RadiologyToday.net   |   View web version
Radiology Today  e-Newsletter
Magazine
Subscribe or Renew
Share
Digital Edition
July 2021 Connect with us Facebook Twitter Sign up  |  Archive  |  Advertise
Editor's e-Note
AI is finding its way into many aspects of radiology. One of the most exciting uses is improving detection of easy-to-miss imaging features. This month, we have some news about AI paired with radiography to better identify wrist fractures. Although still in the research phase, AI algorithms such as this may eventually be important components of DR systems.

How would you like to see AI deployed in radiology? Let us know on Twitter and/or Facebook.

— Dave Yeager, editor
e-News Exclusive
AI Improves Wrist Fracture Detection

An automated system that uses AI is effective at detecting a common type of wrist fracture on X-rays, according to a study published in the journal Radiology: Artificial Intelligence. Researchers say the AI-derived algorithm could help speed diagnosis and allow earlier treatment.

Scaphoid fractures are injuries to one of the small bones of the wrist that typically occur when people try to break a fall with their hands. They comprise up to 7% of all skeletal fractures. Prompt diagnosis is important, as the fracture may fail to heal properly if untreated, leading to a host of problems such as arthritis and potentially loss of function. Conventional X-ray is the imaging technique of choice for diagnosing scaphoid fractures, but it is often limited by overlap of the scaphoid with the surrounding bones of the wrist. Variations in wrist positioning and X-ray technique can also limit the visibility of fractures.

“Consequently, scaphoid fractures can be overlooked during initial X-ray examinations,” says study lead author Nils Hendrix, PhD, a candidate at the Jeroen Bosch Hospital and Jheronimus Academy of Data Science in the Netherlands.

Hendrix and colleagues recently studied a system that could aid radiologists in detecting these common fractures. The system is based on deep learning with a convolutional neural network, a sophisticated type of AI that is capable of discerning subtle patterns in images beyond the capabilities of the human eye.

While previous research found that a convolutional neural network was inferior to human observers at identifying scaphoid fractures on X-rays, the new study used larger datasets and further algorithm refinements to improve detection. It also employed class activation maps, which are AI tools that help users understand what region of the image is influencing the network’s predictions.

The researchers used thousands of conventional X-rays of the hand, wrist, and scaphoid to develop the system. They tested it on a dataset of 190 X-rays and compared its performance with that of 11 radiologists. The system had a sensitivity of 78% for detecting fractures with a positive predictive value of 83%, which refers to the likelihood that patients identified by the AI as having a fracture do, in fact, have one. Analysis showed that the system performed comparably to the 11 radiologists. The system has significant potential in clinical use, Hendrix says. It could reduce the incidence and costs of additional imaging exams and unnecessary therapy, speed up diagnosis, and allow earlier treatment.

Full story »
Recently Online
Intelligent Upgrades
We check in with experts from top manufacturers to bring you the latest on DR trends and technology, a discussion driven by the profound influences of COVID-19 and AI. Read more »

Targeted Treatment
Delivered at the time of surgery, intraoperative radiation therapy is making a difference for women with early-stage breast cancer, particularly among underserved populations. Read more »

Super Models
3D virtual reality models are bestowing the gift of X-ray vision upon medical personnel. Read more »

On the Case
A mammography screening leads to a diagnosis of SMOLD, alternatively known as Zuska’s disease. Read more »
Other Imaging News
Celestial Technology Detects ‘Galaxylike’ Pattern in Ancient Sudanese Tombs
Using the Neyman-Scott Cluster model, typically applied to astronomical phenomena, researchers determined that more than 10,000 medieval Sudanese tombs were laid out in a pattern reminiscent of a galaxy cluster. The findings in PLOS One, along with visuals courtesy of the Daily Mail, are invigorating the study of ancient burial customs.

Comprehensive Brain-Imaging Technique Combines fMRI, EEG, and EROS
According to the University of Illinois Urbana-Champaign, event-related optical signal, or EROS—a technique using near-infrared light to track neuron activity—used in tandem with functional MRI and electroencephalography, overcomes the shortcomings of each traditional procedure, thereby affording a comprehensive glimpse into brain activity.

UK Museum Announces Large-Scale Collaborative to Study Insect Archives
The United Kingdom’s Natural History Museum has partnered with Diamond Light Source, the UK’s national synchrotron science facility, to apply the latest 3D imaging technology to the study of 35 million insects in its archives. The effort, they say, will add volumes to what is presently known about insect evolution, diversity, and extinction.

Finnish Company Consolidates, Expands Satellite Surveillance Platform
The Helsinki-based company Iceye announces that its Coherent Change Detection technology can meticulously monitor human activity from space. By overlaying images taken from an identical orbital perspective 24 hours apart, the system can detect the minutest movements at the area of interest, according to a recent press release.
Advertising Opportunities
Have a product or service you want to market to radiology professionals or an open position that you need to fill quickly? Radiology Today offers many flexible advertising programs designed to maximize your results. From print advertising to e-newsletter sponsorships, website advertising to direct mail opportunities, Radiology Today helps achieve your goals. Email our experienced account executives today for more information or call 800-278-4400!

Jobs.AlliedHealthCareers.com is the premier online resource to recruit radiology professionals. Post your open positions, view résumés, and showcase your facility's offerings all at Jobs.AlliedHealthCareers.com!

Radiology Today's Physician Recruitment Center gives physician recruiters a powerful tool to satisfy their current needs. An ideal option for recruiters looking to fill partnership opportunities, academic appointments, and hospital staff positions, the Physician Recruitment Center is visited regularly by radiologists and other imaging physicians during their frequent trips to our website for the best coverage of industry news and trends.
 
In This e-Newsletter
Worth Repeating
“This is tremendously exciting news for the Santa Barbara Zoo given the critically endangered status of the Amur leopard. Conservation is a critical part of our mission, and we’re proud to celebrate Ajax’s pregnancy with our colleagues and conservation partners, as well as the Santa Barbara community and beyond. Breeding Amur leopards is complicated and challenging, and our team has worked really hard to help Ajax get pregnant.”

Julie Barnes, BVSc, MSc, of California’s Santa Barbara Zoo, regarding their efforts to breed a near-extinct species of leopard, a procedure that involved training the animal to voluntarily participate in ultrasound imaging
Gift Shop
Radiology Today's online gift shop features a wide variety of items for radiology professionals. Choose from t-shirts, journals, clocks, buttons, mouse pads, and much more! Check out our secure online shop today or call toll-free 877-809-1659 for easy and fast ordering.
Set up Job Alerts and create your online Résumé
to let potential employers find you today!