|
Does BMI Affect AI, Medical Device Tariffs, and ASTRO 2025 News
September 29, 2025
|
|
|
|
|
Together with
|
|
|
|
“Even if AI models become accurate enough to read scans on their own and are cleared to do so, radiologists may still find themselves busier, rather than out of a career.”
|
|
Deena Mousa, on why AI won’t replace radiologists anytime soon.
|
|
|
|
High body mass index is known to create problems for various medical imaging modalities, from CT to ultrasound. Could it also affect the accuracy of artificial intelligence algorithms? Researchers asked this question as it pertains to lung nodule detection in a new study in European Journal of Radiology.
X-ray photons attenuate as they pass through body tissue, which can decrease image quality and produce more noise.
- This is particularly a challenge for CT exams that don’t use a lot of radiation, like low-dose CT lung screening.
At the same time, AI algorithms are being developed to make LDCT screening more efficient, such as by identifying and classifying lung nodules.
- But if high BMI makes CT images noisier, will that affect AI’s performance? Researchers from the Netherlands tested the idea in 352 patients who got LDCT screening as part of the Lifelines study.
Researchers compared patients at both the high end of the BMI spectrum (mean 39.8) and low end (mean 18.7).
- Lung nodule detection by both Siemens Healthineers’ AI-Rad Companion Chest CT algorithm and a human radiologist was performed and compared.
Across the study population, researchers found…
- There was no statistically significant difference in AI’s sensitivity between high and low BMI groups (0.75 vs. 0.80, p = 0.37).
- Nor was there any difference in the human radiologist’s sensitivity (0.76 vs. 0.84, p = 0.17).
- AI had fewer false positives per scan in the high BMI group than low BMI (0.30 vs. 0.55), a difference that was statistically significant (p = 0.05).
- While the difference in false positives with the human radiologist was not statistically significant (0.05 vs. 0.16, p = 0.09).
The study authors attributed AI’s lower performance to more noise in the high BMI scans.
- They recommended that AI developers include people with both high and low BMI in datasets used for training algorithms.
The Takeaway
The results offer some comfort that patient BMI probably doesn’t have a huge effect on AI performance for nodule detection in lung screening, but it suggests a possible effect that might have achieved statistical significance with a larger sample size. More study in the area is definitely needed given the rising importance of AI for CT lung cancer screening.
|
|
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.
|
|
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.
|
|
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.
|
|
- U.S. Probes Medical Device Imports: The tariff wars could get real for manufacturers of imported medical devices, including medical imaging scanners. The U.S. Department of Commerce last week said it was investigating medical device imports under a federal law that allows the government to restrict or impose tariffs on imports that “threaten to impair” national security. Imports in question include personal protective equipment, medical consumables, and medical devices, including CT and MRI scanners. At least one imaging vendor – Philips – said it was discussing the probe with the department.
- Radiation Oncology Highlights at ASTRO 2025: ASTRO 2025 opened this weekend, with the latest developments in radiation oncology on display in San Francisco. Top research included work on a PSMA-targeting radioligand therapy for recurring prostate cancer; low-dose radiation therapy for people with knee osteoarthritis; a genomic test that can predict which patients with recurrent prostate cancer will benefit from adding hormone therapy to radiation after surgery; and a 5DCT technique to reduce breathing artifacts in patients treated for lung cancer.
- AI for MRI Rad Therapy Planning: AI is also making inroads into radiation oncology. In an ASTRO 2025 presentation, researchers discussed their development of a foundation model for 3D MRI, which increasingly is being used for radiation therapy planning and guidance. They tested the model for three MR image analysis tasks in 6.9k patients, finding that compared to older AI models, the foundation approach improved the accuracy of cancer classification, tumor and organ segmentation, and image registration (4.8%, 1%, and 4%, respectively).
- Dual-Energy CBCT for Radiation Therapy: Dual-energy CT is carving out a role in diagnostic radiology for distinguishing between tissue types based on their energy signatures. At ASTRO 2025, researchers presented work on dual-energy CBCT for radiation therapy in which a dual-layer kV detector was placed on a clinical linear accelerator. CBCT images were acquired at 120 keV for metal artifact reduction and 40 keV for soft-tissue contrast enhancement, with 49% improvement in MAR uniformity and a 170% contrast improvement in head and neck adipose tissue and muscle.
- GE Updates Rad Therapy Software: GE HealthCare launched an updated version of its Intelligent Radiation Therapy workflow management software at ASTRO 2025. Radiation oncology facilities use iRT to manage data between systems, and the new version includes better connectivity with RaySearch Laboratories’ RayStation treatment planning software. It also has new features for analytics reporting, staff scheduling, and auto-segmentation of organs, as well as a virtual reality app.
- Accuray Launches Stellar: Another vendor launching a new solution at ASTRO 2025 is radiation therapy company Accuray, which debuted Accuray Stellar, a new configuration of its Radixact treatment delivery system that combines hardware with software to expand the range of treatment modalities available, including IMRT, SBRT, and surface-guided radiation therapy. Stellar also includes newer techniques like Accuray’s Adapt LTE treatment plan evaluation tool and ClearRT helical kVCT imaging.
- RT/Ultrasound Combo Maps Radiation Dose: Researchers at ASTRO 2025 presented their real-time radiation dose tracking technology – ionizing radiation acoustic imaging – that combines radiation therapy with ultrasound. iRAI maps radiation dose during treatment by measuring acoustic signals given off by tissue as it absorbs radiation. In tests with 10 patients, iRAI detected radiation levels as low as 10 cGy, and its calculations of dose distribution and dose deposition corresponded well with treatment plans. iRAI could be integrated into treatment delivery systems to personalize treatment.
- RT Video System Keeps Kids Still: In another ASTRO presentation, Texas researchers presented results from PROMISE, a video-based program to keep children from moving during radiation therapy sessions without requiring anesthesia. An age-appropriate video was projected into the treatment system while a 3D surface imaging system monitored the child and shut off the radiation beam if they moved too much. In tests with 25 kids ages 3-7 years, 88% completed PROMISE with all of their radiation treatments, with anesthesia only used for 12%.
- One-Minute Whole-Heart MRI for Kids: It can also be a challenge to get kids to stay still in an MRI bore long enough to acquire quality cardiac images. Researchers in a paper in JCMR offer a solution with a one-minute whole-heart protocol that’s optimal for assessing congenital heart disease. The protocol uses the iron supplement ferumoxytol off-label as a contrast agent in combination with a 3D ultrashort echo time sequence, and in 38 patients produced acceptable image quality compared to the standard cardiac MRI sequence.
- Echo AI Classifies Aortic Stenosis: Us2.ai’s echocardiography AI solution was used to classify aortic stenosis severity in research presented at ASE 2025. Researchers used Us2.ai in 954 patients to grade stenosis severity and predict clinical outcomes, finding the company’s gradient boosted model performed well compared to an expert cardiologist, with high accuracy for all cases (74%) as well as low-flow cases (75%). GBM analysis outperformed the cardiologist in predicting a composite of clinical endpoints.
- Study Questions Breast AI’s Value: Breast screening is one of AI’s most promising clinical use cases, but new research throws cold water on its economic value. In a modeling study in Value in Health, researchers analyzed clinical and economic outcomes of biennial DBT screening with AI, finding that the combination reduced false-negative exams by 2.1 cases per 1k women with 50 fewer false positives. But it increased lifetime costs by $936k with an ICER of $303k per QALY, well above a $100k willingness-to-pay threshold.
- RamSoft Partners with Koios: RamSoft partnered with Koios Medical to make its Smart Ultrasound AI ultrasound decision support portfolio available to RamSoft RIS/PACS users. Koios’ solutions help radiologists identify and report cancer on breast and thyroid ultrasound scans, and will join a portfolio of women’s health applications available through RamSoft PACS that include offerings from Stana, iCAD, Therapixel, and Ikonopedia.
- Harrison.ai Lands New Contracts: Harrison.ai secured contracts to supply its AI solutions to radiology groups in Washington and Texas. In the first contract, the company partnered with Inland Imaging, a radiology practice in Spokane, Washington that serves the Pacific Northwest. Inland operates nine outpatient imaging centers and employs over 120 subspecialized radiologists. The other agreement is with Radiology Associates of North Texas, the largest radiology group in the state with over 220 radiologists.
- Why AI Isn’t Replacing Radiologists: By now, radiology has (mostly) rejected the argument that AI will replace radiologists. But does radiology’s experience hold lessons for other fields facing wholesale job destruction from AI? This question is explored in an in-depth article in Works in Progress magazine that reviews AI’s history going back to the days of computer-aided detection and explains why AI may paradoxically result in radiologists becoming busier than ever.
|
|
Cost Savings from AI for Fracture Detection
Using AI to analyze X-rays for wrist, ankle, and hip fractures in the emergency setting can save costs while improving patient care. Read how the NHS did it with Gleamer’s BoneView solution.
|
|
Easily Share Patient Images and Reports
Physicians can easily share patient images and reports from a personal worklist using Intelerad’s InteleShare Physician Portal. Discover how easily it works in this self-guided demo.
|
|
Start at the Source to Improve MRI
Looking for ways to improve MRI speed and image quality while addressing broader concerns in healthcare? The answer may lie in proven MRI physics in your existing scanner – learn how to unlock it with STAGE from SpinTech MRI.
|
|
- Top-Tier Care at Rural Hospitals: Holzer Health System in Jackson, OH, treats local patients like family. In this video, learn how United Imaging equipped Holzer Health with its uMR 570 MRI scanner, helping them to offer top-tier care.
- 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.
- Bringing Real-Time AI Echo to Clinicians: Us2.ai and deepc are bringing real-time standardized AI echo analysis and reporting to clinicians through their new partnership. Find out how Us2.ai’s software is now available within the deepcOS platform.
- What’s Next for AI for Cancer Detection? AI is transforming the fight against cancer by enabling faster and more accurate cancer detection. Read this article from DeepHealth to learn how the company is pioneering new ways to advance cancer screening and broader imaging-based care.
- Opportunistic Detection of CAC and Pulmonary Nodules: Achieve a newfound certainty of search for thoracic CT when using ClearRead CT from Riverain Technologies. It’s a natural addition for opportunistic CAC scoring and nodule detection, or as part of a CT lung cancer screening program.
- Leading the Way in AI Transparency: There’s a need to better inform radiologists about AI’s role when interpreting images and generating measurements. Visage Imaging’s Visage 7 can display text in the viewer indicating that AI was used as a diagnostic aid – find out how it works today.
- Adding Digital Pathology to Enterprise Imaging: In this on-demand video from SIIM 2025 hosted by Mach7, watch as a panel of industry experts discusses how to add digital pathology images into a healthcare organization’s overall enterprise imaging strategy.
- Radiology Case Reports: A female in her 40s without symptoms presented for screening mammography. Discover how information from contrast-enhanced MRI led to a finding of carcinoma.
- How AI Is Redefining Data Migration: Enlitic’s Migratek data migration services – combined with AI-enabled ENDEX data standardization – is changing the game for data migration projects. Discover how it can benefit you in this article.
- 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.
- Streamlining Sonographer Workflows: Alaska Radiology Associates needed to streamline sonographer workflows, so they turned to SonoReview by Kailo Medical. Learn how the solution enhanced accuracy and saved valuable time for both radiologists and sonographers.
- Solving Burnout through Teleradiology: Is your radiology staff facing burnout? Check out this case study to find out how Northern Light Medical Management addressed burnout with teleradiology solutions from Merge.
- 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.
- Purchasing a Cloud-Hosted Enterprise Imaging Solution: The decision to move your enterprise imaging to the cloud is significant. But how do you choose the right solution? Discover the 10 critical questions to ask in this guide from AGFA HealthCare.
- 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.
|
|
|
|
|
