|
Measuring AI’s Impact, Predicting Practice Closure, and More ASTRO News
October 1, 2026
|
|
|
|
|
Together with
|
|
|
|
“[P]ractices with high shares of [technical component] billing seem somewhat protected against forces driving consolidation. Why this is the case is unknown but could be related to higher revenue or better negotiating positions.”
|
|
Christensen EW et al, in a JACR article on radiology practice closures.
|
|
|
It’s now October, and there’s an unmistakable feeling that pumpkin spice season is fully upon us. Hard to believe that RSNA 2026 is just eight weeks away, and if you’re like us your dance card is already filling up. This could be a good time to take a deep breath of that crisp autumn air. – Brian Casey, Managing Editor
|
|
|
|
One of the criticisms of AI in radiology is that there isn’t much data on its effectiveness in real-world environments. Well, a new study in JACR aims to fill that gap by detailing how AI adoption at a large imaging network in Europe affected key radiology performance metrics.
Plenty of studies have been published on AI’s positive contribution to radiologists’ diagnostic performance.
- But in most cases this research was performed under controlled conditions, or involved a single AI algorithm working on a particular task. That’s left many wondering how well AI would perform under actual conditions.
In the new study, researchers tracked the performance of 10 AI algorithms from seven vendors that were implemented over the Incepto Medical AI orchestration platform at 3R Swiss Imaging Network, a 20-center outpatient radiology network in Switzerland.
- Over 4.5 years, researchers tracked the network’s performance before and after AI implementation for the major radiology key performance indicator, report turnaround time (TAT). They also tracked AI adoption rates and infrastructure latency, or how delays in data transfer between PACS networks affected AI usage.
In all, 389k AI-assisted imaging exams were processed over the implementation period from 2021 to 2025, with researchers finding…
- AI’s biggest impact was in high-volume modalities, reducing TAT for trauma radiography (-26%) and knee MRI (-18%).
- AI improved the network’s diagnostic capacity, performing the work of almost half a full-time-equivalent radiologist for trauma radiography alone (0.46 FTE).
- AI usage rates were high, with 91% reporting active AI adoption and 66% reporting regular use.
On the downside, latency in data transfer between PACS networks slowed down AI performance, and in some cases AI results arrived after reports were finalized – too late to make a clinical impact…
- Median total latency was 2.06 minutes per exam, with 72% attributable to data routing and tasks like fetching studies from PACS.
- AI’s “too late rate” was 7.2% overall, ranging from 13% for chest CT to 3% for knee MRI, with 6.8% for trauma X-ray.
How did the network’s radiologists feel about AI? Researchers surveyed over 50 radiologists working for the network, finding that most of the differences in before-and-after opinions weren’t statistically significant.
- The only difference was a modest gain in the perception that AI made radiologists more productive (from 2.57 to 2.94 on a five-point Likert scale).
The Takeaway
The new study fills in a major gap in real-world experience regarding radiology AI implementation. It also reveals areas for improvement, as slow data transfer rates between networks can prevent AI results from reaching radiologists in time.
|
|
End-to-End Imaging Interoperability
Basic image exchange is increasingly table stakes. The harder work happens around it: finding relevant priors, bringing in outside imaging, reconciling patient identity, and much more. In this live demo, see how Medicom manages those workflows end-to-end through one interoperability platform.
|
|
A New Solution for Radiology Reporting
Sectra Reporting delivers a fully built-in, AI-enhanced reporting experience that seamlessly connects PACS imaging data and measurements through intuitive templates. Discover how it can meet your needs today.
|
|
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.
|
|
- Predictors of Radiology Practice Closure: It’s always a good idea to control your own destiny. A new study in JACR on radiology practice closure reinforces that concept, finding that practices that owned their own equipment – and were able to bill for the technical component (TC) of imaging exams – were more likely to remain independent. Practices with TC billing were 17% less likely to close, and those with the highest shares of TC billing were 23% less likely compared to practices with no TC billing.
- Petitions Seek Ultrasound Contrast Change: The International Contrast Ultrasound Society (ICUS) filed petitions with the FDA asking the agency to change its regulations for microbubble ultrasound contrast agents. One petition requests a whole-body indication for approved agents, replacing the current organ-based approach. The second seeks to remove the black-box warnings required since 2007 for three commercially available contrast agents, Definity, Lumason, and Optison. ICUS said the warnings are based on outdated science and that new studies support their safety profiles.
- More News from ASTRO 2026: ASTRO 2026 drew to a close this week in Boston, with the latest radiation oncology research presented. A five-treatment course of stereotactic body radiation therapy (SBRT) was an effective alternative to surgery for prostate cancer, while a five-course SBRT regimen also was effective in preserving physical function before pancreatic cancer surgery. And a study from Russia found that low-dose radiation therapy was associated with 67% lower hazard of disability due to knee osteoarthritis in patients followed for almost 12 years.
- Radiation Therapy for Brain Conditions: A number of studies at ASTRO 2026 focused on neurological conditions. Patients with small cell lung cancer that spread to the brain lived longer (17 vs. 9 months) if they got focused stereotactic brain radiosurgery versus an advanced form of whole-brain radiation therapy. A fractionated radiation therapy regimen over 3-5 sessions reduced cancer recurrence after surgery for large brain metastases compared to a single session. And patients who got treatment for depression shortly after a cancer diagnosis had a 21% lower risk of cancer-specific mortality.
- Accuray’s Samsung Alliance: In other ASTRO 2026 news, Accuray entered a relationship with Samsung to add its NeuroLogica CT imaging technology to Accuray’s CyberKnife system. The combination will give CyberKnife users the ability to perform volumetric imaging during radiation therapy treatments, which can help radiation oncology practices better manage patient motion in real time, especially during robotic radiosurgery.
- IBA, Penn Launch Proton Therapy Network: Proton therapy is gaining traction worldwide, and IBA and Penn Medicine announced a joint venture during ASTRO 2026 to further speed adoption. Called the Noventra Oncology Alliance, the partnership will help healthcare providers develop and optimize programs in proton therapy and other advanced radiation oncology techniques by offering strategic and financial planning, clinical readiness monitoring, and other services.
- NorthStar Nabs Theranostics Financing: Radiopharmaceutical provider NorthStar Medical Technologies secured a growth capital facility worth up to $185M to help the company scale up its radiopharmaceutical campus to support commercial production of no-carrier-added actinium-225 (n.c.a. Ac-225) for use in cancer therapies. The financing will include $100M upfront and will help the firm transition to an electron-accelerator-based high-capacity production line for n.c.a. Ac-225 at its main campus.
- Leo Cancer Care’s Upright Rad Therapy: Leo Cancer Care used ASTRO 2026 to highlight its Marie platform for treating patients in the upright position. The first Marie patients were treated in June on a compact proton therapy system from Mevion Medical Systems, but Leo points out its technology can also be used with any fixed-beam system, including conventional photon therapy machines. Leo is also developing a fixed-beam photon system of its own that would integrate upright patient positioning and image guidance in a single package.
- Lunit’s Stockholm Screening Expansion: Lunit’s Insight MMG AI algorithm for breast cancer screening will soon be implemented across Stockholm at three major hospitals, in partnership with Sectra. In an interesting twist, Insight MMG will operate as an independent second reader for mammograms at the facilities, where wait times remain a challenge as Sweden’s shortage of breast specialists persists. Results from the ScreenTrustCAD trial in Sweden in 2023 found that radiologists using Insight MMG detected 4% more cancers than two radiologists while cutting reading time in half.
- Saphier Nomination Advances in Senate: The U.S. Senate on Wednesday voted along party lines to advance the surgeon general nomination of radiologist Nicole Saphier, MD. Her nomination now goes to the full Senate for approval. Saphier is director of breast imaging at Memorial Sloan Kettering Cancer Center in Monmouth, New Jersey, and was a frequent contributor to Fox News on medical topics before leaving the network after her nomination. She would be the first radiologist to serve as surgeon general.
- Prenuvo Premieres Research Network: Healthy people are the most common users of whole-body scans. Now, Prenuvo is leveraging data from those scans for a much broader clinical audience with a newly launched research network. The company is lending its AI research team and data from >200k whole-body MRI scans to researchers studying disease patterns beginning years before symptoms appear. Over 50 institutions are set to appear in the first batch of Prenuvo Research Network collaborators, ranging from cancer centers like City of Hope to research universities like the University of Southern California.
- Patient Concerns About Medical AI: Patients have many concerns about medical AI, but they appear to be warming up to its use in their care, with a majority of men open to autonomous AI. A new Wolters Kluwer Health survey found that strong majorities worry about health data privacy (74%) and inaccurate AI-generated answers (69%), and want medical AI responses to be validated by humans (89%). Interestingly, far more men than women are comfortable with autonomous AI making a diagnosis and recommending treatment (61% vs. 36%).
- Sectra Scores Brazil Installation: Sectra is bringing its cloud-based imaging software from Sweden to São Paulo thanks to a new partner agreement. The company signed with S&S Partners to facilitate Sectra’s entry into the largest Latin American healthcare market. Brazil is also home to one of the world’s largest decentralized, universal healthcare systems, so the Sectra One Cloud system could help speed up communication and access between providers, as well as mitigate care bottlenecks across the healthcare system.
- Physician Burnout Relief: Physician burnout is endemic throughout healthcare, but there are steps you can take to help. Some of the more effective ones are described in a new JAMA Network Open article based on interviews with 30 physicians who tried interventions that worked. Some 87% attributed improvements to active work or personal changes, including “deliberate changes in mindset, contemplative practices, taking time away, working with a therapist or coach, and prioritizing self-care.” Many also reported changing jobs or stepping away from leadership roles.
- CMS Puts Brakes on Breakthrough NTAP: CMS finalized a new rule that limits reimbursement under the New Technology Add-On Payment (NTAP) program for medical devices being reviewed in the FDA’s Breakthrough Devices program. CMS repealed an NTAP alternative pathway that expedited reimbursement for Breakthrough Devices, meaning they will now have to navigate NTAP’s traditional reimbursement pathway. This could slow the path to reimbursement for new AI solutions and could shift the balance of power from independent AI developers to large EHR vendors.
|
|
A Next-Generation Oncology Ecosystem
Quibim has launched their next-generation oncology ecosystem platform. Find out how QP-Prostate 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.
|
|
Radiology’s Biggest Challenges Don’t Occur One at a Time
Why should your solution address them one at a time? SWO simultaneously optimizes the operational factors affecting throughput, turnaround time, workload equity, radiologist capacity, and burnout – transforming how the entire practice performs.
|
|
AI-Assisted Radiology Reporting
Move beyond legacy radiology reporting with AI-assisted reporting from Mosaic Technologies. See how Mosaic Reporting can help your organization move faster today while building for tomorrow.
|
|
- Connected Imaging. Empowered Flow: Know those rare and indescribable moments at work when distractions melt away? AGFA HealthCare’s Enterprise Imaging Platform is designed to keep you in that hyper-focused state of mind all day long. Learn more about their solutions today.
- Modernize PACS Without a Rip-and-Replace Budget: The question isn’t what modernization costs. It’s what standing still costs in support contracts, migration debt, and risk you already carry. Mach7’s framework gives CIOs and imaging leaders a phased path they can defend to finance. Read the framework.
- A Long-Term Partnership: Nashville General Hospital aimed to enhance their mammography and CT systems to remain competitive, and Fujifilm stood out as the right fit. Learn how they enhanced patient care with Fujifilm’s ASPIRE Cristalle 3D mammography system and Scenaria View CT scanner.
- Improved Productivity + Efficiency = Less Burnout: With a modern reporting software, repetitive parts of reporting are automated. The results: less stress, less burnout and better performance. Find out how Rad AI Reporting can get you there. Book a demo.
- Technical Brilliance That’s a Generation Ahead: Read with the highest quality and precision at ultrafast speed using Visage Imaging’s friction-less, server-side architecture, enabling you to use Visage 7 on your favorite devices without compromise.
- The Power to Explore Further: The SIGNA Sprint MRI scanner from GE HealthCare combines exceptional power at 1.5T with brilliant intelligence from their deep-learning solutions. Learn how it can help you unlock the full clinical potential of MRI.
- 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.
- AI Detects Pulmonary Hypertension from a Single Echo Clip: Pulmonary hypertension carries a diagnostic delay of years due to symptoms that can overlap with common heart and lung diseases. But AI from Us2.ai can detect the condition from a single echocardiography clip, substantially exceeding current clinical benchmarks.
- Driving Advances in Lung Health Through Early Detection: Earlier detection of chest conditions leads to more effective treatments and patient outcomes. Learn more about lung diseases, the impact of early detection, and tools from Riverain Technologies to improve detection accuracy and efficiency.
- A New Foundation for Healthcare AI: MergeIQ from Merge provides a scalable, governed approach to healthcare AI, enabling organizations to adopt advanced capabilities without adding standalone systems, increasing IT complexity, or disrupting existing workflows. Learn more about the first MergeIQ applications today.
- 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.
- 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.
- How Cloud-Based Enterprise Imaging Accelerates Insights: Cloud-based enterprise imaging shortens the path from scan to diagnosis by centralizing data, automating workflows, and enabling AI-driven prioritization. Find out how Intelerad’s cloud-native imaging platform can help you change healthcare delivery.
- Making a Difference For Pediatric Patients and Families: A new study published by Stanford Children’s and Duke examined over a year and a half of patient feedback following the implementation of patient-friendly radiology reports from Scanslated. Learn about the positive impact Scanslated can create for your patients today.
- Elevate Your Imaging Enterprise: Altamont Software’s Connectivity Platform affords a unified and modern approach to enterprise medical image management through one powerful platform with many amazing apps. Find out how it can help your enterprise today.
- Adding AI Automation to Radiology Reporting: Reporting Pro from DeepHealth is a next-generation AI-powered solution designed to transform the way radiologists generate clinical reports and findings. Discover how it can transform your practice.
- What Everyone Should Know About Radiology: What should every medical student know about radiology? In this episode of The Joys of Radiology, a Medality Radiology Report podcast, Gautam Agrawal, MD, sits down with three Johns Hopkins radiology residents to discuss what residency actually looks like.
- Preserve Your Radiography Investment: FutureProof 20 is Philips’ commitment to support their Radiography 7300 C for 20 years, helping you keep the system performing for decades, reducing total cost of ownership over the long run and letting you focus on the patient.
|
|
|
|
|
