|
Big Prostate AI Study, Siemens’ Ultrasound Exit, and Leo’s Lung Cancer
October 15, 2026
|
|
|
|
|
Together with
|
|
|
|
“Radiologists are not losing interest in learning. They are becoming more selective about where they spend their time and money.”
|
|
Tarang Patel, MD, of Radiology One, on the annual RSNA meeting’s educational value to radiologists.
|
|
|
Is your imaging facility doing everything it can to maximize the value of data you’re acquiring every day? In this edition of The Imaging Wire Show, we spoke to Michael Sistenich of Enlitic and Ilham Gharbi of GE HealthCare about the importance of data standardization. Check it out today. – Brian Casey, Managing Editor
|
|
|
|
A new international study testing AI’s performance in analyzing prostate MRI exams could lay the groundwork for the technology’s broader role in prostate cancer screening. In the SCARLET-1 study in Radiology, researchers found that an open-source AI algorithm performed well – and consistently – across different research studies.
Prostate cancer screening stands on the cusp of population-based adoption, but concerns remain about false positives, particularly how to determine which men should undergo biopsy and which ones can be directed to PSA monitoring.
- MRI has proven invaluable for working up patients with elevated PSA levels, but it’s expensive and requires a level of radiologist expertise that’s usually only available at high-volume centers.
AI could help by automating key parts of the MRI process, enabling the modality to be offered more broadly to support prostate cancer screening.
- The SCARLET-1 study investigated AI’s potential by combining results from research studies conducted in 22 countries around the world: PRIME, STHLM3-MRI, and IP1-PROSTAGRAM.
All three studies used an updated version of the PI-CAI AI algorithm, developed as part of a challenge sponsored by the Prostate Imaging-Cancer AI consortium in 2024.
- In all, 2k patients received prostate MRI on 1.5T and 3T scanners, and the PI-CAI algorithm was used to analyze exams at different sensitivity and specificity thresholds to detect cases suspicious for prostate cancer rated at Gleason grade group ≥ 2, the threshold for clinically significant cancer.
When compared to interpretations by local radiologists, prostate AI…
- Achieved good AUC across the three studies (AUC = 0.84 to 0.89).
- Had significantly higher agreement with an external reference standard than local radiologists (13 to 16 percentage points).
- Maintained a positive net benefit across different thresholds, in particular those intended to reduce biopsies (patient must have > 30% chance of cancer).
- Predictably, sensitivity thresholds affected AI’s performance, with higher sensitivity detecting more cancers but also generating more biopsies.
The Takeaway
The SCARLET-1 study confirms that AI of prostate MRI performs as well as radiologists in real-world settings across multiple different locations. That’s important in making prostate cancer screening available in areas where specialty expertise may not be available to interpret imaging exams.
|
|
Check out Mosaic Reporting at RSNA
Mosaic Reporting is available to radiology practices, hospitals, and health systems. It runs alongside an organization’s existing PACS, so the image archive and viewer stay in place. Mosaic Reporting can be seen live at RSNA 2026: booth #5304 in the South Hall AI Showcase or through a private demo scheduled here.
|
|
Image Exchange Is Only One Part of the Workflow
Medicom helps automate the work around the transfer, so teams spend less time searching, matching, routing, and managing exceptions. See how Medicom connects imaging across systems, workflows, and destinations.
|
|
Five Years Into the Cloud – And Just Getting Started
John Muir Health in California needed help dealing with its data deluge, which became acute with the adoption of 3D breast tomosynthesis. Find out how they turned to Sectra and their cloud-based enterprise imaging management for a solution.
|
|
- Siemens Exits Radiology Ultrasound: Siemens Healthineers dropped stunning news this week: The company is exiting the market for general radiology ultrasound. Siemens said it would no longer sell well-known general imaging scanners like Acuson Sequoia, Redwood, Juniper, and Maple, instead focusing on scanners for cardiac imaging and guiding interventional procedures, like Acuson Origin, P500 (ICE), and Freestyle. Siemens once had the largest market share in general radiology ultrasound thanks to its 2000 acquisition of Acuson, but in recent years its share has fallen to the single digits.
- Pope Leo Undergoes Lung Cancer Surgery: Pope Leo XIV this week underwent surgery to remove a lung nodule that turned out to be adenocarcinoma. The Vatican didn’t explain how the nodule was found other than that it was during “recent medical examinations” and that it “was detected at a very early stage and is well localized.” While it’s unclear if Leo received CT lung cancer screening, the news drew attention to the value of early lung cancer detection. His Holiness is not known to have a smoking history.
- NLP Mines EHR for Lung Screening: To find existing patients in their health system who might be eligible for CT lung cancer screening based on their smoking histories, UC Irvine researchers developed a natural language processing (NLP) algorithm to analyze free-text notes in their EHR. In testing on 2.2k patients, the NLP algorithm found 3X more screening-eligible patients than relying on smoking history in structured EHR data. NLP was also more likely to agree with manual radiologist review than structured EHR data (84% vs. 46%).
- AI Improves CT Lung Cancer Screening: Data to be presented at next week’s CHEST 2026 conference will highlight how AI software from eyonis improved CT lung cancer screening in France. In a population of 2.2k people whose screening exams were analyzed by eyonis LCS, the algorithm turned in an AUC of 0.98, sensitivity of 93%, and specificity of 92%, suggesting it can reduce both false positives and false negatives. eyonis LCS got FDA clearance earlier this year.
- Neiman HPI Challenges Imaging Demand Study: Experts from the ACR’s Neiman HPI group are challenging a controversial study published earlier this year claiming that growth in U.S. medical imaging volume has slowed. Neiman researchers say the JAMA Health Forum article relied on outdated data (2003 through 2016) and ignored recent trends in utilization patterns and radiologist workload. It also ignored Medicare coding changes, like code bundling, that could have obscured an accurate comparison. The Neiman authors cited other studies projecting strong growth in imaging volume.
- RapidAI’s Real-World Accuracy: Despite broad adoption of RapidAI’s technology for ischemic stroke detection, evidence gaps remain in how it works in the real world. Researchers addressed some of those gaps with a new study in Clinical Radiology assessing the algorithm’s use in 481 patients with acute stroke. Compared to neuroradiologists, RapidAI had lower agreement with a reference standard of follow-up MRI and CT scans, but had higher agreement in cases with extensive ischemia, while neuroradiologists were better with mid-range cases and deep infarcts.
- Clearsense Launches Medical Image Archive: Healthcare data management company Clearsense debuted a cloud-based archive targeted at storing historical image data. Clearsense DICOM archive is designed for facilities that want to move older medical image data from higher-cost production storage environments and retire legacy archives but still maintain access to patient data. The solution integrates with existing enterprise IT systems, and clinicians can access archived studies with Clearsense’s web-based viewer.
- Music Eases Pain of MRI Cannulation: Music could help make MRI scans more comfortable for patients — but the type matters. In all, 204 patients had venous puncture and cannulation before a non-emergency MR scan. Those listening to their favorite music or Mozart reported less pain than those listening to no music at all or tunes specifically made for relaxation, but Mozart only helped those with preexisting pain.
- CT of Beer Bottle Assaults: Just how dangerous is it to attack someone with a broken beer bottle? Swiss researchers investigated this question in a simulation study that mimicked attacks with different types of intact and broken beer bottles. CT was used to scan broken bottles, and researchers found that hand injuries would be more common in stabbing events with broken bottles than striking events with intact bottles. This matters because under Swiss law breaking a bottle before an attack could incur more severe punishment.
- Home-Buying Handbook for Radiologists: Radiologists will interpret millions of images during their careers, building up a reflex for decision-making. Still, that reflex isn’t easy to apply to personal decisions like home-buying, especially when they face debt and lack of financial training. That’s why an article in Seminars in Ultrasound, CT and MRI is valuable, providing financial guidance on the home-buying process for radiologists. The review covers buying versus renting, financing, closing, payments, and more, while differentiating between the very different financial landscapes of trainees and attending physicians.
- What’s New at RSNA 2026: RSNA 2026 is less than seven weeks away, and the society announced a range of new features and attractions for this year. An Innovation Park will be a new highlight in the South Hall, including a Startup Showcase where attendees can learn about new companies, and a First-Time Exhibitor Pavilion. The AI Showcase will return, with over 100 companies exhibiting. And RSNA will continue its popular Parks concept with several themed areas, most importantly the Bark Park with friendly and energetic dogs.
|
|
How AI is Unlocking Opportunistic Screening
Routine imaging already contains preventive health information patients often never receive, and AI is making it possible to surface that data. Learn how CARPL can help you implement opportunistic screening on this page.
|
|
End-to-End Prostate Workflow Management
Find out how Quibim’s QP-Prostate solution provides a comprehensive, end-to-end management workflow for prostate cancer care, supporting clinicians from the earliest stages of image acquisition through diagnosis, patient management, and follow-up.
|
|
What If Your Biggest Operational Constraint Isn’t Your Radiologists?
Many practices continue adding people while the real bottleneck is how work is coordinated across the enterprise. Learn how leading radiology groups increased throughput, reduced burnout, and gained radiologist capacity through operational transformation.
|
|
- How AI Powers Lung Cancer Screening: Discover how DeepHealth’s AI and workflow applications are helping radiologists report findings efficiently and with consistency in the U.K. national lung cancer screening program, finding cancers earlier at more treatable stages.
- Many VNAs Are Just Bigger PACS Archives: Vendor neutral is a claim, not a checkbox. This guide separates true neutrality from an expanded PACS archive, shows where enterprise imaging savings actually come from, and names five strategic moves the approach unlocks. Read the enterprise imaging guide.
- Advanced Women’s Health with Smarter Breast Imaging: Meeting the demands of advanced women’s health requires an imaging ecosystem that helps radiologists work efficiently, supports diagnostic confidence, and expands access to specialized breast imaging expertise. Discover how Fujifilm’s comprehensive portfolio of women’s imaging solutions can help.
- Meet Rad AI at RSNA 2026: The next era of radiology is taking shape. Meet with Rad AI at RSNA 2026 to see what AI-native reporting workflows can make possible. Book a meeting.
- Radiology Without Limits: Watch this video from Visage Imaging to learn how their Visage 7 solution enables you to achieve radiology without limits – performance, reliability, and innovation.
- Unlock Next-Level Diagnostic Possibilities: Photonova Spectra from GE HealthCare is designed to realize the full potential of photon-counting CT in oncology, cardiology, neurology, and more. Learn more about the difference its Deep Silicon technology makes on this page.
- The Heart of a 30-Year Relationship: Regional Medical Imaging (RMI) has relied on Merge for its enterprise imaging needs for over 30 years. Learn how Merge gives RMI the scalability and flexibility to keep up with growth, while Merge’s cloud solution helps offload strain on the network.
- AI Echo for Hypertrophic Cardiomyopathy: Hypertrophic cardiomyopathy is a leading cause of sudden cardiac death in the young. It is now treatable in the era of cardiac myosin inhibitors, yet remains substantially underdiagnosed. Learn how AI echo with Us2.ai can help.
- Elevating Outpatient Imaging in Texas: River Oaks MRI & Diagnostic in Texas was founded on a simple but powerful idea: to bring high-quality, accessible imaging to the local community. Learn how they turned to United Imaging to help realize their vision.
- 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.
- Fewer Biopsies, Better Accuracy: AI is converging with TI-RADS and BI-RADS in ways that go beyond automation. Read this article from Kailo Medical to learn how structured reporting is reducing unnecessary biopsies, improving consistency, and reclaiming clinical time.
- Data that’s Correct, Complete, and Consistent: ENDEX from Enlitic standardizes your DICOM imaging data with AI precision, so every study is labeled right and ready to use. Learn how it can benefit your radiology practice today.
- Don’t Leave Your Patients in the Dark: Top institutions like Duke and Northwell Health are using patient-friendly radiology reports from Scanslated to boost patient engagement and satisfaction. Discover how Scanslated can work for you today.
- A Paradigm Shift in Imaging Information: Have you ever wanted instant access in the palm of your hand to real clinical cases, innovative MR technologies, and quality customer support to guide you in finding the right MR solution? Check out the Philips MR Imaging App today.
- Increase Radiologist Productivity in DEXA Reporting: Manually dictating DEXA measurements into structured reports is time-consuming and creates unnecessary workload for radiologists. In this case study, discover how Tower Saint John’s Imaging used Altamont Software’s Passport SR to eliminate manual dictation of DEXA measurements.
- A New Resource for Radiology Jobs: Check out the new Job Boards from Medality to gain access to newly posted positions for radiologists, residents, and fellows. If you’re an employer, post your first job for no charge to reach Medality’s network of over 40,000 monthly users.
- The Business Case for Modernizing Medical Imaging: Explore the business case for modernizing medical imaging with Intelerad’s IntelePACS and InteleOrchestrator. Read the white paper to learn how healthcare organizations can improve operational efficiency, diagnostic quality, and cost management while delivering measurable business value.
- CAC Reimbursement for Routine Chest CT: The new Medicare code G0680 brings reimbursement for coronary artery calcium (CAC), enabling health systems to transform routine imaging into a proactive cardiovascular screening tool. Use Riverain’s customizable ROI calculator to demonstrate its potential financial impact on your operations.
|
|
|
|
|
