|
More Mammo AI, CEO Clarifies AI Comments, and CMS to Work with FDA
April 27, 2026
|
|
|
|
|
Together with
|
|
|
|
“We are not getting rid of a single radiologist, just for the record.”
|
|
Hospital CEO David Lubarsky, MD, one of three hospital CEOs who participated in a panel on AI and healthcare last month.
|
|
|
|
Radiologists using a commercially available mammography AI algorithm saw improved diagnostic performance in breast cancer screening, mainly due to better specificity. The study adds to a growing body of research supporting mammography AI.
Mammography screening has been one of the most promising use cases for AI, and recent randomized controlled trials have demonstrated that AI can both improve diagnostic accuracy and speed up workflows.
- But RCTs are usually performed under highly controlled conditions in high-income Western countries, and the results might not be generalizable to other countries around the world.
In the new study in Academic Radiology, researchers in Singapore tested Lunit’s Insight MMG algorithm in a retrospective review of a dataset of 302 digital mammograms that was enriched with 89 breast cancers.
- Researchers noted that many countries have a high breast cancer incidence-to-mortality ratio due to limitations in population-based screening programs, and AI potentially could help.
The authors focused on AI’s ability to improve the diagnostic performance of nine breast radiologists from four countries in Asia and North Africa who interpreted the mammograms, finding that AI assistance…
- Improved radiologist accuracy as measured by AUC (from 0.799 to 0.851).
- Generated a big jump in specificity (from 77% to 88%).
- And significantly reduced per-case image interpretation times (from 122 to 83 seconds per case).
- Without changing sensitivity at a statistically significant level (83% vs. 82%, p = 0.73).
There were some subtle differences in the current study’s findings relative to previous research, some of which were the result of using a cancer-enriched dataset rather than a screening population as would be the case in an RCT.
- The specificity improvement with AI would reduce unnecessary recalls in a population-based screening program and make mammography more cost-effective – an important consideration in countries with constrained public health budgets.
The Takeaway
The new study doesn’t have the statistical heft of a large, randomized controlled trial, but it still adds to the body of knowledge supporting AI for mammography, especially at facilities that haven’t been party to the large-scale RCTs.
|
|
Turning Clinical AI Research into Real-World Readiness
Discover how a strategic partnership between Stanford University and Radiology Partners’ Mosaic Clinical Technologies division will pioneer new methods for assessing and monitoring AI tools for medical imaging.
|
|
A Breakthrough in Imaging Data Standardization
Enlitic’s Ensight 2.2 is a breakthrough in imaging data standardization that gives health systems a clearer, more detailed understanding of imaging data, accelerating the path from implementation to impact. Find out what it can do for you today.
|
|
A Comprehensive Suite of Tools in a Single Platform
UnityVue from Mach7 Technologies offers a comprehensive suite of tools in a single platform, streamlining the entire radiology process from image acquisition to reporting. Discover what it can do for you today.
|
|
- Hospital CEO Clarifies AI/Radiologist Remarks: One of the three hospital CEOs who participated in a controversial panel on healthcare AI last month is clarifying remarks on whether they would replace radiologists with AI. David Lubarsky, MD, of Westchester Medical Center Health Network said coverage of the event misconstrued the discussion by claiming CEOs were ready to replace radiologists with AI. In actuality, they discussed how AI could be used to read basically negative scans of low-risk patients and enable radiologists to focus on high-risk cases.
- CMS to Work with FDA on Breakthrough Devices: Getting FDA approval for a breakthrough medical device is great, but what if providers can’t get paid for using it? A new CMS program may fix that. CMS and the FDA last week announced their new Regulatory Alignment for Predictable and Immediate Device program, which enables the agencies to work together so evidence generated for breakthrough FDA submissions can be used to determine Medicare coverage. The RAPID program should reduce delays between FDA market authorization and Medicare national coverage decisions.
- AI for Fracture Detection – Pro and Con: AJR continues its popular point-counterpoint series on new imaging technologies with a pair of articles on AI for fracture detection. Radiologists arguing the “con” position cite the mismatch between algorithm performance in clinical trials and the real world, and note the lack of FDA clearance of algorithms for detecting multiple musculoskeletal conditions. On the “pro” side, authors note that fracture detection algorithms already have high accuracy and will improve in the future, and are especially valuable where radiologists are not available.
- GE Moves Manganese MRI Contrast Ahead: GE HealthCare continues to advance development of an MRI contrast agent that doesn’t use gadolinium. The company last week announced that the first patient had been dosed in the LUMINA Phase 2/3 trial of mangaciclanol, a manganese-based contrast agent that has clinical performance comparable to gadolinium-based contrast agents without the environmental and patient health concerns of gadolinium. GE notes that manganese is a naturally occurring element that is already present in food; the FDA has granted mangaciclanol Fast Track status.
- MRI Connects Poor Muscle Quality to Mortality: More research is showing how MRI scans of muscle quality can predict mortality. Researchers used AMRA Medical’s AMRA Researcher software to analyze MRI scans from 894 people with chronic kidney disease in the UK Biobank trial. The software quantified adverse muscle composition, particularly low muscle volume and higher muscle fat infiltration. Researchers found that after 3.6 years, people with poor muscle quality had higher risk of all-cause mortality than those with normal muscle composition (HR = 6.17).
- SIIM Builds Bridges to Pathology: Radiology and pathology are two sides of the diagnostic medicine coin, and SIIM will unveil a bridge to pathology at the upcoming SIIM 2026 conference. The group collaborated with the Digital Pathology Association to offer a Bridge Pass that will grant attendees access to both SIIM 2026 and DPA’s Pathology Visions 2026 conference, October 16-18 in San Diego. Like radiology before it, pathology is tackling the challenge of integrating large digital images into enterprise IT systems.
- Rad Therapist Vacancies Fall: The vacancy rate for radiation therapists fell last year in the latest ASRT survey, a sign of the ongoing shortage of allied health professionals. The ASRT’s survey found that the 2025 radiation therapist vacancy rate slipped several percentage points compared to 2024 (11.4% vs. 13.6%), while the vacancy rate for medical dosimetrists also fell (6.8% vs. 9.6%). The number of budgeted full-time radiation therapists per facility also slipped slightly (8.1 vs. 8.3 positions).
- AdvaHealth Acquires FlexView: Cloud-based software developer AdvaHealth acquired Radical Imaging’s FlexView zero-footprint DICOM viewer software and is rebranding it as AdvaView. FlexView received FDA clearance in 2024 and features an open, modular, web-native architecture that also supports integration of AI tools. AdvaView will be integrated into AdvaHealth’s AdvaPACS cloud-native image management platform. As part of the acquisition, AdvaHealth has added Radical Imaging founder and CEO Rob Lewis to its board of directors. Radical Imaging remains an independent company.
- HOPPR Adds Chest AI Model: AI developer HOPPR released a vision language model for chest X-rays that turns radiographs into descriptive, structured text. The company’s MC Chest Radiography Narrative Model is designed to be a foundational software component that AI developers can integrate into their own applications for chest X-ray analysis. HOPPR believes that foundation models offer a more flexible and adaptable solution than traditional AI point solutions.
- Viz Signs Neuro AI Pact with J&J: Radiology companies are finding fertile ground for collaborations with some of healthcare’s biggest brands. The latest partnership is between Viz.ai and Johnson & Johnson, with Viz supplying its Subdural Hemorrhage solution to J&J for identifying chronic subdural hematoma. J&J in December received FDA approval for the TRUFILL n-BCA liquid embolic system for embolizing the middle meningeal artery as a treatment for cSDH as an adjunct to surgery, and Viz’s software can help identify patients who would benefit from these treatments.
- Thinner CT Slices = Better FFR: Thinner is better, at least when it comes to CT slice thickness for fractional flow reserve studies. In a European Journal of Radiology paper, German researchers tested CT-derived FFR at slice thicknesses from 0.5 mm to 1 mm in a group of 50 patients with suspected coronary artery disease. The slice-thickness sweet spot was 0.75 mm reconstruction, which compared to the gold standard of invasive FFR had 86% sensitivity versus 85% for 0.5 mm and 76% for 1 mm.
- Conavi Medical’s FDA Clearance: Toronto-based Conavi Medical received FDA 510(k) clearance for its next-generation hybrid imaging system, which simultaneously performs intravascular ultrasound and optical coherence tomography. The co-registered platform allows for a complete assessment of coronary anatomy, visualizing both deep vessel structures and high-resolution surface detail in a single pullback. Following a January catheter recall for its original Novasight system, Conavi plans a limited U.S. commercial launch for this updated technology in the second half of 2026.
- Survey Predicts Research Slowdown: Radiology researchers believe that recent U.S. government policies will hinder the advancement of radiology research. That’s according to a new study in Clinical Imaging based on a survey of 176 radiology researchers, 55% of whom were from Europe. In all, 48% expected “slower” research progress, and 26% “much slower” progress. Disrupted research funding, administrative barriers, safety concerns, and shifts of research opportunities to areas outside the U.S. were cited.
|
|
Low Dose, Remarkably Open Design
The Scenaria View CT scanner from Fujifilm Healthcare Americas is a powerful premium CT solution that provides dependable routine application capabilities, including coronary artery imaging with the Focus Edition’s optional Cardio StillShot 3D motion correction technology.
|
|
Radiologists Can Tell
They know when technology supports their workflow, and when it interrupts it. Reporting systems should adapt to radiologists, not the other way around. Discover radiologist-first reporting from Rad AI. Book a demo.
|
|
Visit Visage at SIIM 2026
At this year’s SIIM 2026, Visage Imaging will demonstrate its Visage 7 solution operating across the entire Apple ecosystem, including on Apple Silicon-powered workstations with multiple Studio Display XDRs. Book a priority demo today or drop by booth #404-408.
|
|
- Could AI Help People Live Longer? The most powerful transformation in healthcare may come not after illness appears, but through what we do before disease ever takes hold. Read this article from DeepHealth on how AI can fundamentally change the way we approach health.
- AI-Powered Referral Automation: Radiology teams are drowning in referrals, and a huge chunk of that burden is purely administrative. Kailo Medical built a solution to fix that: An AI-powered referral automation workflow that handles the full intake process. Find out how it works today.
- AI Tools for Lung Cancer Screening: CT lung cancer screening is gaining momentum around the world. Learn about AI-based nodule detection tools that can improve the accuracy of low-dose CT scans in this video from Riverain Technologies.
- Advanced Medical Imaging in Small-Town Iowa: Clarinda Regional Health Center has been a cornerstone of care in Clarinda, Iowa, since opening its doors in 1939. Learn how CRHC partnered with United Imaging to bring advanced imaging capabilities directly to its patients.
- How CHU Bordeaux Integrated AI into Their Echo Lab: Bordeaux University Hospital evaluated the real-world use of AI in echocardiography from Us2.ai. Results showed strong agreement between AI-generated and human measurements, particularly for ejection fraction and Doppler-based parameters, highlighting AI’s potential to streamline workflow and reduce variability.
- 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.
- Why ‘Ologies Can’t Work in Isolation Anymore: No diagnostic imaging department is an island. Discover how enterprise imaging platforms like Merge Imaging Suite unify radiology and clinical workflows to improve patient care and efficiency.
- Bring Your Radiology AI into Your Clinical Workflows: CARPL enables healthcare providers and researchers to develop, test, and deploy their own AI models within existing clinical infrastructure. From seamless data ingestion and de-identification to model training, packaging, and live deployment, CARPL provides an end-to-end environment tailored for radiology.
- Intelligent Imaging in Radiography: As a technologist, you face tight schedules, complex exams, and the need for consistent quality. Check out this article from Siemens Healthineers to learn more about their intelligent imaging solutions and see what experienced colleagues have to say about using them.
- Building Bridges Across Imaging Informatics: Visit Medicom at Booth #615 at SIIM 2026 to see how their automated workflows move every image to where it needs to go, connecting patients, providers, EHRs, and research teams without manual workarounds. Book your demo today.
- Accelerating Imaging Workflows in Radiology and Cardiology: Radiology and cardiology are turning to enterprise imaging platforms to break out of silos and benefit from shared medical image management. Join AGFA HealthCare to discover what this looks like in a live discussion on Tuesday, May 19 at 12 pm ET.
- Always-On Spectral CT Imaging: Philips received FDA 510(k) clearance for Verida, combining always-on spectral CT with AI reconstruction to enhance image quality, efficiency, and clinical insight. Verida enables clinicians to see more on first scan, supporting faster decisions and expanding CT across clinical applications. Learn more.
- Curiosity, Growth, and the Joys of Radiology: What makes a great radiologist? The residency program? The fellowship pedigree? The hospital name on the badge? Check out the inaugural episode of Medality’s The Joys of Radiology podcast, featuring a conversation between Marc Gosselin, MD, and Gautam Agarwal, MD.
- Preventive and Predictive Whole-Body Screening: Join Intelerad on Tuesday, April 28 at 2 pm ET for a RadEqual webinar on the evolving landscape of preventive whole-body screening. Reserve your seat today to learn how innovation in screening and diagnosis can be advanced while maintaining patient safety.
- Transform Imaging Data into Actionable Predictions: When you choose Quibim, you get more than a partner for detecting and diagnosing prostate cancer on MRI scans. Learn how they can help you transform imaging data into actionable predictions by booking a demo today.
|
|
|
|
|
