|
Doubling Lung Screening Rates, AI to Monitor AI, and Data Breach
October 16, 2025
|
|
|
|
|
Together with
|
|
|
|
“Sometimes it takes becoming the patient to reconnect with what it truly feels like to be one.”
|
|
Radiologist Corbin Pomeranz, MD, on his experience undergoing a whole-body MRI scan.
|
|
|
A new generation of artificial intelligence is stepping in to serve as a high-tech scribe for radiologists, automating and streamlining the radiology reporting process. Learn how AI-based solutions from New Lantern can weave dictated phrases into complete sentences, generate impressions based on clinical guidelines like BI-RADS, and flag errors like laterality mistakes or semantic impossibilities.
|
|
|
|
Low CT lung cancer screening rates have disappointed medical imaging professionals and public health advocates alike since the test received USPSTF recommendation over 10 years ago. But a new study shows how one health system doubled its lung cancer screening rates – to levels approaching those of more established cancer screening exams.
USPSTF recommended low-dose CT lung cancer screening in 2013, but 10 years later patient screening rates languished in the mid-teens, compared to rates of around 75% for breast and cervical cancer and above 72% for colorectal cancer.
- That means many lung cancer patients are showing up with late-stage disease, when it’s more difficult to cure. Perhaps as a result, lung cancer is expected to cause almost 125k deaths in the U.S. in 2025.
Breaking that cycle was the goal of researchers at the University of Rochester Medical Center in New York, who wrote about their experiences in a study published in NEJM Catalyst.
- They wanted to boost lung cancer screening adherence across their network of 42 locations in western New York.
So how did they do it? Success came through a combination of IT innovation and old-fashioned legwork in patient outreach. Clinicians…
- Provided evidence on lung cancer screening to primary care providers.
- Updated their EHR software to identify patients eligible for lung screening based on the daily schedule to provide screening prompts during patient visits.
- Created dashboards to guide outreach to patients due or overdue for screening exams.
- Developed an extensive follow-up program with patient navigators to facilitate recall for annual exams.
- Created a centralized pulmonary team to provide referrals for smoking cessation, conduct shared decision making for screening exams, and manage pulmonary nodules.
The program produced immediate results. In an analysis comparing screening rates in March 2022 to June 2025, researchers found…
- Lung screening rates doubled (from 33% to 72%).
- On-time completion of annual LDCT screening exceeded 94%.
- 78% of lung cancer cases in 2023 and 2024 were diagnosed at an early stage.
- There were no statistically significant differences in screening rates by patient race.
The Takeaway
The new results match up with recent findings – such as those presented at WCLC 2025 in September – underscoring the importance of reaching out to potential lung cancer screening candidates to bring them into the fold. Despite CT lung screening’s halting history, these studies show that it can be done.
|
|
Planning for Data Migration Success
When UCSF Health’s enterprise imaging team needed to bring two new hospitals into their network, a new data migration project was born. Watch this on-demand webinar to learn how UCSF ensured a successful migration by working with Laitek, an Enlitic company.
|
|
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.
|
|
What Healthcare Really Needs from AI
The AI hype cycle has flooded healthcare with promises, yet many tools fail to deliver real-world impact. Reserve your seat at this October 29 webinar hosted by Rad AI to hear healthcare leaders share their real-world experiences in making AI work.
|
|
- New Thinking on Shared Decision Making: A new literature review in CHEST Pulmonary is contributing to changing perceptions of the shared decision making process that’s required before patients can get CT lung cancer screening. Once thought to depress screening rates, the new review of 31 studies found that shared decision making can increase screening participation and doesn’t prompt screening candidates to experience conflict or regret. The findings track with a study published earlier this year.
- A High-Tech Scribe for Radiologists: A new generation of artificial intelligence is stepping in to serve as a high-tech scribe for radiologists, automating and streamlining the radiology reporting process. Learn how AI-based solutions from New Lantern can weave dictated phrases into complete sentences, generate impressions based on clinical guidelines like BI-RADS, and flag errors like laterality mistakes or semantic impossibilities.
- When AI and Radiologists Agree: In a study in Radiology: Artificial Intelligence, South Korean researchers assessed AI/radiologist agreement in 82.9k women whose mammograms were analyzed with Lunit’s Insight MMG algorithm. Not including women whose cancer was diagnosed in the first year, cases classified as positive by both AI and radiologists had the highest five-year adjusted cancer incidence rates per 1k person-years compared to if both judged mammograms as negative (37 vs. 5.9 cases). Measuring AI/radiologist agreement could have prognostic value for future cases.
- FFR-CT’s Long-Term Predictive Value: FFR-CT predicted long-term adverse cardiac events in new results in Radiology from Denmark’s ADVANCE-DK trial. Patients got FFR-CT with Heartflow’s FFRCT Analysis solution in addition to CCTA and coronary artery calcium scores. In 900 patients over a mean of seven years, those with abnormal FFR-CT were more likely to have adverse cardiovascular events (13% vs. 5.7%), while those with high CAC scores also had higher rates (13% vs. 8.2%).
- Monitoring AI with AI: What’s the best way to find out if your AI algorithm is working as intended? How about using another AI algorithm? In a paper posted to ArXiv, Stanford University researchers present their Ensembled Monitoring Model, a framework to monitor commercial AI algorithms. EMM estimates confidence in AI calculations in real time and without ground truth labels or access to internal AI components. In addition to testing AI models, EMM can be used to stratify cases by confidence in the original AI model’s prediction.
- SimonMed Reports Toll of Medusa Breach: Imaging services provider SimonMed Imaging is in the news this week for a security breach that occurred in January, when the company was hit with a cyberattack by the Medusa hacking group. SimonMed this week revealed details of the security breach, which news sources say affected 1.3M patients and involved the theft of some 200 GB of patient data. SimonMed took steps to contain the incident at the time it occurred and is working with legal authorities to investigate the breach.
- OneImaging Raises $38M: One of the biggest funding rounds in radiology this year came from a company you may not have heard of: OneImaging, which this week said it raised $38M to further develop what it calls an imaging orchestration service that matches patients with imaging providers. OneImaging was founded in November 2022 by Siemens Healthineers veteran Elan Adler, and contracts with employers to connect their employees with a network of accredited imaging centers, saving costs and streamlining the referral process.
- Cortechs.ai Buys ZepMed: Neurology AI developer Cortechs.ai acquired ZepMed, which developed the NeuroAlign CT software for segmenting, aligning, and reformatting head CT scans. NeuroAlign automatically registers head CT images with an anatomical atlas for standardized viewing, and clinical studies have shown it can improve radiologist reading efficiency in visualizing ventricular volume for clinical use cases like traumatic brain injury. Cortechs is best known for its NeuroQuant algorithm for automatic segmentation and reporting of brain MRI scans, and the ZepMed acquisition will extend its operations into CT.
- Surgical Software Gets FDA Nod: Advanced visualization software developer Surgical Theater received FDA clearance for SyncAR Spine, the company’s next-generation platform for intraoperative guidance using MRI and CT scans. SyncAR enables surgeons to visualize preoperative imaging data that’s overlaid on intraoperative CT data and integrated with Medtronic’s StealthStation to help surgeons navigate through patient anatomy during surgery.
- High-Speed Whole-Body Prostate SPECT: French researchers cut imaging times dramatically by using a high-speed whole-body SPECT system with digital CZT detectors to monitor prostate cancer treatment with lutetium-177 PSMA therapy. In a new study in JNM, Spectrum Dynamics’ Veriton-CT 200 camera was used to image lutetium-177 after therapeutic infusions, and the modality provided better prognostic data than either gallium-68 PSMA PET or PSA measurements. Whole-body SPECT-CZT scans were completed in 18 minutes versus 36-90 minutes for conventional SPECT.
- BeSound Raises $7M: A California startup called BeSound raised $6.8M in seed funding to roll out an imaging services business targeting women with dense breast tissue. BeSound’s model combines ultrasound with near-infrared photoacoustic imaging, a technology that’s been explored for breast imaging for years but that’s still not widely used. The company plans to open its first center in West Hollywood offering scans for $350 that are reviewed by a radiologist within 24-48 hours.
|
|
Adding Digital Pathology to Enterprise Imaging
In this on-demand video hosted by Mach7 Technologies, watch as a panel of industry experts discusses how to add digital pathology images into a healthcare organization’s overall enterprise imaging strategy.
|
|
Reimagining Radiology with Apple Vision Pro
Discover how Apple Vision Pro is helping to pioneer what’s possible in radiology in this special event in Chicago during RSNA 2025. Hear from key opinion leaders and Visage Imaging executives on how spatial computing is transforming radiology.
|
|
- AI for Pediatric Fracture Detection: Pediatric fractures are common but can be easily missed on radiography. Meanwhile, AI tools for fracture detection have mostly been tested in adults. Learn how Gleamer’s BoneView AI solution helped clinicians find fractures in kids in a recent research study.
- 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.
- Redefining Breast Imaging in the Enterprise Era: As breast imaging grows more complex, radiology teams need more than siloed tools. Watch this on-demand webinar hosted by AGFA HealthCare about transforming breast imaging workflows in the enterprise imaging era.
- 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.
- 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.
- Workflow Orchestration to Revolutionize Imaging: Intelligent teleradiology solutions can combat radiologist shortages with smarter workflows that reduce burnout and improve patient care. Find out how workflow orchestration solutions from Merge are making it possible.
- New-generation Platform for Managing Multi-Omics Data: QP-Insights from Quibim is a new-generation advanced platform for the management, storage, and analysis of large-scale multi-omics data and medical images for clinical studies and research projects. Learn more on this page.
- Presenting Unboxing AI: Check out CARPL’s video series, Unboxing AI, featuring experts discussing AI and its future in radiology. The next episode on October 16 features Anthony Eigier of NeuralMed – reserve your seat today.
- A Bold Transformation in Client Experience: Intelerad is transforming how it supports customers and partners with clients through a company-wide Client Obsession initiative. The company is making investments in new tools, technologies, and staff to remove friction and deliver value – find out how it works on this page.
- The Future of Fluoroscopy Is Here: The future of fluoroscopy has arrived. The LUMINOS Q.namix fluoroscopy systems from Siemens Healthineers are available on the U.S. market. Discover why they have already earned the prestigious Red Dot Design Award for intuitive design and user-centric innovation.
- Unlocking Precision – A New Era of AI-Powered CT: AI is transforming diagnostic imaging, especially in CT. Discover how Prof. Davide Ippolito is leading the way with the Philips CT 5300, pioneering ways to reduce radiation dose while improving image quality and setting a new standard for the future of CT.
- Learn a New Subspecialty in 5 Minutes a Day: Become a faster, more confident radiologist with expert-led online video courses from Medality. Gain simulated practice with the largest collection of curated, scrollable DICOM cases available anywhere. Browse their library of radiology courses today.
- Gain Clarity in MRI at Speed: Discover how STAGE from SpinTech MRI gives you better gray-white matter contrast in MRI and more efficient reads, with up to 30% faster scans on all 1.5T and 3T magnets.
- Echo AI Automation Improves Sonographer Workflow: The use of AI-based automated tools enhanced the efficiency of screening echocardiography, reducing exam times despite a 3.4-fold increase in parameters measured. Discover how it was done on this page from Us2.ai.
|
|
|
|
|
