|
Mammo Risk Prediction, Gen AI Reporting, and Co-Pay Lawsuit
June 9, 2025
|
|
|
|
|
Together with
|
|
|
|
“If AI was a baseball game, people would still be showing up at the park. We’re still early in the game.”
|
|
Insight Links CEO and Boston Red Sox fan Jake Fishman, discussing radiology AI adoption on CARPL’s Unboxing AI show.
|
|
|
|
Artificial intelligence is beginning to show that it can not only detect breast cancer on mammograms, but it can predict a patient’s future risk of cancer. A new study in JAMA Network Open showed that a U.S. university’s homegrown AI algorithm worked well in predicting breast cancer risk across diverse ethnic groups.
Breast cancer screening traditionally has used a one-size-fits-all model based on age for determining who gets mammography.
- But screening might be better tailored to a woman’s risk, which can be calculated from various clinical factors like breast density and family history.
At the same time, research into mammography AI has uncovered an interesting phenomenon – AI algorithms can predict whether a woman will develop breast cancer later in life even if her current mammograms are normal.
The new study involves a risk prediction algorithm developed at Washington University School of Medicine in St. Louis that uses AI to analyze subtle differences and changes in mammograms over time, including texture, calcification, and breast asymmetry.
- The algorithm then generates a mammogram risk score that can indicate the risk of developing a new tumor.
In clinical trials in British Columbia, the algorithm was used to analyze full-field digital mammograms of 206.9k women aged 40-74, with up to four years of prior mammograms available. Results were as follows …
- The algorithm had an AUROC of 0.78 for predicting cancer over the next five years.
- Performance was higher for women older than 50 compared to 40-50 (AUROC of 0.80 vs. 0.76).
- Performance was consistent across women of different races.
- 9% of women had a five-year risk higher than 3%.
The algorithm’s inclusion of multiple mammography screening rounds is a major advantage over algorithms that use a single mammogram as it can capture changes in the breast over time.
- The model also showed consistent performance across ethnic groups, a problem that has befallen other risk prediction algorithms trained mostly on data from White women.
The Takeaway
The new study advances the field of breast cancer risk prediction with a powerful new approach that supports the concept of more tailored screening. This could make mammography even more effective than the one-size-fits-all approach used for decades.
|
|
Catch What You’ve Missed on Unboxing AI
Missed an episode of Unboxing AI, CARPL’s video series on AI in radiology? Check out all the past episodes on their YouTube channel.
|
|
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.
|
|
AI-Based Automated Echo Measurements
Discover how researchers improved sonographer workflow using AI-based automated echocardiography measurements in the AI-ECHO randomized crossover trial on this page from Us2.ai.
|
|
- Generative AI Aids X-Ray Reporting: Score another win for generative AI-assisted radiology reporting. Northwestern University researchers writing in JAMA Network Open used their homegrown gen AI algorithm to analyze 24k plain radiographs and produce draft reports that were edited and verified by radiologists. Radiologist interpretation times with gen AI were 16% faster (160 vs. 189 seconds), and peer review of 800 studies showed no difference in clinical accuracy or textual quality. Gen AI also flagged unexpected pneumothorax with 73% sensitivity and 99.9% specificity.
- Lawsuit Over Mammo Co-Pays: A Texas law firm has filed a class-action lawsuit against an insurance provider over its policy of requiring women to pay deductibles and coinsurance for diagnostic breast imaging. The firm is suing Oscar Health Insurance for violating a 2022 Texas law that requires medical insurers to pay 100% of the cost of diagnostic breast imaging. The litigation opens up a new front in the battle against breast imaging co-pays, which have been shown to discourage women from getting breast care.
- Healthcare Workforce Bounces Back: The healthcare workforce appears to be bouncing back after hitting rock bottom during the COVID-19 pandemic. A JAMA research letter documents how the number of healthcare jobs fell 6.9% from Q4 2019 to Q2 2020, but by Q3 2024 was only down 0.2% relative to predicted levels. For point of reference, non-healthcare employment fell 11.4% and 2.9%, respectively. Hospitals and skilled nursing facilities are still experiencing shortages, while physician offices have recovered more quickly.
- Location System Finds Wayward X-Ray Units: It’s 10 pm on the hospital ward. Do you know where your mobile X-ray systems are? If not, you might want to try a real-time location system, which uses wireless sensors and device tags to track equipment. In a study in Radiography, researchers in Taiwan found that their location system helped staff find mobile X-ray units faster, which paid off with 58% faster average scheduling time (12 to 5 minutes) and 25% lower equipment idle rate (16% to 12%).
- Angio-CT System Improves Stroke Treatment: Angio-CT suites – which combine a CT scanner and an angiography system – can improve outcomes for stroke. Writing in a study in Journal of Clinical Neuroscience, Japanese researchers tracked use of their Siemens Healthineers angio-CT suite in 86 patients treated with mechanical thrombectomy for acute ischemic stroke, finding the one-stop treatment protocol had lower times for door-to-puncture (53 vs. 87 minutes) and door-to-recanalization (107 vs. 174 minutes) with better outcomes at 90 days as measured by more patients with lower Rankin severity scores (55% vs. 29%).
- Fetal Echo Predicts Delivery Distress: A fetal echocardiography exam can predict clinical outcomes during delivery, in particular whether an infant will experience distress. Italian researchers performed fetal echo scans of 208 pregnant women at the start of labor, with 20 experiencing fetal distress and converting to operative delivery (caesarean or instrument-assisted vaginal birth). Of these, predictive factors included higher left ventricular ejection fraction (47% vs. 13%), increased right ventricular myocardial longitudinal strain (-16 vs. -13), and increased right ventricular endocardial longitudinal strain (-18 vs. -14).
- Dutch Hospitals Deploy Us2.ai: Two hospitals in the Netherlands have deployed AI echo technology from Us2.ai. Erasmus Medical Center and Wilhelmina Hospital installed the company’s software for automatically analyzing cardiac ultrasound images, with Erasmus MC being the first Dutch academic center to use Us2.ai and Wilhelmina the first general hospital. Us2.ai’s software automates echo tasks previously performed manually, giving clinicians more time to spend with patients.
- New AI Tools for Spine Imaging: French AI company Avicenna.AI received the CE Mark for two new AI algorithms for analyzing spinal images. CINA-VCF Quantix detects and assesses unsuspected vertebral compression fractures in patients getting CT scans for other clinical conditions, while CINA-CSpine detects and triages cervical spine fractures on CT images.
- Whole-Body Screening Firm Raises $9M: There is a new entrant in the whole-body MRI screening segment: Aeon, a Swiss startup that closed a $9.4M seed round. Aeon is developing a preventive screening test that combines whole-body MRI with genetic insights and blood biomarker tests into a single 60-minute checkup, and the company touts what it says is a 0% false-positive rate. Aeon is initially targeting the Swiss, German, and U.K. markets, and has reimbursement deals with Switzerland’s largest insurance providers.
- Brainreader Drums Up $7M: Danish brain AI software company Brainreader raised $7.3M to fund the global rollout of its Neuroreader platform, which performs automated volumetric analysis of brain MRI scans to detect conditions like Alzheimer’s disease and traumatic brain injury. Neuroreader has FDA clearance and the CE Mark, and Brainreader is targeting the U.S. market, especially given new CPT reimbursement codes for brain volumetry.
- Is Gen AI Breaking Academic Publishing? The academic publishing system is coming under strain from a deluge of papers produced by researchers using generative AI. U.K. radiologist Prof. Susan Shelmerdine reviews the situation in a LinkedIn post, noting that peer reviewers are buckling under a mass of AI-generated content, while researchers are debating the value of peer-review publishing when pre-print options like Substack, GitHub, and arXiv are available. Fortunately, Shelmerdine offers some solutions for moving forward.
- Google Unveils MedGemma: Google’s I/O developer conference brought some major updates to its AI ecosystem, such as its new open-source MedGemma model for clinical use. MedGemma’s two variants include a 4B multimodal model for image-based comprehension (radiology and pathology were specifically mentioned) and a 27B text-only model for tasks like documentation. I/O also showcased how tools like AI Mode and Vertex AI Search can streamline provider workflows by surfacing new insights from EHRs and eliminating administrative waste.
|
|
AI-Powered Early Breast Cancer Detection
DeepHealth parent RadNet is expanding its presence in mammography AI with its pending acquisition of iCAD. Find out how the transaction will accelerate AI-powered early detection and diagnosis of breast cancer on this page.
|
|
The Benefits of the Cloud for Enterprise Imaging
How are you preparing for the future of cloud-based enterprise imaging? In this downloadable e-book from Optum, learn about the benefits of cloud-based enterprise imaging and how to develop a strategy that works for you.
|
|
Stop Shipping Discs!
By pivoting to a 100% digital fulfillment model for patient images and records, you can improve their experience while significantly reducing labor and shipping costs. Find out how on this page from Clearpath.
|
|
- 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. Download it today.
- Can Whole-Body MRI Revolutionize Medical Imaging? In this episode of The Radiology Report, Medality CEO Daniel Arnold sits down with Daniel Durand, MD, of Prenuvo to explore how whole-body MRI is reshaping the future of preventive care.
- 2 Questions about AI for Radiology Leaders: Are today’s radiology AI solutions solving the right problems? And are there other solutions available for AI of brain MRI? Read this article from SpinTech MRI to learn how their STAGE solution can optimize MRI utilization.
- Maximize New CCTA Reimbursement with Philips CT 5300: Coronary CTA is the preferred noninvasive exam for detecting and ruling out CAD. Updated guidelines and improved reimbursement reinforce its value for stable or atypical chest pain. The CT 5300 from Philips delivers fast, high-quality, low-dose cardiac imaging using AI and zero-click motion correction.
- Reach New Heights with Enterprise Imaging Cloud: Embrace the potential of AGFA HealthCare’s Enterprise Imaging Cloud, a fully managed Software-as-a-Service (SaaS) solution that will transform the handling, storage, and accessibility of medical imaging data. Learn how EI Cloud can help you today.
- 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.
- Unprecedented Insights Made Possible with AI: With the largest normative dataset of whole-body imaging in the world, Prenuvo’s AI researchers partner with the best academic minds to understand – like never before – what “normal” aging means. Learn about their work today.
- The Future of AI in Healthcare: Learn from a panel of radiology key opinion leaders how AI will impact healthcare and future generations of medical professionals in this June 10 webinar hosted by Intelerad. Register now to secure your spot.
- Elevating Generative Reporting to the Web: Learn about the next leap in patient-focused diagnostic imaging with KailoFlow, the web-based evolution of Kailo Medical’s generative structured reporting platform that combines progress, innovation, and accessibility.
- Introducing Voice-Controlled Interventional X-Ray: United Imaging’s uAngio AVIVA is the industry’s first intelligent voice-controlled interventional X-ray system, enabling interventional staff to keep their focus where it belongs: on the patient. Discover AVIVA’s advantages on this page.
- Going Global with Enterprise Imaging: Merge is going global by bringing its enterprise imaging solutions to new regions, marketplaces, and customers. Learn more about its recent initiatives in Puerto Rico, the U.K., Latin America, and Canada.
- Tools for Lung Cancer Screening in Europe: As lung cancer screening programs gear up to launch across various European countries, the integration of AI nodule detection tools promises to enhance the accuracy of low-dose CT scans. Watch this video from Riverain Technologies to learn more.
- Overcoming Data Incompatibilities: Mergers and acquisitions can create data integration challenges for healthcare providers. Learn how the merger of Enlitic and Laitek can help your practice through their cutting-edge solutions that lead to successful data migrations.
- Improve Patient Engagement with Clearer Imaging Insights: When patients better understand their imaging results, they’re more engaged and confident in their care. PocketHealth’s Image Reader adds anatomical visualizations to imaging records, improving comprehension, strengthening provider-patient relationships, and driving higher satisfaction. Learn more here.
- The Advantages of Cloud-Based PACS: CloudPACS offers significant advantages to healthcare providers for enterprise imaging, including no on-premise requirements and enhanced reliability. Learn more about the advantages of CloudPACS in this talk from HIMSS 2025 by Visage Imaging’s Steve Deaton.
- AI and Neuroradiology Workflow: How can AI add value to workflows in neuroradiology? Watch this on-demand video to learn from Blackford partners how AI can help, from assisting providers in managing acute stroke patients to the impact of CPT III codes in driving adoption of brain volumetric AI solutions.
- Experience the Power of Workflow Orchestration: Mach7’s UnityVue Workflow Orchestration Platform is a groundbreaking new solution that creates a unified view of patient imaging data, speeding patient care delivery, creating more efficient workflows, and reducing radiologist stress. Experience the power of UnityVue for yourself.
- Revolutionize the Reading Experience: With intelligent automation and AI‑powered workflow, PowerScribe One from Microsoft allows radiologists to generate and communicate high‑quality, consistent reports – and get more done in less time.
|
|
|
|
|
