|
Agentic AI for Follow-Up, Plaque Risk in Women, and FDA CDS Town Hall
February 23, 2026
|
|
|
|
|
Together with
|
|
|
|
“Improved automated systems … have the potential to augment existing workflows and act as an additional safety net to help ensure patients are identified with radiologist recommendations and get the subsequent care they need.”
|
|
Treacher A et al, in a new study on agentic AI for tracking radiology follow-up.
|
|
|
How can agentic AI help you optimize your radiology department’s operations? Find out on Tuesday February 24 at 12 pm ET/9 am PT for this Imaging Wire webinar featuring speakers from Strings/3DR Labs and Stanford University.
|
|
|
|
Agentic AI has quickly become one of the hottest topics in radiology. But what is it really good for? Texas researchers offer one possible use case in a new study in NEJM Catalyst: scouring radiology reports to identify patients who require follow-up.
Agentic AI is a new flavor of artificial intelligence that’s capable of working autonomously to complete tasks with minimal human supervision.
- In healthcare, it’s being applied to a wide range of tasks, from improving health system operations to clinical and administrative jobs.
In the current study, researchers from Parkland Health in Dallas assigned agentic AI to one of the trickiest tasks in radiology: making sure patients with suspicious findings comply with recommendations for follow-up procedures.
- Previous studies have documented low rates of adherence to radiologist recommendations for follow-up imaging (possibly as low as 50%), creating the uncomfortable possibility of missed opportunities that could have major patient-care ramifications.
The dilemma can be compounded with the use of structured note templates in EHRs, as improper use or modification of these macros can lead to missed notifications.
- To address the problem, Parkland clinicians developed an AI agent based on a pretrained open-source large language model (Meta’s LLM Llama 3 70B) that reviews clinical impressions, extracts important details for follow-up, and integrates its findings into departmental workflow to enable patient outreach.
In tests on 10k radiologist notes, Parkland researchers found that their AI agent…
- Had an overall detection rate of ~5.1%, slightly lower than other published studies (8% to 12%).
- Had far higher sensitivity than Parkland’s previous macro-based follow-up notification system (99% vs. 16%), correctly flagging 6X more cases (513 vs. 83).
- Achieved higher accuracy (99% vs. 58%), and 94% accuracy for characterizing follow-up timing, recommended procedure, and underlying abnormality.
Considering Parkland’s annual volume of 500k imaging studies, the AI agent could identify 21.5k follow-up cases a year.
- Many of these could be serious issues, such as new cancer diagnoses or pathologies that require surgical intervention.
The Takeaway
The new study shows that agentic AI isn’t some technogeek’s far-off dream – it’s a useful tool on the verge of real-world implementation, with the potential to improve patient care without overburdening radiology staff.
|
|
Redefining What’s Possible in MRI
Since 2018, BlueSeal technology from Philips has redefined what’s possible in MRI – from a bold engineering idea to the world’s first fully sealed, helium-free 1.5T MR system. Learn about the technology behind the innovation on this page.
|
|
Pioneering AI for Medical Imaging
With more than 40 clinical publications and real-world deployments, Gleamer combines scientific rigor and medical expertise to redefine AI for radiology. Learn more about the company’s pioneering suite of AI solutions on this page.
|
|
- Modality-Focused Reorg Improves Efficiency: Reorganizing a health system’s radiology operations along modality service lines rather than hospital locations could improve efficiency and lead to happier technologists. Emory University researchers described in JACR how they implemented horizontal enterprise-wide modality-based service lines that cut across individual hospitals, enabling sites to more easily balance technologist staffing and other resources. Technologist headcount grew 11%, first-year turnover fell 34%, and overall turnover plunged 55%.
- Less Plaque Still Risky for Women: Women typically have less arterial plaque than men, but their cardiovascular risk starts at lower plaque levels. That’s according to a new study in Circulation: Cardiovascular Imaging that assessed CT-derived plaque levels in 4.2k adults over two years. Women were less likely to have coronary plaque (55% vs. 75%) and had lower median plaque volume (78 mm3 vs. 156 mm3). But they had similar adverse event rates and their cardiovascular risk began rising at lower levels of plaque burden (20% vs. 28%).
- FDA Schedules Decision Support Town Hall: The FDA will hold a town hall for developers of clinical decision support software on March 11 to discuss the agency’s new guidelines for regulating CDS applications. The meeting follows guidance the agency issued in January stating that it would not regulate a CDS application as a medical device if it isn’t used to acquire, process, or analyze medical images, among other criteria.
- Abramson Tapped to Lead FDA Digital Health: Former Harrison.ai chief medical officer Rick Abramson, MD, has been named to lead the FDA’s Digital Health Center of Excellence. Abramson’s appointment comes as the agency is wrestling with how to regulate new clinical IT technologies like AI and clinical decision support software. The center was created in 2020 to provide the FDA with advice on regulatory approaches, although it does not make marketing authorization decisions.
- Physician Groups Oppose Medicare Cuts: A coalition of 38 healthcare organizations, including ASTRO, ASNC, and SCMR signed a letter backing the Efficiency Adjustment Delay Act (HR 7520). The bill aims to postpone until 2030 a 2.5% Medicare pay cut triggered by a CMS “efficiency adjustment.” CMS implemented the reduction based on the belief that technologies like AI simplify procedures; however, lawmakers and medical groups argue the cut ignores clinician burnout and isn’t supported by data on actual procedure times.
- Kickback Scheme Ends in Jail Time: Two New York men accused of paying kickbacks to doctors in exchange for patient referrals for transcranial Doppler ultrasound scans have been sentenced to jail. Timothy Doyle received 14 months in prison, while James Rausch got an eight-month sentence. The men were also ordered to pay millions in restitution for the scheme, in which Medicare paid $27M to a mobile diagnostics company that performed the scans. Both Doyle and Rausch pleaded guilty to anti-kickback charges in 2025.
- Fujifilm to Show Zero-Helium MRI at ECR 2026: Fujifilm Healthcare is developing a zero-helium MRI scanner and it plans to highlight the system at the upcoming ECR 2026 meeting. The company’s Echelon ZeroHelium system is a superconducting 1.5T scanner that requires no liquid helium to operate thanks to a novel copper cooling structure. Deep learning technology is used to suppress artifacts, shorten scan times, and improve image quality.
- GE Touts Trio of MRI Clearances: GE HealthCare is highlighting three FDA clearances for its MRI technology, two for scanners and one for workflow optimization software. The scanners include the Signa Sprint with Freelium system, a 1.5T sealed-magnet scanner with helium-free operation, and Signa Bolt, a helium-cooled 3T scanner with a powerful gradient system rated at a maximum amplitude of 80 mT/m and a slew rate of 200 T/m/s. Signa One is an AI-powered workflow ecosystem. All three solutions debuted at RSNA 2025.
- AI Helps Focus Prostate Biopsy: A key to making prostate cancer screening a reality is better biopsy targeting of suspicious cases. To that end, researchers in European Radiology tested Lucida Medical’s Prostate Intelligence AI algorithm for MRI to determine which patients are most likely to have serious disease (≥ Gleason grade group 2). In tests on 252 patients, AI at a 31% detection threshold would have avoided 28 biopsies while missing one ≥ GG2 cancer, a 143% increase in biopsies averted (from 2.8 to 6.8 cases).
- Scottish Project Tests Field-Cycling MRI: Researchers in Scotland are moving ahead with development of field-cycling imaging MRI, a type of low-field MRI scanning that can switch between field strengths to identify contrast between tissues. A group at the University of Aberdeen has been scanning volunteers with a new generation of their FCI-MRI scanner with the goal of identifying cerebral small-vessel disease and investigating the role it plays in stroke and dementia.
- SMART’s Wearable Ultrasound: The Singapore-MIT Alliance for Research and Technology launched the Wearable Imaging for Transforming Elderly Care project to develop the world’s first wearable ultrasound system for continuous 48-hour cardiovascular monitoring. Utilizing sub-micrometer 3D printing and AI-enhanced diagnostics, the technology enables real-time tracking of chronic conditions like heart failure outside hospital settings. The project aims to shift cardiac care from episodic snapshots to proactive home-based management to improve patient outcomes while reducing burden on the healthcare system.
- Mammo Rates Boom in U.K.’s NHS: The number of women attending their first mammography screening last year jumped 11% in NHS England’s breast cancer screening program (1.94M vs. 1.75M). Higher attendance is also driving more cancer detection, with the number of detected cancers up 16% (19.3k vs. 16.7k). The program’s overall screening compliance rate is now 72%, up 1.8 percentage points from the previous year. NHS England last year launched its first promotional campaign to boost screening rates.
|
|
Financial Planning for Radiologists
Every stage of a radiologist’s career brings new financial challenges and opportunities. Watch this on-demand webinar from Medality to learn how to take control of your future through smarter financial planning, decision-making around RVU-based compensation, productivity models, and private-practice economics.
|
|
Radiology Case Report
A man in his 40s presented with a known metastasis within his abdomen. Learn how contrast-enhanced MRI helped to diagnose the extent of his disease.
|
|
- Address Your Imaging Needs Today: With so many options at their disposal, imaging leaders must navigate to the solutions that meet their needs today and set them up for success tomorrow. Discover how solutions from Merge can help you achieve your vision.
- The World’s Happiest Customers – 13 Straight Years: Sectra continues to top the charts when it comes to customer satisfaction. The company recently won seven Best in KLAS awards, including the 13th straight for its Sectra PACS enterprise imaging solution. Find out why on this page.
- Discover AI-Powered Radiology Screening Solutions: Visit DeepHealth at ECR 2026 to learn more about how they are transforming population health and cancer screening with innovative AI solutions. Book a meeting today.
- New-Generation Platform for Managing Multi-Omics Data: QP-Insights from Quibim is a new-generation advanced platform for the management, storage, and analysis of large-scale multi-omics data and medical images for clinical studies and research projects. Learn more on this page.
- How AI Is Redefining Data Migration: Enlitic’s Migratek data migration services – combined with AI-enabled ENDEX data standardization – is changing the game for data migration projects. Discover how it can benefit you in this article.
- A New Direction at Mach7: Enterprise imaging company Mach7 Technologies has embarked on a new direction with recently appointed CEO Teri Thomas at the helm. Learn about the new focus in this Imaging Wire Show.
- Cut Repetitive Manual Tasks: Discover how Rad AI’s radiology reporting software helps you speak less and say more by reducing dictation times up to 50% and words dictated up to 90%. Join 9 of the top 10 radiology practices using Rad AI to improve efficiency.
- Driving Efficiency in Radiology: Radiology’s workforce is under pressure. Discover evidence-based strategies for driving efficiency without burning out your staff in this e-book from Riverain Technologies.
- The Workstation of the Future: A dedicated team of radiologists shapes every aspect of the functionality and design of MosaicOS from Mosaic Clinical Technologies. Learn how every feature was built to eliminate distractions, amplify focus, and enhance the radiologist experience.
- Meet with Visage at HIMSS 2026: Visage Imaging is not only leading imaging’s move to the cloud, they’ve defined it with their Visage 7 CloudPACS solution, which provides unparalleled speed and interpretation efficiency. Discover Visage 7 by booking a priority demo at HIMSS 2026 or drop by at booth #3753.
- Radiology Automation Simplified: CARPL is an enterprise-grade radiology AI validation and deployment platform with 250+ AI applications across 85+ AI vendors that empowers healthcare providers to access, assess, and securely integrate imaging AI in their practice. Book a demo today.
- Experience the Next Evolution: From Day 1, AGFA HealthCare has understood that striking the critical balance between clinical efficiency and quality patient care starts with the physician experience. Learn about their history of firsts on this page.
- Merge Partners with Us2.ai: A new partnership integrates Us2.ai’s cutting-edge, FDA-cleared algorithms with Merge Cardio’s advanced imaging systems to deliver AI-generated analysis and reporting of echocardiograms. Find out what it means for you today.
- Digital Radiography Designed for Freedom: United Imaging’s new uDR Aurora CX digital radiography system was designed to give you unprecedented freedom in imaging patients thanks to its new advances in computer vision, automation, and AI diagnostics.
- AI-Centric Radiology Reporting: KailoAir is a new AI-centric radiology reporting solution from Kailo Medical that combines real-time voice dictation, AI-powered prior study analysis, and structured reporting in a seamless browser-based workspace. No installation and no compromise.
|
|
|
|
|
