|
AI Risk Prediction Redux, Imaging the World Cup, and AI’s Impact
June 25, 2026
|
|
|
|
|
Together with
|
|
|
|
“Treated defensively, AI narrows us to the very tasks that are most vulnerable to automation. Treated strategically, it lets us move up the value chain and strengthen our role as the physician specialty responsible for imaging intelligence in modern healthcare.”
|
|
Christoph Wald, MD, PhD, MBA, chair of the ACR Board of Chancellors.
|
|
|
As the World Cup’s group stage draws to a conclusion, we’re starting to get some clarity on the teams that will progress to the knockout round. In radiology, new research on AI-powered breast cancer risk analysis is providing similar clarity on which women may need additional screening to achieve radiology’s ultimate goal – early disease detection. Enjoy the issue! – Brian Casey, Managing Editor
|
|
|
|
AI-based calculations of breast cancer risk derived from screening mammograms can track cancer risk as it evolves over time, giving clinicians a longitudinal tool for following patients who might need additional care. A new study in Radiology adds to the growing body of knowledge on AI-based risk analysis.
Cancer risk prediction has emerged as a promising new application for AI, as exemplified by a study earlier this month in which three commercial AI models for screening mammograms were also able to predict risk as much as six years before diagnosis.
- At least one AI model – Clairity Breast from Clairity – has received FDA clearance for image-based risk prediction, with others under review at the agency.
But most studies of AI-powered breast cancer risk prediction calculate risk at a single point in time.
- While that’s useful, a woman’s breast cancer risk can evolve with factors such as breast tissue density, which is known to change over time – thus changing their risk profile.
So authors of the current study tracked breast cancer risk longitudinally using the Mirai algorithm, an open-source model that’s been validated in previous studies as more accurate than clinical risk prediction models like Tyrer-Cusick and BCRAT.
- They retrospectively applied Mirai to 54k women who got mammograms from 2009 to 2019, and compared changes in risk scores between women who developed cancer and those who didn’t.
Researchers found…
- Median risk scores six years before diagnosis changed from 2.1 to 6.6 in women eventually diagnosed with cancer.
- Risk scores were essentially stable in women who were cancer-free (1.8 to 2.2).
- Risk scores rose at a higher annual rate longitudinally in those with cancer versus those without (1.13 vs. 0.09 per year).
- Women in the group who developed cancer tended to be older and had dense breast tissue or a personal or family history of breast cancer.
Exactly what is the AI detecting if cancer isn’t visible to radiologists reading the mammograms?
- Most likely, AI is detecting changes in patterns of breast parenchymal tissue that “may precede radiographic detection.” These changes are basically biomarkers that can be used to develop personalized screening intervals, supplemental modalities, and other preventive strategies.
The Takeaway
The new study on AI-based breast cancer risk prediction advances our understanding of how risk can be calculated far in advance of a cancer diagnosis. It’s easy to see this knowledge put to use with earlier intervention strategies that exemplify the rise of personalized medicine.
|
|
Still Managing Multiple Imaging Silos?
Consolidate imaging access and simplify clinical workflows with Mach7 enterprise imaging solutions. Modernize your imaging with Mach7 Technologies.
|
|
AI-Powered MRI for Better Efficiency
Neurological Associates of Long Island runs its MRI service six days a week, conducting 850 scans each month. Learn how they met their efficiency needs by upgrading to Fujifilm’s AI-powered ECHELON Synergy 1.5T MRI and OASIS Velocity high-field open MRI systems.
|
|
Workflow Shouldn’t Feel Like Work
Reporting friction shows up in clicks, delays, and broken concentration. Modern reporting should feel intuitive and aligned with how radiologists actually read. See how Rad AI Reporting streamlines workflow. Book a demo.
|
|
- Game Planning for the World Cup: A JACR article notes the 2026 World Cup could create a surge of imaging use by athletes, spectators, and local residents at host-city radiology departments. Imaging was the most requested service at Qatar hospitals during the 2022 World Cup, after all. Radiologists should consider where players go for care, who authorizes imaging studies, how images are transmitted, and more. The tournament is well underway, so the time to prepare may have passed, but the article’s advice holds for future events like the 2028 Summer Olympics.
- Does AI Really Save Radiologists Time? One of the selling points of radiology AI is that it will save radiologists’ time. But is that the case? In a poster presentation at SIIM 2026, researchers quantified the time savings from the rollout of Gleamer’s BoneView AI fracture detection algorithm at 20 sites in Switzerland. Across 19.5k X-rays and 59 radiologists, researchers found a 20% drop in mean reporting time, but only 37% of radiologists were faster individually. Radiologists most commonly valued AI as a safety net (72%), then as a time-saver (57%).
- Will AI Increase Healthcare Costs? AI is being pitched as a potential time-saver for radiologists, but will it end up increasing healthcare costs? That’s the suggestion of a thought-provoking article in Health Affairs by David Brailer, MD, PhD, who in the 2000s headed the U.S. government’s “meaningful use” program to boost EHR adoption. Brailer sees AI as amplifying the forces that lead to healthcare inflation in the U.S. fee-for-service system. For example, detecting cancer earlier with AI will expand the population being treated, often using new AI-discovered therapies.
- Human Factors in AI Adoption: Radiologists are concerned about more than just speed and accuracy when weighing whether to use AI tools, according to a qualitative study published in the European Journal of Radiology Open. Of the 18 radiologists interviewed by researchers, 72% prioritized usability, 83% emphasized human oversight, and 56% said patients should be informed and able to consent. The people behind the AI systems mattered, too, with 89% of respondents trusting non-commercial developers, like universities and academic medical centers, over private companies.
- Shrinking the Odds of Shortages: A new article in JACR outlines steps to prevent future shortages of breast biopsy needles following the January 2026 recall and subsequent undersupply of Hologic Brevera needles. The authors recommend a combination of strategic stockpiling to maintain 30- and 90-day buffers as well as vendor diversification to eliminate dependency on a single company. Still, they note these site-level measures are only effective alongside a greater standardization of protocols across health networks.
- Sectra Lands Canada Customer: Sectra continues to see success in Canada for its cloud-based enterprise image management solutions. The company will install its Sectra One Cloud software at Oak Valley Health, a community care organization in Ontario. The system includes Markham Stouffville Hospital, Uxbridge Hospital, and Reactivation Care Centre, which together serve about 480k patients annually. Sectra will fully manage Oak Valley’s network over the course of the five-year contract.
- Cancer Disparities Diminish: An AACR progress report released this week revealed promising reductions in cancer disparities. Cancer mortality differences between Black and white Americans dropped from 34% in 1991 to 9% in 2024, driven by decreases in relative lung cancer mortality for Black individuals. Excess mortality rates for cervical cancer in Hispanic women and stomach cancer in Asian and Pacific Islander communities also showed declines, shrinking 86% and 46%, respectively, from 2000. However, with gaps persisting, researchers emphasize that the work to fix these disparities is far from over.
- GuideAI Health Gets FDA Nod: A new AI developer has emerged on the radiology scene: GuideAI Health, which this month received FDA 510(k) clearance for an AI application for prioritizing and triaging vascular occlusion in the lower extremities based on CT scans. The company’s VascularAssist Occlusion Triage solution helps physicians diagnose peripheral vascular disease by flagging suspected occlusions. In clinical trials supporting the 510(k), VAOT had patient-level sensitivity of 94% and above for identifying patients with PAD. The company also raised $5.2M in a private placement.
- HOPPR Launches Add-On Reporting AI: AI foundation model company HOPPR is getting into the radiology reporting segment with Presto Agent, a new solution that adds AI draft reporting capabilities to existing reporting systems. Presto can be integrated with open-source, internally developed, or commercial reporting software – including PowerScribe 360 and PowerScribe One – to enable radiology practices to produce AI-generated draft reports without having to completely replace their technology stack.
- Maine Health System Hit with $23M Judgment: A jury in Maine last week awarded $23M to a man who claimed he was left paralyzed after radiologists missed a bone calcification near his spine. Robert-Michael Giordano was treated at Northern Light Health’s AR Gould Hospital in 2020 after a fall. A radiologist allegedly missed the bone calcification on a CT scan, and Giordano’s attorneys claim it led to his paralysis six weeks later. Northern Light said it would appeal the decision.
- Neko Adds Body Composition: In a sign of the growing importance of body composition biomarkers, whole-body scanning firm Neko Health will begin including body composition analysis with its Neko Health Scans. The scans will provide measures of visceral fat and body fat percentage, biomarkers that have been linked to conditions like metabolic disease, insulin resistance, and fatty liver disease. The data will be acquired with the company’s proprietary “scanning pods,” which use a combination of high-definition cameras, lasers, and radar sensors.
- Akumin Launches Prefab Imaging Centers: Akumin is launching a line of prefabricated imaging clinics that can be installed and relocated based on demand. The company’s Akumin AXIS clinics are self-contained units that occupy a niche between mobile imaging trailers and outpatient centers and can be configured with MRI, PET, or linear accelerator radiation therapy systems. Akumin signed a contract with CGS Premier of Wisconsin to produce the units as a joint venture called Mobile Healthcare Innovations.
|
|
Radiology Without Limits
Watch this video from Visage Imaging to learn how their Visage 7 solution enables you to achieve radiology without limits – performance, reliability, and innovation.
|
|
Unlock Next-Level Diagnostic Possibilities
Photonova Spectra from GE HealthCare is designed to realize the full potential of photon-counting CT in oncology, cardiology, neurology, and more. Learn more about the difference its Deep Silicon technology makes on this page.
|
|
The Power of a Smooth Go-Live
Don’t gamble on your healthcare institution’s go-live: take control of your PACS migration with ENDEX from Enlitic. Discover how ENDEX uses AI to standardize, normalize, and cleanse your imaging metadata before migration.
|
|
- Connected Imaging. Empowered Flow: Know those rare and indescribable moments at work when distractions melt away? AGFA HealthCare’s Enterprise Imaging Platform is designed to keep you in that hyper-focused state of mind all day long. Learn more about their solutions today.
- Experience Dynamic Simplicity in Fluoroscopy: Introducing LUMINOS Q.namix R and LUMINOS Q.namix T from Siemens Healthineers – truly multifunctional imaging systems designed to simplify your daily work routines and amplify your capabilities. Learn from your peers what makes LUMINOS Q.namix systems so special.
- Five Years Into the Cloud – And Just Getting Started: John Muir Health in California needed help dealing with its data deluge, which became acute with the adoption of 3D breast tomosynthesis. Find out how they turned to Sectra and their cloud-based enterprise imaging management for a solution.
- A Next-Generation Oncology Ecosystem: Quibim has launched their next-generation oncology ecosystem platform. Find out how QP-Prostate provides a comprehensive, end-to-end management workflow for prostate cancer care, supporting clinicians from the earliest stages of image acquisition through diagnosis, patient management, and follow-up.
- Rapid AI Deployment in Emergency Care: University Hospitals used CARPL to deploy AZmed’s fracture detection tool directly in the emergency department, reducing interpretation time by 30% without disrupting workflows. Learn how UH accelerated AI deployment.
- From Image Exchange to Enterprise Interoperability: Easily share, access, and exchange any medical image with solutions from Medicom. Deliver critical studies directly into the EHR to ease clinician burden, simplify your tech stack, and unlock the research potential hidden in clinical imaging data.
- 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.
- How Cloud-Based Enterprise Imaging Accelerates Insights: Cloud-based enterprise imaging shortens the path from scan to diagnosis by centralizing data, automating workflows, and enabling AI-driven prioritization. Find out how Intelerad’s cloud-native imaging platform can help you change healthcare delivery.
- Adding AI Automation to Radiology Reporting: Reporting Pro from DeepHealth is a next-generation AI-powered solution designed to transform the way radiologists generate clinical reports and findings. Discover how it can transform your practice.
- Radiology Case Report: A female in her 40s presented with right upper quadrant pain. Learn how contrast-enhanced MRI helped to provide a diagnosis.
- Smarter CT at Lower Dose: Meet Verida, the latest in Philips’ new CT fleet, built for smarter imaging, less complexity, and lower dose. Verida combines AI-powered reconstruction with advanced spectral imaging for consistent results and streamlined workflows – scan after scan.
- IT Solutions for Radiologist Efficiency: Inefficiencies in reporting are some of the biggest challenges facing radiologists today. Learn how imaging IT solutions from Altamont Software can help radiologists work more efficiently in this Imaging Wire Show video.
- Preventing Burnout in Mid-Career Radiologists: Navigating the mid-career stage in radiology presents unique challenges and growth opportunities for radiologists reaching the 10- to 20-year mark. Check out these tips from Medality for thriving in the middle years of your professional journey.
- Don’t Leave Your Patients in the Dark: Top health systems like Duke Health and Lumexa Imaging are using patient-friendly radiology reports from Scanslated to boost patient engagement and satisfaction. Discover how Scanslated can work for you today.
- One Viewer for All: Achieve ultrafast image interpretation with greater efficiency and precision with Visage 7 from Visage Imaging. Visage’s one-viewer philosophy enables all end users – from radiologists to clinicians – to access powerful tools based on clinical need.
- Reimbursement for AI-Powered CAC Scoring: Medicare reimbursement for AI-powered coronary artery calcium scoring is now available with code G0680. Find out how it can impact your practice – and your patients – in this video interview with Riverain Technologies.
- 8 Ways Merge Meets Enterprise Imaging Requirements: Merge enterprise imaging solutions deliver measurable value through continued innovation, thoughtful design, and flexible deployment. Learn how they can benefit your organization today.
- The Economics of AI-Assisted Heart Failure Diagnosis: An AI-assisted diagnostic pathway for diagnosing heart failure saved $1.4k per patient – without compromising diagnostic accuracy. Read the white paper from Us2.ai.
- KailoFlow Replaces the Patchwork: KailoFlow from Kailo Medical gives you one platform from digital patient intake to final structured report, with automated measurement transfer, built-in TI-RADS and BI-RADS calculations, and pre-drafted reporting across any device, any site.
- Power at the Point of Care: The uDR 380i Pro from United Imaging is a high-performing and agile mobile X-ray system with an ultra-narrow body design, a high-voltage generator, and the uVision Remote Console that redefines the workflow for point of care imaging.
|
|
|
|
|
