RSNAI Monthly—September 2026 Recap

The Radiological Society of North America (RSNA) leads the charge in advancing artificial intelligence (AI) as a tool to drive excellence in patient care and healthcare delivery. RSNAI Monthly is a collection of media briefs to help news outlets stay abreast of RSNA’s latest AI initiatives.

Technical Exhibits at RSNA 2026 Will Be Premier Forum for Latest AI Advances
With more than 100 companies already registered to exhibit in the AI Showcase—and 217 planning to demonstrate AI tools on the exhibit floor—Technical Exhibits at RSNA 2026 will be a must-attend for the most promising applications in medical imaging AI. Attendees can interact with products, watch hands-on demonstrations in the AI Theater and explore practical clinical uses for AI in radiology practice. The Showcase will also house RSNA-led initiatives and research to streamline radiology workflows and improve patient care. Early-bird registration savings end October 1.

RSNA Journals Investigate Benefits, Blind Spots in Medical Imaging AI
RSNA’s flagship journal Radiology published a call to action for accelerating AI-driven transformation in medical imaging and the broader healthcare system. Original research explored how large language models and human reader expertise influence diagnostic advice in thoracic radiology, how applying GPT-5 thinking can help both generalists and subspecialists better diagnose head and neck tumors on MRI and how a deep learning model can link CT bone density measurements to brain white matter changes associated with cognitive decline.

Early September articles in RSNA’s journal Radiology: Artificial Intelligence investigated medical imaging’s “blind spots” in human and AI collaboration, a deep learning model to predict breast cancer recurrence and DeepVEST, a model that selectively removes vascular structures in breast MR images to improve lesion visibility. A special report outlined the limitations of AI-based image reconstruction and postprocessing—which can make images appear sharper, smoother, and more detailed, but can also exacerbate the disconnect between perceived image quality and the diagnostic information available.

In RSNA’s journal Radiology: Cardiothoracic Imaging, original research tested how AI-enabled coronary artery calcium CT chamber volumetry stacks up to the Agatston scoring model and the American Heart Association’s PREVENT model for assessing heart failure risk.

With its suite of six premier journals, RSNA covers the breadth of groundbreaking research, career-advancing education, and specialty-focused techniques and trends for medical imaging professionals.

RSNA 2026 Plenary Session Explores Equity and AI in Interventional Radiology
Among the plenary speakers at the 2026 RSNA annual meeting is Janice M. Newsome, M.D., who will present “From Pixels to People: Humanism, Equity, and AI in Interventional Radiology” on Tuesday, Dec. 1. See the full plenary speaker lineup.

Fall National Imaging Informatics Course Begins September 28
For more than 10 years, the Society for Imaging Informatics in Medicine Inter-National Imaging Informatics Course (NIIC) has helped imaging professionals understand the systems, technologies, and workflows that power modern imaging practice. Supported by RSNA, the Digital Pathology Association and the Association of Academic Radiology, NIIC pairs a strong foundation in general imaging informatics with dedicated Radiology and Pathology learning tracks. The fall track runs Sept. 28 – Oct. 22 and is open to professionals and trainees in radiology cardiology, dermatology, ophthalmology and other imaging-driven fields.

Knee Abnormality AI Challenge Submissions Open through October
The 2026 RSNA Knee Abnormality Detection AI Challenge is underway—and it’s the first to use both images and the text of radiology reports to train and test AI models. The dataset includes more than 5,000 knee MRI exams from 19 sites worldwide and associated radiology reports written in a dozen different languages.

MIDRC Seminar Open to Medical Community
The Medical Imaging and Data Resource Center (MIDRC), funded by the National Institute of Biomedical Imaging and hosted at the University of Chicago, is co-led by RSNA, the American College of Radiology, and the American Association of Physicists in Medicine. Held on the third Tuesday of every other month, the Seminar Series is an opportunity for members of the medical community at large to hear directly from the MIDRC team. The next session, planned for Tuesday, Nov. 17, will feature research presentations from MIDRC investigators on new and noteworthy advances, and will include a live Q&A session for all attendees. The seminar is free; registration is required.