Imaging Informatics

Imaging informatics (also known as radiology informatics, a component of wider medical or healthcare informatics) includes systems to transfer images and radiology data between radiologists, referring physicians, patients and the entire enterprise. This includes picture archiving and communication systems (PACS), wider enterprise image systems, radiology information. systems (RIS), connections to share data with the electronic medical record (EMR), and software to enable advanced visualization, reporting, artificial intelligence (AI) applications, analytics, exam ordering, clinical decision support, dictation, and remote image sharing and viewing systems.

Hands-free, generative AI system reduces radiologists' time spent creating reports
"Application of these technologies represents potential areas to combat burnout," researchers wrote recently in the Journal of the American College of Radiology.
Radiomics-based tool predicts fracture risk in COPD patients
Such technology can be leveraged to improve risk assessments without accruing additional expenses for patients or clinicians, potentially filling in gaps where DXA exams fall short.
Many radiology PowerPoints inadvertently put private health information at risk
Many of these files are still readily available online, and numerous contain PHI that is “easily accessible,” a new analysis reveals.
Incidental finding characteristics that warrant communication
Three factors are associated with true high-risk findings—imaging protocols for aortic valve implantation planning, imaging area, and cardiology department orders.
GPT-4 as accurate as neurologists in predicting final diagnosis based on MRI reports
The large language model can also outperform other human providers, radiologists included, new study shows.

Providing plain language and context in spine imaging reports helps drop opioid prescriptions

The intervention is inexpensive and simple to replicate, UW Medicine experts explained in JAMA Network Open.

September 17, 2020

RSNA offering cash, massive dataset for AI solutions to tackle pulmonary embolism

The Radiological Society of North America launched its fourth annual artificial intelligence challenge, hoping to help docs detect and characterize the condition.

September 14, 2020

New liability concerns emerge for radiologists who have used patient images in presentations

Recent updates to search engines such as Google and Bing may expose imaging data previously thought to be anonymous, ACR, RSNA and SIIM warned.

August 21, 2020

How one radiology department ‘recovered wisely’ to bounce imaging numbers back near pre-COVID levels

University of Cincinnati Health has deployed a data-driven, team-based approach to resuming nonurgent radiology services after it sustained a “sharp,” systemwide decrease in the spring.

August 13, 2020

Intelerad acquires private cloud provider Radius

The move builds upon the Montreal tech company’s cloud-based imaging strategy and allows Intelerad to provide a flexible approach to managed services and a hybrid cloud solution to providers.

August 5, 2020

Radiology practice launches investigation, warns patients after data breach

Mid-Delaware Imaging said it first became aware of the incident earlier this year, with leaders recently notifying the FBI.

July 29, 2020

‘A huge game changer’: Penn uses machine learning, radiomics to share brain imaging data privately

“Federated learning,” as it’s called, works by training an algorithm across multiple data servers, without exchanging any images, experts detailed in Scientific Reports.

July 29, 2020

Adding physicians’ phone numbers to radiology reports bolsters patient contact, job satisfaction

That’s according to the results of a recent survey conducted at one private Colorado imaging practice, highlighted in the American Journal of Roentgenology.

July 8, 2020

Imaging Informatics

Hands-free, generative AI system reduces radiologists' time spent creating reports

Radiomics-based tool predicts fracture risk in COPD patients

Many radiology PowerPoints inadvertently put private health information at risk

Incidental finding characteristics that warrant communication

GPT-4 as accurate as neurologists in predicting final diagnosis based on MRI reports