|
Lunit Acquires Prognosia, Mammo AI, and MRI for ARIA
September 4, 2025
|
|
|
|
|
Together with
|
|
|
|
“[R]adiologists have internalized a medico-legal truth. It’s safer to suggest a follow-up than risk being sued for missing something rare. For AI, this is a labeling nightmare.”
|
|
Former AI company executive Ayushi Sinha.
|
|
|
Our webinar on integrating mammography with enterprise imaging networks is next week at 2 pm ET on Tuesday September 9. Reserve your seat today to learn from key opinion leaders how to transform your breast imaging workflows.
|
|
|
|
AI developer Lunit is ramping up its position in breast cancer risk prediction by acquiring Prognosia, the developer of a risk prediction algorithm spun out from Washington University School of Medicine in St. Louis. The move will complement Lunit and Volpara’s existing AI models for 2D and 3D mammography analysis.
Risk prediction has been touted as a better way to determine which women will develop breast cancer in coming years, and high-risk women can be managed more aggressively with more frequent screening intervals or the use of additional imaging modalities.
- Risk prediction traditionally has relied on models like Tyrer-Cuzick, which is based on clinical factors like patient age, weight, breast density, and family history.
But AI advancements have been leveraged in recent years to develop algorithms that could be more accurate than traditional models.
- One of these is Prognosia, founded in 2024 based on work conducted by Graham Colditz, MD, DrPH, and Shu (Joy) Jiang, PhD, at Washington University.
Their Prognosia Breast algorithm analyzes subtle differences and changes in 2D and 3D mammograms over time, such as texture, calcification, and breast asymmetry, to generate a score that predicts the risk of developing a new tumor.
Prognosia built on that momentum by submitting a regulatory submission to the FDA, and the application received Breakthrough Device Designation.
- In conversations with The Imaging Wire, Colditz and Jiang believe AI-based estimates like those of Prognosia Breast will eventually replace the one-size-fits-all model of breast screening, with low-risk women screened less often and high-risk women getting more attention.
Colditz and Jiang are working with the FDA on marketing authorization, and once authorized Prognosia’s algorithm will enter a segment that’s drawing increased attention from AI developers.
- The two will continue to work with Lunit as it moves Prognosia Breast into the commercialization phase and integrates the product with Lunit’s own offerings like the RiskPathways application in its Lunit Breast Suite and technologies it accessed through its acquisition of Volpara in 2024.
The Takeaway
Lunit’s acquisition of Prognosia portends exciting times ahead for breast cancer risk prediction. Armed with tools like Prognosia Breast, clinicians will soon be able to offer mammography screening protocols that are far more tailored to women’s risk profiles than what’s been available in the past.
|
|
Unifying All Your Diagnostic Images
The Mach7 eUnity enterprise diagnostic viewer can unify all your images and solve your integration needs under one universal viewing platform. Find out how you can upgrade your enterprise visualization strategy today.
|
|
The Benefits of Operational AI
Explore the transformative potential of operational AI in healthcare in this on-demand webinar hosted by Blackford. Learn from the company’s partners how AI can help your practice operate more efficiently.
|
|
- How Can AI Best Aid Mammographers? What’s the best threshold for determining whether AI tells radiologists a mammogram is suspicious for cancer? In a new paper in AJR, researchers tested ScreenPoint Medical’s Transpara algorithm at two risk thresholds – intermediate or elevated – in 24.8k women who got digital mammography or DBT. AI had high negative predictive value at elevated risk compared to radiologists (99.8% vs. 99.9%), but its recall rate was higher for DM (14% vs. 7.2%) and DBT (12.1% vs. 6.9%).
- FDA Wants Earlier MRI for ARIA: The FDA will recommend earlier MRI scans for patients being treated with the Leqembi anti-Alzheimer’s drug after a review discovered six patient deaths connected to amyloid-related imaging abnormalities with edema. ARIA-E is a known side effect of Leqembi, and MRI is already recommended to monitor treatment. But the FDA is now advising an additional MRI scan to be performed prior to the third Leqembi infusion after the review found 101 cases of serious ARIA-E, with 24 cases before the fourth Leqembi infusion.
- 4DMedical Gets Lung Software Clearance: 4DMedical received FDA clearance for CT:VQ, the company’s software for performing ventilation-perfusion with non-contrast CT scans to detect pulmonary embolism. CT:VQ targets the large market for nuclear V/Q exams, which can be cumbersome and time-consuming to perform as they require two scans in a single appointment. In contrast, CT:VQ extracts quantitative V/Q data and images from routine CT scans without radiopharmaceuticals or contrast agents.
- Is CT Overused for GI Bleeding? A new study in JAMA Network Open suggests CT angiography is overused for working up patients suspected of gastrointestinal bleeding. In 76.6k CT exams in the emergency department, the share of scans performed for GI bleeding rose 7X from 2017 to 2023 (0.09% to 0.65%), while the percentage of positive exams fell (20% to 6.3%). Physicians may order unnecessary CT exams to clear emergency patients more quickly, practice defensive medicine, or in response to patient requests.
- CAC’s Long-Term Predictive Power: A new study in Radiology offers perhaps the best long-term evidence of coronary artery calcium’s value in predicting mortality risk, and the benefits of combining lung screening with CAC scoring. Researchers from the ELCAP CT lung cancer screening project calculated CAC scores in 8.8k ELCAP participants and followed them for a median of 23 years, finding that people with the highest CAC scores had elevated risk of cardiovascular and all-cause death (HR = 1.98 and 1.70, respectively).
- CCTA Quantifies Non-Calcified Plaque: Patients with non-calcified plaque are at higher risk for cardiovascular events, but CAC scores don’t capture the risk. Coronary CT angiography can help by quantifying non-calcified plaque burden, as shown in a paper from ESC 2025. German researchers scanned 5.4k patients, of whom 67% exhibited coronary plaque and 29% had obstructive coronary artery disease. In all, 1.9% had exclusively non-calcified plaque, showing CCTA’s value in detecting non-stenosing plaque.
- Photon-Counting CT’s Double Bonus: In another study at ESC 2025, photon-counting CT showed its advantages over dual-source CT for detecting severe coronary stenosis. Researchers in Germany scanned 261 patients with suspected coronary artery disease using coronary CT angiography with both technologies, finding that photon-counting CT had a lower false-positive rate (7.7% vs. 15%) with 33% lower radiation dose (271 vs. 402 mGy⋅cm). Photon-counting CT could reduce patient referrals to invasive angiography, a known problem with CCTA due to its high sensitivity.
- Radiation Dose in Cardiac Imaging: Another presentation at ESC 2025 provided invaluable data on radiation dose from different types of cardiac imaging exams around the world. In a survey of 747 centers and 19.4k patients, median entrance dose levels were as follows: coronary calcium scoring = 1.2 mSv; PET = 2.0 mSv; SPECT = 6.5 mSv; and coronary CT angiography = 7.4 mSv. More nuclear cardiology labs than CCTA sites met targeted dose levels (80% vs. 46%), and dose levels were lowest in Western Europe.
- Cleerly Touts Quantitative CT at ESC 2025: Meanwhile, Cleerly highlighted research presented at ESC 2025 from the CONFIRM2 trial using its LABS Plaque Analysis software for generating AI-based quantitative coronary CT measurements of plaque burden. By measuring plaque burden, morphology, composition, and luminal obstruction, LABS Plaque Analysis improved the risk stratification of patients with higher AUC compared to other metrics like CAD-RADS (0.81 vs. 0.79), coronary artery calcium scores (0.79 vs. 0.70), and the DUKE Index (0.81 vs. 0.76).
- GE Launches Cardiovascular Ultrasound: GE HealthCare used ESC 2025 to launch Vivid Pioneer, a new ultra-premium cardiovascular ultrasound scanner. The scanner is based on GE’s cSound Pioneer architecture and includes 4Vc-D and 6Sc-D probes that use XDclear technology for visualizing fine anatomic structures and cardiac function. GE also highlighted its range of cardiovascular imaging technologies at the conference, including its ViewPoint EchoPilot echo automation software and CardIQ Suite cardiac CT AI software.
- FDA Clears GE Cardiac CT: In other GE HealthCare news, the FDA cleared the company’s Revolution Vibe CT scanner. The system first debuted at ECR and ACC meetings this year as an economy-level scanner that enables cardiac imaging groups to perform cardiac CT at a lower price point and that supports one-beat cardiac imaging and AI-powered image analysis tools. The first commercial system globally has been installed in France.
- Tempus Adds Quibim Prostate AI: Tempus AI is boosting its offerings for detecting prostate cancer by adding Quibim’s QP-Prostate solution to its Tempus Pixel solution. QP-Prostate provides prostate gland segmentation based on PI-RADS v2.2 guidelines, while lesion detection and risk classification of clinically significant prostate cancer is powered by Quibim’s QP-Prostate CAD algorithm.
- Us2.ai Added to deepc Platform: Us2.ai’s echocardiography AI solutions will be added to deepc’s deepcOS AI orchestration platform under a new agreement between the firms. Us2.ai’s algorithms automate the acquisition of over 150 echo measurements, from heart chamber dimensions to aortic stenosis metrics, and enable a broader spectrum of healthcare personnel to perform echo exams.
- Sectra Lands $21M U.S. Contract: Sectra landed another large enterprise image management contract in North America, this one worth $21M, to provide its Sectra One Cloud software to an unnamed “leading medical center in the U.S.” The installation comes after Sectra scored a big contract with a hospital system in Ontario, Canada.
- UnitedHealthcare Sues RP … Again: UnitedHealthcare and Radiology Partners are at legal loggerheads again. A year after putting a billing dispute to bed, UnitedHealthcare sued RP in an Arizona federal court accusing RP subsidiary Sonoran Radiology of Arizona with allegedly manipulating the federal independent dispute resolution process for surprise billing to inflate claims. The accusations are similar to litigation UnitedHealthcare filed against an RP affiliate in Florida … litigation that ended without a clear winner.
|
|
Leading the Way in AI Transparency
There’s a need to better inform radiologists about AI’s role when interpreting images and generating measurements. Visage Imaging’s Visage 7 can display text in the viewer indicating that AI was used as a diagnostic aid – find out how it works today.
|
|
AI-Enabled DICOM Data Migration
What are the key elements of DICOM data migration? Visit this page for part 2 of Enlitic’s comprehensive guide, focusing on the critical steps of data extraction, normalization, and cleaning.
|
|
AI Innovations in Lung Disease
Check out this on-demand webcast to hear executives from Riverain Technologies and GE HealthCare as they discuss AI applications developed to detect lung nodules, in particular how AI applications can be integrated into PACS.
|
|
- Enterprise Imaging in Action: Find out how Presbyterian Healthcare increased patient engagement and met regulatory requirements by image-enabling their patient portal in this downloadable white paper from Merge.
- Synoptic Reporting of Liver Masses: Contrast-enhanced ultrasound exams for focal liver lesions can be challenging to report in at-risk patients. Learn how Kailo Medical’s synoptic reporting solutions can make reporting easier while improving LI-RADS categorization.
- Unlock Next-Generation AI with Foundation Models: Learn about Microsoft’s new family of cutting-edge multimodal medical imaging foundation models designed for healthcare organizations to test, fine-tune, and build tailored AI solutions specific to their needs, while minimizing extensive compute and data requirements.
- Cutting-Edge PET/CT to Support Theranostics: Theranostics is an exciting new field that combines diagnostics and therapy. Discover how Florida Theranostics is using United Imaging’s uMI Panorama PET/CT scanner to establish a high-quality level of patient care.
- DeepHealth Completes iCAD Acquisition: DeepHealth has completed its acquisition of mammography AI developer iCAD. Discover how the combination advances DeepHealth’s mission to address clinical and operational challenges in screening and diagnosis by harnessing the power of AI and imaging.
- 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.
- 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.
- Echo AI – Revolution or Replacement? How is AI echocardiography viewed by the clinicians who use it? Clinicians note that AI echo can enhance measurement accuracy and improve workflow efficiency, and share their secrets for successful implementation. Learn more on this page from Us2.ai.
- Transforming Stroke Care with Mobile Stroke Units: When it comes to stroke, time is brain. And many providers are turning to CT-equipped mobile stroke units to slash the time from symptom onset to diagnosis and treatment. Learn more on this page from Siemens Healthineers.
- The Future of Radiology: In this episode of The Radiology Report, Medality’s Daniel Arnold sits down with Marc Gosselin, MD, from Vision Radiology for a thought-provoking conversation on burnout, balance, and the future of radiology.
- MRI Access and the Cost of Inpatient Stays: Longer inpatient stays due to delayed MRI access are a long-standing and costly issue for hospital systems. Find out how STAGE from SpinTech MRI can reduce your MRI backlog and inpatient stays by shortening brain scan times by 30%.
- A New Solution for Chest AI: Gleamer’s ChestView AI solution is a computer-aided detection (CADe) model cleared by the FDA for simultaneously detecting multiple findings on chest X-ray. Discover how it enhances explainability and confidence compared to traditional triage-focused CADt solutions.
- Innovative Mobile Radiography Solutions: The University of Vermont Medical Center prioritizes patients when it comes to advanced diagnostic imaging tools. Read how they rely on Philips for innovative mobile radiography solutions, prompt response times, and a community focus to deliver superior patient care.
- AI for Lung Cancer Diagnosis and Screening: Check out this comprehensive new eBook from Calantic by Bayer on the role of AI in lung cancer diagnosis and screening. It explores AI’s potential role in improving lung cancer screening strategies, identifying high-risk individuals, and enhancing diagnostic accuracy.
|
|
|
|
|
