|
Early News from ECR 2026, DeepHealth Expands Again, and Lung Cancer AI
March 5, 2026
|
|
|
|
|
Together with
|
|
|
|
“The lesson: just having an approved product is not enough; scalability, a strong brand, and financial strength are indispensable to survive as an independent player.”
|
|
Kicky van Leeuwen, PhD, on recent consolidation in the radiology AI segment.
|
|
|
|
ECR 2026 opened yesterday with a light-filled opening ceremony that beautifully illustrated this year’s theme, “Rays of Knowledge.” The ceremony was conducted before an overflow audience in the Austria Center Vienna, with ECR 2026 President Prof. Minerva Becker proudly presiding over a mix of speeches, honorary awards, and musical performances for which ECR is famous.
ECR 2026 is taking place as European radiology reaches an inflection point. The region has workforce shortages that are as serious (if not more so) than the U.S., and it must also accommodate rising demand for medical imaging.
As in the U.S., artificial intelligence is being held up as a potential solution to enable radiologists to do more with less.
- In some ways, Europe is ahead of the U.S., having conducted large-scale prospective trials like MASAI to test AI’s value for tasks like breast screening. One country – Italy – has even recommended that AI be used routinely for breast screening.
But from a regulatory standpoint, skepticism toward AI may be even stronger in Europe than in the U.S.
- The European Union in 2024 implemented the AI Act to promote human-centered and trustworthy AI, and the act classifies AI algorithms as among the highest-risk devices. Some industry observers believe the act may already be slowing the introduction of new algorithms into the European market, even as the U.S. is removing regulatory guardrails on clinical AI.
Be that as it may, the ECR continues to reinforce its reputation as a forum for top-notch clinical content, and the first day of sessions did not disappoint. In particular, AI for lung cancer screening was a prominent focus, including the following sessions…
- Harrison.ai’s chest CT AI algorithm turned in 91% sensitivity for detecting pulmonary nodules in 1.1k LDCT scans, with an average of 1.12 false positives per case.
- Results from the RELIVE study of lung cancer screening in France showed that AI from Median Technologies boosted AUC for radiologists (0.843 vs. 0.828), with less experienced radiologists seeing a 4.8% AUC improvement.
- A survey of patients and clinicians in Northern Ireland found both groups were positive about using AI for lung cancer to reduce waiting times, but neither group liked the idea of autonomous AI.
- The LUNA25 challenge tested AI algorithms developed by five teams for estimating malignancy risk of lung nodules, finding that the top AI had standalone AUC performance better than the average of 75 radiologists (0.78 vs. 0.69).
- Dutch researchers tested four commercially available AI algorithms for LDCT lung screening, finding wide variation in sensitivity (77% to 92%).
- Carebot’s AI CXR software was used to analyze 96.5k chest X-rays from nine Czech hospitals over six months, finding 54 previously undiagnosed thoracic cancers.
The Takeaway
ECR 2026 continues through Sunday, and we’ll be on hand in Vienna to bring you the latest news from radiology’s premier pan-European conference. Stay tuned for our wrap-up newsletter next week, or follow along with our daily video reports on our LinkedIn and YouTube channels.
|
|
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.
|
|
AI-Empowered CT Workflow
CT systems from United Imaging are designed for high image quality and low dose, and their AI-empowered workflow enables fast and reproducible positioning, helping you image patients with confidence. Learn more on this page.
|
|
- DeepHealth Expands Again with Gleamer Buy: In a major acquisition just days before ECR 2026, RadNet acquired French AI company Gleamer for up to $267M and is folding it into its DeepHealth division. The purchase is a big boost for DeepHealth, which has grown rapidly through acquisition, such as its 2025 purchase of iCAD. DeepHealth gets access to Gleamer’s strong portfolio of X-ray fracture detection algorithms, as well as other AI solutions it has recently launched for musculoskeletal, breast, lung, and neurologic uses. Gleamer’s revenues are growing at a 90% rate and should hit $30M this year.
- Sectra to Acquire Oxipit: In another move toward AI consolidation, Sectra agreed to acquire AI developer Oxipit in an agreement announced during ECR week. Oxipit develops AI algorithms for analyzing chest X-rays, including ChestLink, a solution that operates autonomously from radiologists, for which it’s received CE Class IIb certification. Oxipit also offers AI algorithms for CT and MSK applications, which have been offered through Sectra’s Amplifier Marketplace for AI. Oxipit engineers will operate as a dedicated AI development center within Sectra’s Imaging IT Solutions division.
- Medimaps and Radiobotics Merge: Also, Medimaps Group and Radiobotics agreed to merge in a move that unites two European companies focusing on musculoskeletal AI. Medimaps offers the TBS Osteo and TBS Reveal algorithms for detecting bone fragility conditions like osteoporosis, while Radiobotics specializes in fracture detection on X-ray with its RBfracture solution. The companies will form a combined executive team and will retain their established brands while operating under the Medimaps corporate structure.
- Philips Debuts Rembra CT at ECR: A new wide-bore CT scanner called Rembra is spearheading Philips’ product introductions at this week’s ECR 2026. Rembra sports an 85cm bore that makes it well-suited for bariatric procedures and claustrophobic patients, as well as a new XD detector technology for higher-resolution images. The scanner also features a new table design that enables a Zenition 90 mobile C-arm to be brought into the scanning room for hybrid diagnostic/interventional procedures. In other ECR news, Philips launched a new Elevate Plus upgrade package for the Affiniti and Epiq ultrasound scanners with better image quality and AI-powered applications.
- Esaote Debuts Ultrasound Scanners at ECR: Esaote is launching new ultrasound scanners targeted at interventional radiology at this week’s ECR 2026. MyLab E85 GTS and MyLab C30 GTS are optimized for ultrasound-guided interventional procedures, with MyLab E85 GTS including advanced tools for better needle visualization and Esaote’s Virtual Navigator and ablation confirmation, while MyLab C30 GTS is a compact system supporting contrast ultrasound and shear-wave elastography. In MRI, Esaote is debuting the HyperSpeed AI acceleration solution and M-Score quantitative tool for opportunistic assessment of bone health during routine lumbar spine MRI exams.
- AI for CNS Imaging: First-day highlights in the scientific sessions at ECR 2026 included presentations on AI for central nervous system imaging. Swedish researchers tested Aidoc’s vessel occlusion algorithm against radiologists in the emergency setting for occlusions in 3k adults, finding comparable sensitivity (82% vs. 81%) and specificity (100% vs. 99%). A French team found brain age estimations varied greatly between MRI scanners of different manufacturers and field strengths, while Dutch researchers added Aidoc’s AI for C-spine injuries to their existing CT brain workflow, finding that for 2.6k emergency cases, it reduced workload thanks to a 99% negative predictive value.
- What Causes AI Deployment Failures? Why do AI implementations fail? Researchers found three distinct reasons in this Wednesday morning presentation at ECR 2026 (RPS 314), including: 1) Errors related to AI models, like algorithm bias and lack of testing; 2) Infrastructure failures like poor PACS/RIS integration; and 3) Human factors such as human/AI interaction and resistance to change. To avoid such failures, authors recommended adequate AI training, continuous monitoring, standardized reporting, and other solutions.
- AI Aids Fracture Detection: AI for fracture detection in real-world clinical practice was the focus of a Wednesday afternoon session. Finnish researchers found similar performance for three commercially available AI algorithms for trauma X-ray, while Italian researchers found that two other algorithms performed similarly to non-specialist radiologists for tibial plateau knee fractures. Czech researchers found AI for emergency MSK cases reduced false negatives by 55%, although false positives rose 140%. And U.K. researchers described the SAMURAI-Fracture study underway to see if AI can reduce unnecessary patient visits.
- Radiology Leads Sustainability: A set of Wednesday presentations described how radiology can take the lead in environmental sustainability. A newly developed CT power-save mode reduced power draw by 27% with a 7.2% reduction in total operational energy use, while a review of MRI scanners from the same vendor found wide variations in energy consumption. An abbreviated non-contrast MRI protocol saved up to 87% of active energy use, while another study of modality carbon emissions found ultrasound to be the lowest and MRI the highest.
- Bracco Launches AiMIFY in Europe: Bracco is using ECR 2026 as a platform to launch AiMIFY, the MRI contrast enhancement solution it developed with Subtle Medical. AiMIFY uses AI to amplify contrast enhancement on brain MRI scans using gadolinium-based contrast agents and received the CE Mark last year. Separately, Bracco signed a partnership with Avicenna.ai to develop AI solutions for contrast-enhanced CT angiography, with FDA submissions from the partnership expected in late 2026.
- Harrison.ai Adds New Partners: Harrison.ai is adding new partners to the Open Platform AI orchestration project it launched at RSNA 2025 as an alternative to commercial AI platforms. The company said that AIRAmed, Koios Medical, Lunit, and Nanox AI are joining the initiative, which gives healthcare providers access to a range of AI solutions without the markups and fees associated with commercial offerings.
- AI Recon Cuts MRI Costs: AI-based data reconstruction can cut costs and even eliminate the need for another MRI scanner. Researchers from Finland provided an update in the European Journal of Radiology on their use of Siemens Healthineers’ Deep Resolve algorithms for MRI reconstruction. Scanners using Deep Resolve saw up to a 27% reduction in sequence duration and up to 21% in total exam time, and their MRI fleet saw patient throughput fall by only 6.4% despite having one fewer scanner. The findings track with results they reported in 2024.
- Could AI Be a First Reader for Lung Screening? Italy continues to push the envelope of clinical AI adoption. In a new study in the European Journal of Radiology, researchers tested using AI as a standalone first reader for CT lung cancer screening exams in the BioMILD study. In 4.1k baseline screenings, Coreline Soft’s AI had comparable sensitivity to radiologists (91% vs. 90%), but specificity was lower (76% vs. 90%). AI reduced workload 75%, suggesting that with radiologist oversight it could be a viable first reader.
- Lung Cancer Treatment Disparities: Meanwhile, back in the U.S., a paper in JAMA Network Open found racial discrepancies in lung cancer treatment that could affect patient survival after diagnosis. In 28.3k patients diagnosed with early-stage non-small cell lung cancer from 2005 to 2019, Black patients were 8%-9% less likely to receive curative treatment than White patients over various time periods. Black patients were also less likely to receive surgical or stereotactic body radiotherapy.
- Executives Testify on AI’s Value: Healthcare executives including Rad AI Chief Innovation Officer Demetri Giannikopoulos spoke earlier this week in a U.S. House of Representatives hearing on how AI can improve Americans’ quality of life. Giannikopoulos discussed AI’s role in reducing medical errors, from areas like triage and prioritization to image interpretation, and also touched on AI’s potential impact on radiologist jobs. The hearing came as the FDA is examining ways to streamline AI regulation to promote innovation while preserving patient safety.
- Attrition Affects All Radiology Subspecialties: A new analysis of radiologist attrition – how often radiologists are exiting the workforce – found it affects all imaging subspecialities. Neiman HPI researchers writing in AJR found that U.S. radiologist attrition averaged 2.2% from 2014 to 2022, but varied from 4.3% for cardiothoracic imaging to 1% for vascular/interventional radiology. Perhaps not surprisingly, the study found years in practice to be the biggest driver of workplace exits, with cardiothoracic imaging having the largest number of senior radiologists.
- Breast Cancer’s Global Toll: Despite recent gains in breast cancer survival in developed countries, the disease continues to extract an awful toll worldwide. A new study in The Lancet Oncology documents the situation, finding that breast cancer is the leading cause of cancer-related illness and premature death in women, with 2.3M new cases and 764k deaths globally in 2023. The number of new cases worldwide will rise by one-third to over 3.5M in 2050, with deaths increasing 44% to nearly 1.4M.
- Mammo Skeptics Critique USPSTF Coverage: Mammography skeptics continue to grumble over the USPSTF’s 2024 decision to reinstate the mammography screening starting age to 40. In their latest salvo, researchers in a paper in JAMA Network Open claim that media reporting of the USPSTF’s guideline change ignored discussion of overdiagnosis and didn’t address the new guidelines in the context of informed decision-making, a practice often pushed by skeptics to “educate” patients about screening’s perceived harms.
- USPSTF Hasn’t Met in a Year: Meanwhile, an NBC News story points out that the USPSTF panel hasn’t held an in-person meeting in almost a year, with its last meeting in March 2025. The panel typically meets three times a year to review scientific research and make recommendations on preventive care like screening exams, and its decisions determine insurance reimbursement for both Medicare and private payors. The panel typically issues 20-25 recommendations a year, but in 2025 only published five.
|
|
Diagnosing Cardiac Amyloidosis with Echo AI
Diagnosing cardiac amyloidosis on echocardiography can be challenging. In a new study, echo AI algorithms from Us2.ai were used to improve an existing multiparametric CA scoring system, and also perform automated video-based amyloidosis detection.
|
|
Meet Merge at HIMSS 2026
Built with clinical and technical expertise, guided by customer insights, and personalized to your needs, Merge imaging solutions deliver reliable imaging, less complexity, and better care. Schedule a HIMSS 2026 meeting to see how Merge can help you meet your goals.
|
|
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.
|
|
- Enterprise Imaging Done Differently: Legacy radiology solutions were not designed to carry healthcare organizations into the future. From their first line of code, Mach7 Technologies was designed to meet the imaging needs of the entire healthcare enterprise. Learn more about their unique approach today.
- 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 how Visage 7 can help you by booking a priority demo at HIMSS 2026 or drop by at booth #3753.
- 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.
- Empowering Radiologists at the Point of Interpretation: Rad AI and RSNA Ventures have partnered to deliver trusted, peer-reviewed RSNA insights directly into the radiologist’s workflow — at the exact point of interpretation. Watch this on-demand video to find out how it can benefit your practice.
- Book a Meeting with Enlitic at HIMSS 2026: Enlitic empowers healthcare systems to leverage AI to enhance the quality of their medical imaging data. Learn how they can help make your data work for you by booking at meeting at HIMSS 2026, or visit them at booth #5337.
- AI Innovations in Lung Disease: Check out this on-demand webcast to hear from Riverain Technologies and GE HealthCare executives as they discuss AI applications developed to detect lung nodules, in particular how AI can be integrated into PACS.
- Join Intelerad at HIMSS 2026: Visit Intelerad at HIMSS 2026 to explore how modern imaging workflows can help healthcare organizations deliver faster answers and a better experience for both patients and clinicians. Schedule a meeting today.
- Visit Gleamer at ECR 2026: Gleamer will be showing its vision of radiology’s future with its comprehensive AI Copilot that paves the way for precision medicine. The solution has been validated in over 80 clinical studies and featured in more than 30 scientific publications. Visit them at Expo AI-09.
- Explore the Philips MRI App: Discover clinical cases at your fingertips, find MR solutions for your needs, enhance your diagnostic skills, and unlock insights and information, all in one place. Available on the Apple or Google app stores.
- 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 or stop by at Expo 506.
- A New Solution for Radiology Reporting: Sectra Reporting delivers a fully built-in, AI-enhanced reporting experience that seamlessly connects PACS imaging data and measurements through intuitive templates. Discover how it can meet your needs today.
- 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.
- Join Quibim at ECR 2026: Join Quibim at ECR 2026 to explore the latest advances in medical imaging, connect with global experts, and help shape the future of precision medicine with AI-powered imaging biomarkers. Book a demo today or visit them at Expo-X1 booth #AI-34.
- Meet Medicom at HIMSS 2026: Learn how medical image exchange solutions from Medicom can help you reduce clinical friction in this presentation at HIMSS 2026 by founder and CEO Michael Rosenberg on March 11 at 2 pm PT in the AWS In-Booth Theater booth #1823.
- A Radiology Question Bank with Analytics: Medality’s new DXIT/Core Radiology SmartBank powered by TrueLearn includes over 800 practice questions aligned to the Diagnostic Radiology In-Training and ABR Qualifying (Core) Exam Domain Blueprints. Assess your readiness for test day now.
|
|
|
|
|
