You are here

Imaging Informatics

 

Free-text radiology reports can be automatically classified by convolutional neural networks (CNNs) powered by deep-learning algorithms with accuracy that’s equal to or better than that achieved by traditional—and more labor-intensive—natural language processing (NLP) methods.

Researchers in the radiology department at the University of California, San Francisco (UCSF)—led by of Sabrina Ronen, PhD, director of the Brain Research Interest Group (RIG) and professor in the department of radiology and biomedical imaging at UCSF—are in the process of developing new, non-invasive imaging biomarker indicators to address multiple types of cancer, according to a recent UCSF press release

Many radiologists use Twitter and LinkedIn for staying up on matters related to their work. A study published online Nov. 12 in the Journal of the American College of Radiology shows they’d do well to tap, for the same purposes, the social-media platform that’s commonly thought of as a purely personal online space.

A group of German researchers has developed a nuclear medicine test that can detect infections in kidney transplant tissue, according to a study published in Journal of Nuclear Medicine

Members of the online radiology community, take note: Personally tweeting links to articles posted ahead of print in online medical journals doesn’t increase overall pageviews of these articles. It just increases the number of people who find their way to any given “article in press” via Twitter.

 

Recent Headlines

RLI Summit 2017: What radiology can learn from pathology about AI

Most health systems already have enough clinical data to make more useful primary observations than any group of humans could ever connect the proverbial dots on. The good news is that machines are here to help—and they’re getting better at it all the time.

 

CAD algorithm proves its power in early diagnosis of lung cancer

A novel computer-aided diagnosis (CAD) algorithm has bested three un-aided thoracic radiologists at predicting malignancy in small lung nodules found on low-dose CT imaging, according to a study published online Aug. 5 in Radiology.

CT process mapping cuts outpatient wait times to 1/3 of earlier average

The radiology department at an urban academic medical center has cut its average outpatient CT wait times to a little over an hour, and that includes the scan. Prior to starting the project that took aim at streamlining CT processes, the department was averaging more than three hours in arrival-through-completion times.

Brain PET scans change management of patients with possible Alzheimer’s

Knowing the amyloid status of patients who have symptoms of mild cognitive impairment or dementia affects diagnosis and alters care management, according to the authors of a study running online in Dementia and Geriatric Cognitive Disorders.

AI will augment rather than replace radiologists: How and why

Projections of radiology’s demise at the hands of algorithms have been greatly exaggerated. In fact, not only will machine learning not take rads’ jobs: It will become a routine component of their clinical practice, making their work more efficient, accurate, satisfying and valued.

Many radiotherapy cases require elevated diligence for imaging

When there’s a near-miss or safety incident (NMSI) with a patient undergoing radiation therapy, and the incident was related to the disease or treatment itself, the lapse often involves imaging. But it’s not imaging per se that raises any particular risk.

Fujifilm’s PACS gets go-ahead from Defense Department

The U.S. Department of Defense has given Fujifilm’s Synapse PACS the green light to operate on the department’s networks, granting the company an Authority to Operate (ATO) and making it the first medical-imaging vendor to obtain such clearance since DoD switched to its Risk Management Framework (RMF), according to a press release sent by Fujifilm Medical Systems USA.

Netherlands medical-imaging AI startup attracts $2.5M funding boost

A European AI startup that has so far focused on deep-learning detection of lung cancers on imaging has raised around $2.5 million (2.25 million euros) in seed-round funding to refine its product and bring it to market.

‘RAD Women’ launch online resource center

Women with an interest in medical imaging informatics have a new online resource center thanks to RADxx, the women’s advancement initiative kicked off at last year’s RSNA by Geraldine McGinty, MD, and Mini Peiris of the healthcare software company Ambra Health. 

Rejected scientific rad articles: Destiny depends on rejecters’ input vs. lack thereof

Tracking the fate of 200 unsolicited manuscripts rejected in one calendar year by the American Journal of Roentgenology, a researcher has found that the majority—117 manuscripts, close to 60 percent—eventually found a home in other scientific journals, according to an analysis running in the June edition of that very journal. 

Pages