|
Reducing CT Radiation, Replacing Your MRI, and Lung Nodule CT
October 9, 2025
|
|
|
|
|
Together with
|
|
|
|
“Over time, judges will increasingly need to decide whether physicians should be held accountable for following or ignoring AI recommendations. Liability boundaries will likely be shaped case by case as courts and regulators and the medical community gain more perspective.”
|
|
Deepika Srivastava, COO of The Doctors Company.
|
|
|
|
CT radiation dose has been one of the top radiology headlines this year due to the publication of several studies linking radiation to cancer risk. But new research offers hope that CT radiation dose can be reduced, even across large healthcare systems.
CT’s link to cancer risk has been controversial, but most established models connect low-level radiation to cancer formation.
There are lots of great technologies for reducing CT radiation dose, from photon-counting CT to adjusting scanner parameters like mA and kVp, while image reconstruction algorithms can upscale noisy low-dose images to look like higher-quality exams.
- But the problem has always been getting these technologies into the hands of clinicians – and then making sure they use them, especially across large multi-center health systems, where dose can vary even within the same network.
Taking a crack at the problem were cardiologists from Lee Health Heart Institute in Fort Myers, Florida, in a new paper in JACC: Case Reports.
- They specifically looked at radiation dose for coronary CT angiography exams, determining that based on the literature an optimal radiation dose for CCTA should be ≤ 4 mSv – lower than the system’s 6.2 mSv median dose.
So they implemented several strategies for reducing CCTA dose…
- Standardizing scanning protocols that emphasized prospective ECG gating, reduced field of view, BMI-tailored tube voltage (kVp), and elimination of redundant imaging phases.
- Setting parameters for single-source CT at 100 kVp for patients with BMI <30 and 120 kVp for BMI ≥30, with prospective scanning for 60-80% of the cardiac cycle.
- Using similar kVp settings for dual-source CT scanners, but implementing systolic imaging between 250-450 milliseconds.
How well did it work? After reviewing the program, researchers found…
- System-wide radiation dose fell 23% (4.8 vs. 6.2 mSv).
- Diagnostic quality improved as measured by the acceptance rate for FFR-CT exams (93% vs. 91%).
- Dose consistency was achieved across locations despite differences in scanner models and practices.
The Takeaway
The new study on CCTA radiation dose shows that dose can be reduced system-wide while maintaining – and even improving – diagnostic image quality. Is it a problem that the research was led by cardiologists and not radiologists? Not if you’re a patient.
|
|
Abdominal Ultrasound Worksheets and Reports in 45 Seconds
Visit Kailo Medical at booth #4555 at RSNA 2025 to discover augmented reporting that produces worksheets and reports in 45 seconds, improving accuracy, boosting efficiency, and delivering better outcomes for patients and providers alike.
|
|
Explore the Future of Imaging
Explore the future of medical imaging in 2030 in this October 9 webinar hosted by AGFA HealthCare. Learn how radiology has evolved from traditional PACS to intelligent AI-enabled platforms that integrate multiple -ologies and provide decision support and longitudinal insights.
|
|
Digital Radiography Designed for Freedom
Learn how United Imaging’s new uDR Aurora CX digital radiography system was designed to give you unprecedented freedom in imaging patients thanks to its new advances in computer vision, automation, and AI diagnostics.
|
|
- Ultra-Low-Dose PET/CT Cuts Radiation: In another dose reduction study, researchers cut CT radiation dose for PET/CT exams by 97% by using a tin filter-based imaging protocol. In a new paper in JNM, they performed FDG PET/CT scans on 29 oncology patients using a tin filter at 100 kVp and 6 mAs and compared it to a low-dose protocol without the filter at 100-120 kVp and 12-30 mAs. The ultra-low-dose protocol reduced CT radiation dose dramatically (0.059 vs. 1.93 mSv), with variation of less than 3% in standardized uptake values.
- Siemens Launches Updated PET/CT: Siemens Healthineers at this week’s EANM 2025 meeting debuted Biograph Trinion.X, the newest member of its Biograph Trinion PET/CT family. The update is based around the company’s X-Class LSO PET detectors, which improve the system’s speed, sensitivity, and scalability with better timing resolution. The detectors sport 197-picosecond time-of-flight and an extended 48cm field of view, representing a 20% improvement. Biograph Trinion systems in the field can be upgraded to the X platform, which has both the CE Mark and FDA clearance.
- How to Replace Your MRI Scanner: If it’s time for your imaging facility to level up its MRI game, a JACR article recommends looking at upgrading or refurbishing first. Researchers examined three replacement models for a 3T MRI scanner, finding that compared to buying a new system, upgrading had 20% lower total cost of ownership and refurbishing 15% lower. Greenhouse gas emissions would also be lower (-8% and -4%, respectively) if running on conventional power grids, with even more reductions on cleaner grids.
- Rad AI Joins RSNA Ventures: Rad AI signed a strategic partnership with RSNA Ventures, the technology and innovation development subsidiary that RSNA launched this month. RSNA Ventures will deliver RSNA’s peer-reviewed content for integration into Rad AI solutions being used across the U.S., giving radiologists access to high-quality content at their workstations to assist with image interpretation. Rad AI and RSNA Ventures will show how the partnership can assist radiologists in real time in demos at RSNA 2025.
- CT Surveillance for Lung Nodules: CT surveillance rather than surgery may be an appropriate management strategy for patients with pulmonary ground-glass nodules, some of which can progress to lung cancer. In a study from China in Radiology, researchers tracked both approaches in 684 patients over 10 years, finding no statistically significant difference in lung cancer-specific survival between CT surveillance and surgery in patients whose nodules did not develop solid components (95% vs. 98%, p = 0.10).
- Harrison.ai to Retire Annalise Branding: AI developer Harrison.ai is retiring the branding for its Annalise.ai offerings, which will now be known as Harrison.ai Radiology. The company is unifying its branding under a single global umbrella and has already been using the Harrison identity for some time, such as for its Harrison.rad.1 radiology-specific vision language model. The company’s pathology AI solutions will continue under its Franklin.ai brand.
- AI Improves Care of AAA Patients: Aidoc’s AI solution for detecting abdominal aortic aneurysms improved the care of AAA patients in a paper published in Annals of Vascular Surgery. Yale University researchers compared pre- and post-deployment periods for 536 patients, finding that after AI deployment a greater proportion of patients underwent initial AAA evaluation (42% vs. 18%), with a higher rate of long-term follow-up (45% vs. 30%) and scheduled appointments for long-term AAA monitoring (99% vs. 65%). There was a trend toward shorter evaluation timelines, but it wasn’t statistically significant.
- Clairity Highlights RSNA Papers: AI mammography startup Clairity emerged from stealth earlier this year after its Clairity Breast algorithm for calculating breast cancer risk got FDA de novo authorization. The company is following up on that news by highlighting a half-dozen presentations at RSNA 2025 with its technology, including one in which Clairity Breast predicted not only breast cancer but also DCIS, another using AI with 120k mammograms, a third comparing AI risk prediction to breast density-based tools, and another analyzing its performance in women under 50.
- 3DR Labs Signs HeartLung: HeartLung’s opportunistic AI solutions for bone and cardiac applications will be available through 3DR Labs under a new partnership. Users of 3DR Labs’ 3D post-processing services will have access to HeartLung’s AutoBMD tool for osteoporosis detection and AutoChamber solution for detecting enlarged cardiac chambers and left ventricular hypertrophy. Both applications can analyze CT scans acquired for other clinical indications.
- Bunkerhill’s Cardiac AI Clearance: The FDA cleared Bunkerhill Health’s AI algorithm for detecting and quantifying mitral annular calcification on routine non-gated CT scans. Called Bunkerhill MAC, the algorithm enables users to opportunistically detect MAC that might have been missed on CT scans for non-cardiac indications. The clearance makes MAC available alongside other FDA-cleared Bunkerhill algorithms for coronary artery calcification and aortic stenosis, giving users a comprehensive cardiac AI package.
- Caristo Partners with Longevity Firm: Caristo Diagnostics partnered with longevity provider Biograph to provide its CaRi-Heart and CaRi-Plaque technologies as part of a research study involving Biograph’s Black Tier members. Caristo and Biograph will enroll 100 asymptomatic people to test Caristo’s AI-based technologies for detecting early heart disease using markers like coronary inflammation and cardiac plaque on CT scans.
- MediView Series A Raises $24M: Augmented reality software developer MediView closed a $24M Series A funding round that included investments from GE HealthCare, Cleveland Clinic, and Mayo Clinic. MediView will use the funds to further commercialize its augmented reality solutions, including the XR90 augmented reality surgical navigation system, which got FDA clearance in 2023 for guiding minimally invasive procedures. The company will also expand industry partnerships, such as its partnership with GE on the OmnifyXR interventional suite.
|
|
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.
|
|
Innovation for the Imaging Workflow You Deserve
Radiologists are overwhelmed by complex systems and growing caseloads. Discover how innovative workflow orchestration from Merge integrates various PACS, RIS, and EMR systems into a single AI-driven workspace.
|
|
- The Advantages of Cloud-Based PACS: Visage Imaging’s 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 video.
- Building the Future of Radiology: Visit Medality at RSNA 2025 booth #1140 to learn how they are at the forefront of radiology practice growth and training as the simulated learning platform that everyone loves. Book a demo today.
- Save 60+ Minutes a Day: Rad AI Impressions automatically generates report impressions from dictated findings with impression language that’s individually customized to each radiologist and practice. Find out how it works today.
- All Your Data in One Place: Mach7’s Vendor Neutral Archive (VNA) is a powerful data management and workflow orchestration technology built for the future. Learn how it can help you drive better patient care by centralizing all your data in one place.
- The Power of a Smooth Go-Live: Don’t gamble on your healthcare institution’s go-live: take control of your PACS migration with ENDEX from Enlitic. Discover how ENDEX uses AI to standardize, normalize, and cleanse your imaging metadata before migration
- 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.
- It’s Time to Make AI Adoption Simple: Visit Gleamer at RSNA 2025 booth #4936 to experience a milestone moment that will reshape AI’s role in medical imaging. Expect more than a sneak peak: Expect the future.
- Innovation in Remote Radiology Scanning: Join this October 13 webinar hosted by Philips to learn how remote radiology scanning is transforming care delivery at Outpatient Imaging Associates, improving efficiency and supporting better patient outcomes.
- Radiology Case Reports: A man in his 50s presented with syncope with minor head trauma and unassociated risk factors. Find out how MRI helped provide a diagnosis in this case study.
- AI Innovations in Lung Disease: Check out this on-demand webcast to hear from Riverain Technologies and GE HealthCare executives as they discuss AI applications developed to detect lung nodules, in particular how AI can be integrated into PACS.
- Transforming Echocardiography with AI: AI is rapidly becoming part of cardiovascular medicine, with innovations moving quickly from research into clinical practice. Hear clinicians share their experiences and reflections of integrating echo AI solutions from Us2.ai into daily workflows.
- 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 9 features Dr. Anjali Agrawal of Teleradiology Solutions – reserve your seat today.
- Advanced AI for Prostate MRI: QP-Prostate from Quibim is your advanced solution for detection and diagnosis of prostate cancer from MRI scans. Discover how it streamlines your workflow by detecting suspicious lesions, segmenting the prostate, and ensuring compliance with PI-RADS V2.1 guidelines.
- AI-Powered Population Health: DeepHealth closed its acquisition of iCAD, a major step in DeepHealth’s vision to build the future of AI-powered population health. In this Imaging Wire Show, we talked to company executives Kees Wesdorp and Niccolo Stefani about the acquisition and their strategic roadmap.
|
|
|
|
|
