|
Imaging Workload Jumps, AI Trust Gap, and Hinton’s Mea Culpa
May 19, 2025
|
|
|
|
|
Together with
|
|
|
|
“The predicted extinction of radiologists provides a telling case study. So far, A.I. is proving to be a powerful medical tool to increase efficiency and magnify human abilities, rather than take anyone’s job.”
|
|
From a New York Times article on the impact of AI on radiology.
|
|
|
|
Radiology’s shift to more advanced modalities like CT and MRI is increasing the burden on radiologists to interpret more complex exams. A new study in JACR documents the trend, finding that radiologist workload for inpatient imaging has risen sharply over the last 10 years.
Like many physicians, radiologists are feeling burned out from rising patient workload, personnel shortages, and declining reimbursement.
- But radiology has the added burden of being one of healthcare’s most technology-focused specialties, with new imaging modalities giving them cooler tools to work with, but at the cost of steadily increasing exam complexity.
Researchers from Brigham and Women’s Hospital have been tracking inpatient imaging utilization for the past 40 years, and the new paper provides the latest update.
- They calculated inpatient imaging volume at Brigham and Women’s from 2012 to 2023, during which 896k imaging exams were performed.
Results for the study were as follows …
- Total annual inpatient imaging volume grew 17% over 10 years (102k to 119k exams).
- Total imaging exams per patient admission (adjusted by case mix and disease severity) fell 20% due to declines in X-ray, ultrasound, and nuclear medicine.
- But imaging exams per patient admission grew for CT (19%) and MRI (21%).
- Leading to growth in CT and MRI’s combined share of all radiology global RVUs (62% to 75%).
- Hospital length of stay rose 32% (5.6 to 7.4 days), possibly due to the COVID-19 pandemic.
What does it all mean? Basically, the number of inpatient imaging exams per patient is declining when adjusted for disease severity, but radiologists are still having to work harder because the studies are more complex.
- Imaging could also be shifting from the inpatient setting to outpatient centers due to reimbursement changes aimed at shifting exams to lower-cost settings than hospitals.
One big question with the new study is the degree to which the COVID-19 pandemic skewed the results compared with previous years.
- The pandemic may have spurred more use of CT, especially given its value in providing a definitive diagnosis of SARS-CoV-2 infection.
The Takeaway
If you feel like you’re working harder than ever, the new findings show that you’re not crazy. And given radiology’s breakneck pace of innovation, it’s not likely the trends revealed in the new study will let up any time soon.
|
|
Orchestrating AI Across the Healthcare Enterprise
If you’re attending SIIM 2025, stop by booth #237 to meet the Blackford team and discover how they are orchestrating AI across the healthcare enterprise to elevate patient care.
|
|
Book a Visage Demo at SIIM 2025
Visage Imaging is trailblazing medical imaging’s SaaS move to the cloud with an open cloud philosophy based on industry standards and multi-cloud support. Learn more by registering for a priority demo at SIIM 2025 or visit them at booths #627-631.
|
|
Patient Expectations Are Rising. Is Your Imaging Strategy Keeping Up?
At SIIM 2025, leaders from MedStar Health, UCHealth, LucidHealth, and PocketHealth will share how they’re using AI to engage patients, close interoperability gaps, and improve follow-up. Get a preview and connect with them onsite to learn more.
|
|
- AI Trust Gap Divides Patients, Providers: Patients and healthcare providers have different levels of trust in medical AI. The latest iteration of Philips’ Future Health Index report queried 1.9k providers and 16k patients in 16 countries, finding that while 63% of providers agreed that AI could improve patient outcomes, only 48% of patients concurred. But AI optimism was higher among patients under 45 (66%) compared to older ones (33%). Building trust in medical AI among patients is key for successful adoption.
- AI Aids Opportunistic CAC Scoring at VA: A homegrown AI algorithm for calculating coronary artery calcium scores from noncontrast nongated CT scans performed well at Veterans Affairs medical centers. Writing in a study in NEJM: AI, VA researchers found that among 3.6k patients, their CAC algorithm showed higher 10-year all-cause mortality rates for patients with CAC scores >400 versus those with CAC scores of 0 (60% vs. 25%). When used opportunistically on 8.1k CT lung screening patients it found 38% would benefit from lipid-lowering therapy.
- Safety-Net AI Catches Missed Fractures: Radiologists in the Netherlands found that using Gleamer’s BoneView AI software as a safety net to re-evaluate negative fracture cases was the most effective of four implementation strategies. In a study of 1.2k patients in European Journal of Radiology, researchers found safety-net AI produced fewer false negatives than radiologists working without AI (0.07% vs. 2.7%) although false positives were higher (7.6% vs. 1.2%). The safety-net approach also beat standalone AI, AI problem-solving, and AI triage techniques.
- CCTA Auto-Positioning Helps RTs: An automated patient positioning system using 3D cameras in the CT scanning room could help radiologic technologists during CCTA exams. Writing in an article in Radiography, researchers used automated patient positioning on GE HealthCare’s Revolution Apex Elite scanner to position chest phantoms, achieving “near optimal” positioning accuracy with a mean vertical offset from isocenter of -1 mm (versus 19 mm for manual positioning) while improving image quality. Greater offsets can result in higher radiation dose to patients.
- Finding CT Lung Screening Candidates: Where else in the hospital can radiology find eligible candidates for CT lung cancer screening? Researchers analyzed 3.7k medical records of patients already being seen in their hospital, of whom 460 (12%) met screening guidelines. Most of the patients were from the emergency department (49%), followed by cardiology (44%), the pre-operative service line (39%), and orthopedics (14%). Of these, 17% got lung scans, higher than national rates and underscoring the importance of identifying at-risk patients within hospital IT systems.
- CT Shows Mucus Plugs Limit Lung Function: CT scans of COPD patients showed how mucus plugs can affect lung function over multiple years. Writing in a research letter in NEJM, researchers performed CT scans at baseline and then five years later, finding that lung function as measured by FEV1 fell the most in patients with mucus plugs that were persistently positive or newly formed (60 and 55 ml/year, respectively). The biggest drop in lung function occurred with patients in the persistently positive group who resumed smoking.
- Total-Body PET to Spur Tracer Development: The new generation of total-body PET scanners will spur development of PET radiotracers while boosting patient throughput and reducing radiation dose. So says a new article in Pharmacological Reviews that extols the modality’s benefits in scanning the entire body simultaneously. Sites with total-body PET scanners are reporting quantitative exams at doses under 0.5 mSv, supporting repeat studies of new tracers. Such low radiation doses also could make it possible to use PET as a screening tool.
- United Imaging’s Rad Therapy Play? United Imaging appears to be planning to enter the radiation therapy market in North America, tapping Guillaume Groussett as vice president of the business. Groussett previously was vice president of United Imaging’s CT division, and before that was with Siemens Healthineers for 23 years. United Imaging sells the uRT integrated CT/linear accelerator system globally, but the system does not have FDA clearance or the CE Mark. United has reserved a 50 x 60-foot booth at the upcoming ASTRO 2025 conference.
- Siemens to Move Rad Therapy Plant to U.S. Siemens Healthineers plans to spend $150M on U.S. manufacturing projects, including moving its Varian radiation therapy manufacturing plant from Mexico to Palo Alto, California, where the company will add 50 new manufacturing jobs. Siemens is transferring the operation to reduce the complexity of its global supply chain, and the move was cited by the Trump Administration as one of several projects that reflect the success of its trade policies.
- New GE Clearances: GE HealthCare is celebrating two recent FDA clearances, one for interventional radiology and the other for contrast ultrasound. The FDA cleared GE’s CleaRecon DL AI-based 3D reconstruction algorithm for cone-beam CT images acquired on the Allia interventional radiology system. The solution removes streak artifacts caused by arterial blood flow during CBCT acquisitions. Separately, GE got FDA approval for pediatric echocardiography indications with its Optison ultrasound contrast agent.
- NewVue Scores Calantic Alliance: NewVue.ai’s EmpowerSuite AI-based workflow software will be available on Bayer’s Calantic Digital Solutions AI orchestration platform under a new alliance between the companies. EmpowerSuite’s features include intelligent worklist, radiologist cockpit, and quality assurance tools. Separately, NewVue signed a contract to install EmpowerSuite at Baptist Health Central Alabama (becoming NewVue’s first Philips IntelliSpace PACS customer), and they also allied with MD.ai to embed that company’s reporting tools into EmpowerSuite.
- SIIM Updates Virtual Hospital Simulator: On the eve of SIIM 2025, the Society for Imaging Informatics in Medicine is unveiling an updated version of its Virtual Hospital Platform simulator. The simulator helps participants master medical image management in an immersive virtual hospital environment, and VHP 2.0 includes a streamlined interface and enhanced scalability while supporting more simultaneous users. SIIM 2025 attendees can test-drive the simulator at the SIIM booth in Portland.
- Leadership Changes at Segmed: Medical imaging AI data aggregator Segmed made several leadership changes last week. The company tapped medical industry veteran David Gascoigne as CEO, with previous CEO and co-founder Martin Willemink, MD, PhD, moving over to the chief scientific officer role, where he will focus on academic collaborations and advancing Segmed’s market presence. Segmed last year raised $10.4M in a Series A round to further commercialize its Openda platform.
- Heartflow’s FFR CT AI Results: New data published in Nature suggest using Heartflow’s FFR CT Analysis AI to evaluate the cardiac CT results of patients with chest pain is safe, effective, and could reduce unneeded downstream exams. Researchers reviewed two-year data from the FISH&CHIPS trial and found that Heartflow FFR CT Analysis reduced the use of invasive coronary angiography by 7% and reduced the use of unnecessary angiograms by 16% with no difference in all-cause mortality after two years.
- Hinton’s Mea Culpa on Radiologist AI: Noted AI futurist and Nobel Prize winner Geoffrey Hinton, PhD, last week issued a mea culpa (sort of) for his infamous 2016 prediction that AI would make radiologists obsolete by 2021. Hinton was quoted in a New York Times article on AI’s impact on radiology, admitting that he “spoke too broadly” nine years ago. He now believes that most medical image interpretation will be performed by “a combination of A.I. and a radiologist.”
|
|
Visit Enlitic at SIIM 2025
Visit Enlitic at SIIM 2025 at booth #530 to learn about their solutions for data standardization and migration, including their new partnership with GE HealthCare powering the data migration feature in GE’s new Genesis cloud portfolio. Book a demo today.
|
|
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.
|
|
Make the Most of Your SIIM Experience with Mach7
See innovations from Mach7 Technologies in action at SIIM 2025. Schedule a demo of their industry-leading eUnity Enterprise Diagnostic Viewer or explore their groundbreaking UnityVue radiology solution. Reach new heights in imaging informatics with Mach7 at booth #514-516.
|
|
- Visit Kailo Medical at SIIM 2025: Learn about the latest synoptic reporting solutions by visiting Kailo Medical at booth #539 at SIIM 2025. Book an appointment today to find out how their technology can make radiology reporting easier while maximizing efficiency.
- Unprecedented Insights Made Possible with AI: With the largest normative dataset of whole-body imaging in the world, Prenuvo’s AI researchers partner with the best academic minds to understand – like never before – what “normal” aging means. Learn about their work today.
- Meet Merge at SIIM 2025: Merge puts your workspaces, clinicians, and imaging transformation into focus. Explore their market-leading solutions at SIIM 2025 at booth #632, or schedule your visit today.
- See AGFA Innovations at SIIM 2025: Visit AGFA HealthCare at SIIM 2025 to see how their innovative approach to enterprise imaging is advancing diagnostic confidence, clinical collaboration, and operational efficiency across healthcare systems. Book a demo today or swing by booth #431-433.
- The Leader in Molecular Imaging: United Imaging’s uMI portfolio of solutions is designed to help you lead the way in molecular imaging. From digital PET/CT systems designed to stand the test of time to the cutting-edge uEXPLORER total-body PET scanner, discover the uMI difference today.
- Enhance Efficiency, Enhance Care: Find out how Optum’s cloud platform integrates effortlessly with your existing systems, boosting both care and efficiency. Visit now!
- Imaging Workflows that Actually Work: Not a fan of medical image exchange on discs? Then check out Clearpath and find out how it’s removing obstacles to better radiology workflow. Request a demo today.
- AI-Powered Early Breast Cancer Detection: DeepHealth parent RadNet is expanding its presence in mammography AI with its pending acquisition of iCAD. Find out how the transaction will accelerate AI-powered early detection and diagnosis of breast cancer on this page.
- A New Benchmark for Tomo Imaging: There’s a new benchmark for digital breast tomosynthesis 3D images with MAMMOMAT B.brilliant from Siemens Healthineers. The system’s 50° wide-angle tomosynthesis helps you achieve excellent outcomes for your patients, radiologists, and breast care professionals.
- Presenting Unboxing AI: Check out CARPL’s video series, Unboxing AI, featuring experts discussing AI and its future in radiology. The next episode on May 22 features Nathan Qin of Keya Medical – reserve your seat today.
- Partnership for AI-Automated Echo Analysis: Us2.ai partnered with Fujifilm Healthcare Americas to equip Fujifilm’s Lisendo 800 cardiovascular ultrasound scanner with Us2.ai’s AI-driven automated clinical workflow solution. Learn more on this page.
- Achieve More with AI You Can Trust: Visit Microsoft at SIIM 2025 to experience how Microsoft Cloud for Healthcare can empower your workforce and unlock insights. Request a meeting or stop by at booth #314-316.
- Connect with Calantic by Bayer at SIIM 2025: Visit Calantic by Bayer at SIIM 2025 to learn how they are helping clinicians leverage radiology AI to enhance the patient experience. See their schedule of presentations or book at meeting today at booth #231-235.
- The Future of Radiology: In this episode of The Radiology Report, Medality’s Daniel Arnold sits down with Marc Gosselin, MD, from Vision Radiology for a thought-provoking conversation on burnout, balance, and the future of radiology.
- 2 Questions about AI for Radiology Leaders: Are today’s radiology AI solutions solving the right problems? And are there other solutions available for AI of brain MRI? Read this article from SpinTech MRI to learn how their STAGE solution can optimize MRI utilization.
- Connect with Intelerad at SIIM 2025: Join Intelerad at booth #533 at SIIM 2025 to learn how they are redefining healthcare imaging with innovative solutions designed to provide a clear path to answers. Schedule your visit today.
- 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.
- MRI That’s Lighter, Faster, and Sharper: Rise above and experience MRI excellence with Philips BlueSeal, the industry’s lightest, vent pipe-free, high-performance, helium-free 1.5T scanner. Watch this video to see how it can benefit your practice.
|
|
|
|
|
