- Measurements of lung nodule volume on CT scans made with computer-aided diagnosis (CADx) software were more accurate than conventional measurements of nodule diameter in predicting the recurrence of subsolid lung cancer in patients who underwent surgery, according to a recent study published in Radiology.  Discuss
Are you ready for a radiologist shortage?
April 3, 2018 -- Could the U.S. be heading toward a shortage of radiologists? The idea might not be as crazy as it sounds if current demographic trends in radiology continue. Laurie Lafleur of Paragon Consulting Partners ponders this question and proposes that technologies such as artificial intelligence and blockchain could come to the rescue.  Discuss
Google AI algorithm shows promise for chest x-rays
April 2, 2018 -- How many radiologist-annotated images are needed to train a deep-learning algorithm for radiology applications? Perhaps not as many as you might think. Using both annotated and unannotated images, researchers from Google have developed an algorithm that can simultaneously identify and localize disease found on chest x-rays.  Discuss
ACR partners with MICCAI to make AI a clinical reality
March 30, 2018 -- Two influential radiology groups have signed a partnership to foster development of artificial intelligence (AI) algorithms to better meet the clinical needs of radiologists. The American College of Radiology (ACR) and the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society announced the deal at the NVIDIA GPU Technology Conference in San Jose, CA.  Discuss
Radiology and AI: From bête noire to nuts and bolts
March 29, 2018 -- SAN JOSE, CA - Radiologists appear to have overcome their fears of artificial intelligence (AI) and are moving on to the nuts and bolts of making the technology work in clinical practice, according to a series of talks on March 28 at the NVIDIA GPU Technology Conference. But the task won't be easy, and challenges remain.  Discuss
Straight Talk From the PACSman: The FUD factor with AI
March 29, 2018 -- There's no doubt that research and commercial activity is surging for artificial intelligence (AI) in radiology applications: AuntMinnie.com published more than 175 articles on AI news alone in the past year. The fear, uncertainty, and doubt (FUD) factor remains a big hurdle to clear, however, explains PACS consultant Michael J. Cannavo.  Discuss
4 reasons why AI won't replace radiologists
March 27, 2018 -- Are you worried about artificial intelligence (AI) eliminating your job? Don't be. Even with the rapid development of AI, the great majority of radiologists will likely continue to have jobs in the decades to come, according to an article published online March 27 in the Harvard Business Review.  Discuss